基于核方法的说话人辨认模型研究
|
摘要
说话人识别技术由于其独特的便利性、精确性和经济性,被认为是最自然的生物认证技术,在安全监控、司法鉴定、电子侦听、金融服务等方面都具有广泛的应用前景。当前,说话人识别系统开发已逐渐从理论研究转向实际应用,对其要求也随着应用环境的变更而越来越高,不仅期望具有极高的识别率,还要具有较高的实时性,此外,系统构建便捷性、模型扩展能力等都不容忽视。近十几年来,基于核函数的分类算法已成为模式识别领域的研究焦点,它有效克服了传统模式识别方法中局部极小和非完全统计分析的缺点,具有很强的非线性处理能力,而说话人识别系统中输入的语音特征参数正好是非线性的且局部特性复杂。因此,应用核分类模型于说话人识别时能够获得很好的效果。
本文针对说话人识别中的辨认任务,以小样本语料库为应用对象,着重研究模型域的改进,提出具有各种优势的核分类方法。主要工作如下:
1.深入分析当前主导的说话人识别模型GMM-UBM和SVM。产生性模型-高斯混合模型(GMM)一直作为说话人识别的基准技术,但其直接应用存在训练样本量需求过大的缺陷,而统一背景模型(UBM)可以削减目标说话人的输入数据,且效果更比单纯GMM优越。区分性模型-支持向量机(SVM)具有最大分类间隔、全局最优解、稀疏性能等优势,在小样本说话人识别应用中效果比GMM-UBM更佳。本文分别从原理、优缺点、融合策略、应用细节等几方面对两者作了细致地分析。通过说话人辨认实验表明,GMM-UBM模型的测试实时度稍逊,而两分类模型SVM的多元扩展能力较为薄弱。
2.联合相关向量机与高斯混合模型进行说话人辨认。相关向量机(RVM)分类模型与SVM具有一致的判决公式,同样有很强的泛化能力,并且其稀疏性更好;此外,RVM使用概率输出克服了SVM二值结果的缺点,又无需进行繁琐的惩罚因子C计算。但是在与文本无关的话者辨别中,RVM模型构建过程却过于缓慢。本文将二元模型RVM引入说话人辨认领域,并采用快速训练算法进行基于帧的话者识别。为进一步提升模型构建速率,取GMM统计特征参数作为RVM的输入矢量,既能够有效地提炼话者个体性信息,解决大样本数据情形中的RVM训练问题,又结合了统计模型鲁棒性高和分辨模型辨别效果好的优点。实验结果表明,RVM与SVM模型扩展能力一致,识别率相仿,但测试实时性能明显优于SVM。
3.提出多元核Logistic回归(MKLR)说话人辨认方法。虽然RVM与SVM都具有优秀的识别性能和测试实时度,但二元模型的本质使得两者都无法直接应用于说话人辨认。本文针对基于帧的与文本无关说话人辨认多分类目标和大训练样本的情况,将经典核Logistic回归(KLR)模型进行多元化变形,叠加L2惩罚因子,以提高模型泛化能力。把最优目标函数负对数Logistic公式对偶化,并利用序列最小优化算法进行模型训练,不仅保持了原KLR模型的强分辨能力,也加快了模型构建过程。实验结果表明,MKLR在辨认任务中无需进行繁复的多分类扩展,且识别率达到99.5%。
4.提出概率稀疏型多元核Logistic说话人辨认方法(SMKLC)。MKLR的缺陷是测试速率低下,因此,本文对经典Logistic回归模型进行多元化扩展后,为参数叠加RVM中采用的稀疏性先验概率分布,在不引入新的先验信息性参数前提下使模型具有稀疏结果。模型训练采用自下向上贪婪算法,规避了大型矩阵逆操作,约简了训练过程计算量。说话人辨认实验结果表明,SMKLC在保持高识别性能的同时,其测试用时仅需0.0057秒/短语。
5.提出保局部核Fisher鉴别说话人辨认方法(LWFDA)。结合核Fisher判别(KFD)方法与局部保持投影(LPP)两者的优势,将亲和因子引入KFD中的类内散度矩阵,保留KFD全局最优投影能力的同时,又凸现LPP的局部保持能力,对重叠(离群)样本与多态分簇样本都能实现有效的分类投影,并给出了快速求解算法,解决大样本训练时出现的内存溢出问题,以适应于说话人辨认。实验结果表明,LWFDA识别率与MKLR一致,测试用时较MKLR缩减了9.25%。
6.提出增强型数据域描述说话人辨认方法(EDDD)。为适应开集的辨认任务,以支持向量域描述(SVDD)算法为基础,通过一种简易的形式引入数据间密度因子,使处于不同区域的数据对分类器的作用不再被同等对待,高密度区数据对分类支撑域的作用被强化,而低密区即呈零星分布的数据作用被削弱,结果使分类超球体自动靠近数据高密区而提高其识别性能。说话人辨认实验结果表明,EDDD模型的识别性能全面优于GMM。
本文主要研究说话人辨认系统中的模型部分,提出或改进了各类基于核的分类方法,包括二元分类器、多元分类器、单类分类器、降维分类器等,它们各自都具有得天独厚的优势,能满足不同需求的说话人辨认系统。
Due to its special merits of flexibility, accuracy and economy, speaker recognition technology has been regarded as the most natural kind of biometrics, which has comprehensive perspective of applications in the field of security access, forensics evaluation, electronic sniff, financial services. Recently the speaker recognition system research has turned from theory to practice and people demands more and more with the change of circumstances. Seeking the higher recognition rate will never be the only criterion. The real-time quality can not be neglected as well as the convenience and expandability of the system model.
In recent ten years, many classification algorithms were proposed based on the kernel function, which effectively solved the drawbacks of local minimum and incomplete statistical analysis of the traditional pattern recognition model. These new algorithms always have super power of nonlinear capacity which can meet the speech feature’s demanding. So speaker recognition systems based on kernel method like the support vector machine have been proved to be very successful.
In this thesis, we focus on the improvement of the model domain and propose different kinds of kernel classification method which can be applied to the task of speaker identification in the circumstance of small sample speech corpus. The main contributions of the work are as follows:
1. Provided the analysis of the leading speaker recognition model, GMM-UBM and SVM. The generative model GMM is always the baseline technology for last decade, but it needs too many input speech data. The GMM-UBM can reduce the amount of the input data for target and has better effect than the GMM. The discriminative model SVM has lots of merits including maximum classification margin, global solution and sparsity. When applied to the small sample speaker recognition system, it has even better result than the GMM-UBM. We deeply analyzed the principle and performances and mixture strategy and application details of these models. The last experiments show that GMM-UBM’s test speed is low and SVM has poor expandability for multi-class classification.
2. Proposed the hybrid strategy of GMM and RVM for speaker identification. Relevance vector machine classification method uses the probabilistic output to overcome SVM’s shortage as well as has more sparsity. Whereas RVM has overloaded computation complexity and memory storage when applied for the text-independent speaker identification because of the mass training samples. For solving this problem, a hybrid GMM/RVM approach is proposed which can effectively extract the speaker feature vector as well as solve the mass storage problem. Further more; this hybrid approach combines the robustness of generative model and the powerful classification of discriminative model to improve the performance and robustness of identification.The experiments prove that this method has better error rate than the GMM system and more sparsity than state-of- the-art GMM/SVM system.
3. Proposed the multi-class kernel logistic regression speaker identification model. The traditional logistic regression model is transformed to multi-class kernel logistic model applying for text-independent speaker identification, which is nonlinear and more than just two classes. The L 2 penalty factor is added for enhancing model generalization ability. Then a new iterative algorithm is proposed based on the solution of a dual problem using ideas similar to those of the Sequential Minimal Optimization algorithm for SVM. Experiments show that the algorithm is robust and fast and the recognition rate is as good as widely used methods such as SVM while being used in text-independent speaker identification.
4. Proposed the probabilistic sparse kernel logistic speaker identification model. A true sparse multiclass formulation was introduced based on multinomial logistic regression which incorporates weighted sums of basis functions with sparsity-promoting priors encouraging the weight estimates to be either significantly large or exactly zero. Then the bottom-up training algorithm is adopted which controls the capacity of the learned classifier by minimizing the number of basis functions used, resulting in better generalization and faster computation. Experimental results on standard benchmark data sets and speaker identification show the proposed method has best real-time ability.
5. Proposed the local within-class features preserving kernel fisher discriminant algorithm and applied in speaker identification. Dimensionality reduction without losing intrinsic information on original data is an important technique for succeeding tasks such as classification. A novel algorithm is proposed after deeply analysis on the relationship between kernel fisher discriminant and kernel local preservation projection. The new method keeps the ability of KFD’s global projection and introduces the local preservation ability of LPP, which can work well on overlapped or multimodal labeled data. The training algorithm is improved for resolving out-of-memory problem when applied in large sample situation. The speaker identification application shows that the proposed algorithm has more adaptability as well as advanced recognition rate and speed.
6. Proposed the enhanced data domain description speaker identification method. The purpose of data description is to give a compact description of the target data that represents most of its characteristics. In a support vector data description (SVDD), the compact description of target data is given in a hyperspherical model, which is determined by a small portion of data called support vectors. Despite the usefulness of the conventional SVDD, however, it may not identify the optimal solution of target description especially when the support vectors do not have the overall characteristics of the target data. To address the issue in SVDD methodology, the enhanced SVDD is proposed introducing new distance measurements based on the notion of a relative density degree for each data point in order to reflect the distribution of a given data set. Experiments are made for comparison between GMM and the proposed enhanced SVDD because they both can apply for open-set speaker identification, the results show that the enhanced SVDD outperforms the GMM whenever in recognition rate, real-time ability and sample demanding.
本文针对说话人识别中的辨认任务,以小样本语料库为应用对象,着重研究模型域的改进,提出具有各种优势的核分类方法。主要工作如下:
1.深入分析当前主导的说话人识别模型GMM-UBM和SVM。产生性模型-高斯混合模型(GMM)一直作为说话人识别的基准技术,但其直接应用存在训练样本量需求过大的缺陷,而统一背景模型(UBM)可以削减目标说话人的输入数据,且效果更比单纯GMM优越。区分性模型-支持向量机(SVM)具有最大分类间隔、全局最优解、稀疏性能等优势,在小样本说话人识别应用中效果比GMM-UBM更佳。本文分别从原理、优缺点、融合策略、应用细节等几方面对两者作了细致地分析。通过说话人辨认实验表明,GMM-UBM模型的测试实时度稍逊,而两分类模型SVM的多元扩展能力较为薄弱。
2.联合相关向量机与高斯混合模型进行说话人辨认。相关向量机(RVM)分类模型与SVM具有一致的判决公式,同样有很强的泛化能力,并且其稀疏性更好;此外,RVM使用概率输出克服了SVM二值结果的缺点,又无需进行繁琐的惩罚因子C计算。但是在与文本无关的话者辨别中,RVM模型构建过程却过于缓慢。本文将二元模型RVM引入说话人辨认领域,并采用快速训练算法进行基于帧的话者识别。为进一步提升模型构建速率,取GMM统计特征参数作为RVM的输入矢量,既能够有效地提炼话者个体性信息,解决大样本数据情形中的RVM训练问题,又结合了统计模型鲁棒性高和分辨模型辨别效果好的优点。实验结果表明,RVM与SVM模型扩展能力一致,识别率相仿,但测试实时性能明显优于SVM。
3.提出多元核Logistic回归(MKLR)说话人辨认方法。虽然RVM与SVM都具有优秀的识别性能和测试实时度,但二元模型的本质使得两者都无法直接应用于说话人辨认。本文针对基于帧的与文本无关说话人辨认多分类目标和大训练样本的情况,将经典核Logistic回归(KLR)模型进行多元化变形,叠加L2惩罚因子,以提高模型泛化能力。把最优目标函数负对数Logistic公式对偶化,并利用序列最小优化算法进行模型训练,不仅保持了原KLR模型的强分辨能力,也加快了模型构建过程。实验结果表明,MKLR在辨认任务中无需进行繁复的多分类扩展,且识别率达到99.5%。
4.提出概率稀疏型多元核Logistic说话人辨认方法(SMKLC)。MKLR的缺陷是测试速率低下,因此,本文对经典Logistic回归模型进行多元化扩展后,为参数叠加RVM中采用的稀疏性先验概率分布,在不引入新的先验信息性参数前提下使模型具有稀疏结果。模型训练采用自下向上贪婪算法,规避了大型矩阵逆操作,约简了训练过程计算量。说话人辨认实验结果表明,SMKLC在保持高识别性能的同时,其测试用时仅需0.0057秒/短语。
5.提出保局部核Fisher鉴别说话人辨认方法(LWFDA)。结合核Fisher判别(KFD)方法与局部保持投影(LPP)两者的优势,将亲和因子引入KFD中的类内散度矩阵,保留KFD全局最优投影能力的同时,又凸现LPP的局部保持能力,对重叠(离群)样本与多态分簇样本都能实现有效的分类投影,并给出了快速求解算法,解决大样本训练时出现的内存溢出问题,以适应于说话人辨认。实验结果表明,LWFDA识别率与MKLR一致,测试用时较MKLR缩减了9.25%。
6.提出增强型数据域描述说话人辨认方法(EDDD)。为适应开集的辨认任务,以支持向量域描述(SVDD)算法为基础,通过一种简易的形式引入数据间密度因子,使处于不同区域的数据对分类器的作用不再被同等对待,高密度区数据对分类支撑域的作用被强化,而低密区即呈零星分布的数据作用被削弱,结果使分类超球体自动靠近数据高密区而提高其识别性能。说话人辨认实验结果表明,EDDD模型的识别性能全面优于GMM。
本文主要研究说话人辨认系统中的模型部分,提出或改进了各类基于核的分类方法,包括二元分类器、多元分类器、单类分类器、降维分类器等,它们各自都具有得天独厚的优势,能满足不同需求的说话人辨认系统。
Due to its special merits of flexibility, accuracy and economy, speaker recognition technology has been regarded as the most natural kind of biometrics, which has comprehensive perspective of applications in the field of security access, forensics evaluation, electronic sniff, financial services. Recently the speaker recognition system research has turned from theory to practice and people demands more and more with the change of circumstances. Seeking the higher recognition rate will never be the only criterion. The real-time quality can not be neglected as well as the convenience and expandability of the system model.
In recent ten years, many classification algorithms were proposed based on the kernel function, which effectively solved the drawbacks of local minimum and incomplete statistical analysis of the traditional pattern recognition model. These new algorithms always have super power of nonlinear capacity which can meet the speech feature’s demanding. So speaker recognition systems based on kernel method like the support vector machine have been proved to be very successful.
In this thesis, we focus on the improvement of the model domain and propose different kinds of kernel classification method which can be applied to the task of speaker identification in the circumstance of small sample speech corpus. The main contributions of the work are as follows:
1. Provided the analysis of the leading speaker recognition model, GMM-UBM and SVM. The generative model GMM is always the baseline technology for last decade, but it needs too many input speech data. The GMM-UBM can reduce the amount of the input data for target and has better effect than the GMM. The discriminative model SVM has lots of merits including maximum classification margin, global solution and sparsity. When applied to the small sample speaker recognition system, it has even better result than the GMM-UBM. We deeply analyzed the principle and performances and mixture strategy and application details of these models. The last experiments show that GMM-UBM’s test speed is low and SVM has poor expandability for multi-class classification.
2. Proposed the hybrid strategy of GMM and RVM for speaker identification. Relevance vector machine classification method uses the probabilistic output to overcome SVM’s shortage as well as has more sparsity. Whereas RVM has overloaded computation complexity and memory storage when applied for the text-independent speaker identification because of the mass training samples. For solving this problem, a hybrid GMM/RVM approach is proposed which can effectively extract the speaker feature vector as well as solve the mass storage problem. Further more; this hybrid approach combines the robustness of generative model and the powerful classification of discriminative model to improve the performance and robustness of identification.The experiments prove that this method has better error rate than the GMM system and more sparsity than state-of- the-art GMM/SVM system.
3. Proposed the multi-class kernel logistic regression speaker identification model. The traditional logistic regression model is transformed to multi-class kernel logistic model applying for text-independent speaker identification, which is nonlinear and more than just two classes. The L 2 penalty factor is added for enhancing model generalization ability. Then a new iterative algorithm is proposed based on the solution of a dual problem using ideas similar to those of the Sequential Minimal Optimization algorithm for SVM. Experiments show that the algorithm is robust and fast and the recognition rate is as good as widely used methods such as SVM while being used in text-independent speaker identification.
4. Proposed the probabilistic sparse kernel logistic speaker identification model. A true sparse multiclass formulation was introduced based on multinomial logistic regression which incorporates weighted sums of basis functions with sparsity-promoting priors encouraging the weight estimates to be either significantly large or exactly zero. Then the bottom-up training algorithm is adopted which controls the capacity of the learned classifier by minimizing the number of basis functions used, resulting in better generalization and faster computation. Experimental results on standard benchmark data sets and speaker identification show the proposed method has best real-time ability.
5. Proposed the local within-class features preserving kernel fisher discriminant algorithm and applied in speaker identification. Dimensionality reduction without losing intrinsic information on original data is an important technique for succeeding tasks such as classification. A novel algorithm is proposed after deeply analysis on the relationship between kernel fisher discriminant and kernel local preservation projection. The new method keeps the ability of KFD’s global projection and introduces the local preservation ability of LPP, which can work well on overlapped or multimodal labeled data. The training algorithm is improved for resolving out-of-memory problem when applied in large sample situation. The speaker identification application shows that the proposed algorithm has more adaptability as well as advanced recognition rate and speed.
6. Proposed the enhanced data domain description speaker identification method. The purpose of data description is to give a compact description of the target data that represents most of its characteristics. In a support vector data description (SVDD), the compact description of target data is given in a hyperspherical model, which is determined by a small portion of data called support vectors. Despite the usefulness of the conventional SVDD, however, it may not identify the optimal solution of target description especially when the support vectors do not have the overall characteristics of the target data. To address the issue in SVDD methodology, the enhanced SVDD is proposed introducing new distance measurements based on the notion of a relative density degree for each data point in order to reflect the distribution of a given data set. Experiments are made for comparison between GMM and the proposed enhanced SVDD because they both can apply for open-set speaker identification, the results show that the enhanced SVDD outperforms the GMM whenever in recognition rate, real-time ability and sample demanding.
引文
[1] Anil K J, Feng J J, Karthik N. Fingerprint matching [J]. Computer, 2010, 43(2): 36-44.
[2] Sun Z N, Tan T N. Ordinal measures for iris recognition [J]. IEEE Transactions on pattern Analysis and Machine Intelligence, 2009, 31(12): 2211-2226.
[3] Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[4] Xu X, Mu Z. Feature fusion method based on KCCA for ear and profile face based multimodal recognition [A]. Proceeding of the IEEE International Conference on Automation and Logistics[C]. Jinan, China, 2007.
[5]高志贤,周焕英,何永红. DNA在生物传感器金电极上的固定化技术研究进展[J].中华预防医学杂志, 2009, 43(12): 1109-1113.
[6]陈实,马天骏,高有行.用行人轮廓的分布直方图分类和识别步态[J].计算机研究与发展, 2009, 46(2): 295-301.
[7] Zhang D, Lu G M, Li W, et al. Palmprint recognition using 3-D information [J]. IEEE Transaction on System, Man and Cybernetics, Part C: Applications and Review, 2009, 39(5): 505-519.
[8] Gong W G, Yang L P, Chen D. Pitch synchronous based feature extraction for noise-robust speaker verification [A]. Congress on Image and Signal Processing[C]. 2008: 295-298.
[9] Zulfiqar A, Muhammad A, Enriquez A M M. A speaker identification system using MFCC features with VQ technique [A]. 3rd International Symposium on Intelligent Information Technology Application[C]. 2009, vol. 3: 115-118.
[10]陈渤.基于核方法的雷达高分辨距离像目标识别技术研究[D].西安:西安电子科技大学, 2008.
[11] Louradour, J. and K. Daoudi, State-of-the-art sequence kernels for SVM speaker verification [A]. IEEE Workshop on Machine Learning for Signal Processing[C]. Cancun, 2008: 498--503.
[12]于雪莲.基于核方法和流形学习的雷达目标距离像识别研究[D].成都:电子科技大学, 2008.
[13]任双桥.支撑矢量机理论与应用研究[D].长沙:国防科学技术大学, 2006.
[14]周晓飞.几种新型分类器设计及其在人脸识别应用中的研究[D].南京:南京理工大学, 2008.
[15]李青.优化核方法[D].西安:电子科技大学, 2006.
[16] Zhen B, Wu X H, Liu Z M, Chi H S, On the importance of components of the MFCC in speech and speaker recognition [J]. Acta Scicentiarum Naturalum Universities Pekinesis, 2001, 37(3): 371–378.
[17] Zhu J W, Sun S F, Dan Z P, et al. MFCC extraction based on F-Ratio and correlated distance criterion in speaker recognition [A]. International Conference on Multimedia Information Networking and Security[C], 2009.
[18] Zeng Yu-Min W Z. Combination of Pitch synchronous analysis and fisher criterion for speaker identification [J]. Journal of Electronics. 2007, 24(6): 828-834.
[19] Wang C, Miao Z, Meng X. Differential MFCC and vector quantization used for real-time speaker recognition system [A]. 1st International Congress on Image and Signal Processing[C], Sanya, Hainan, China, 2008.
[20] Grimaldi M, Cummins F. Speaker identification using instantaneous frequencies [J]. IEEE Transactionson Audio, Speech, and Language Processing. 2008, 16(6): 1097-1111.
[21] Long Y H, Ma B, Li H Z, et al. Exploiting prosodic information for Speaker Recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009: 4225-4228.
[22] Qiu Z Q, Yin J X, Fan C Y. Using redundant parallel architecture to improve speaker recognition performance [J]. Control Theory Application. 2008, 6(2): 221-223.
[23] Truong T K, Lin C C, Chen S H, et al. Feature comparison among various wavelets in speaker recognition using support vector machine [A]. Proceedings of the 8th IEEE International Symposium on Multimedia[C]. Washington, DC, USA: IEEE Computer Society, 2006: 811-816.
[24] Claussen H, Rosca J, Damper R. Mutual features for robust identification and verification [A]. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Las Vegas, NV, USA, 2008: 1849-1852.
[25] Liu Y L, Yang H W, Zhou H. Speaker identification based on EMD [A]. IEEE International Conference on Network Infrastructure and Digital Content[C], 2009.
[26] Thiruvaran T, Ambikairajah E, Epps J. Extraction of FM components from speech signals using all-pole model [J]. Electronics Letters. 2008, 44(6): 448-449.
[27] Das A, Manyam O K, Tapaswi M, et al. Multilingual spoken-password based user authentication in emerging economies using cellular phone networks [A]. In proceedings of the IEEE Workshop on Spoken Language Technology (SLT)[C], Goa, India, 2008: 5-8.
[28] Gudnason J, Brookes M. Voice source Cepstrum coefficients for speaker identification [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Las Vegas, NV, USA, 2008: 4821-4824.
[29] Kalgaonkar K, Raj B. Ultrasonic Doppler sensor for speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Las Vegas, NV, USA, 2008.
[30] Centingul H E, Yemez Y, Engin E, et al. Discriminative analysis of lip motion features for speaker identification and speech-reading [J]. IEEE Transactions on Image Processing, 2006, 15(10): 2879-2891.
[31] Faraj M I, Bigun J. Synergy of Lip-Motion and acoustic features in biometric speech and speaker recognition [J]. IEEE Transactions on Computers, 2007, 56(9): 1169-1175.
[32]吴朝晖,杨莹春.说话人识别模型与方法[M].北京:清华大学出版社, 2009.
[33] Chao Y H, Wang H M, Chang R C. Gmm-based Bhattacharyya kernel fisher discriminant analysis for speaker recognition [A]. International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 2005.
[34] Campbell W M, Campbell J P, Reynolds D A, et al. Support vector machines for speaker and language recognition [J]. Computer Speech & Language, 2006, 20(2/3): 210-229.
[35] Moreno P J, Ho P P. A new SVM approach to speaker identification and verification using probabilistic distance kernels [C]. EUROSPEECH, 2003.
[36] You C H, Lee K A, Li H. A GMM supervector kernel with the Bhattacharyya distance for SVM based speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C], Taipei, Taiwan, 2009: 4221-4224.
[37] Campbell W M, Sturim D E, Reynolds D A. Support vector machines using GMM supervector for speaker verification [J]. IEEE Signal Processing Letters, 2006, 13(5): 308-311.
[38] Campbell W M, Campbell J P, Gleason T P, et al. Speaker verification using support vector machinesand high-level features [J]. IEEE Transaction on Audio, Speech, and Language Processing, 2007, 15(7): 2085-2094.
[39]刘明辉,戴蓓蒨,解焱陆,等.基于GMM多维概率输出的SVM话者确认[J].模式识别与人工智能, 2008, 21(1): 28-32.
[40] Zhao Z D, Zhang J, Tian J F, et al. An effective identification method for speaker recognition based on PCA and double VQ [A]. Proceeding of the 8th International Conference on Machine Learning and Cybernetics[C], Baoding, 2009.
[41] Lin L, Wang S. A Kernel method for speaker recognition with little data [A]. 8th International Conference on Signal Processing[C]. 2006, 1.
[42]崔连延,徐林,顾树生,等.基于减法聚类与改进的模糊C-均值聚类算法的说话人识别方法的研究[J].信息与控制. 2008, 37(3): 358-361.
[43]林琳,王树勋,陈建,等.基于可区分性加权的模糊核说话人识别[J].电子学报. 2008, 36(7): 1446-1450.
[44]白莹,赵振东,戚银城,等.基于小波神经网络的与文本无关说话人识别方法研究[J].电子与信息学报. 2006(06): 1036-1039.
[45]姚潇,武妍,王守觉,等.一种基于并行覆盖前馈优先神经网络的说话人识别方法[J].计算机科学. 2008, 35(8): 125-128.
[46] Joshi S, Prahallad K, Yegnanarayana. AANN-HMM models for speaker verification and speech recognition [A]. In Proceedings of International Joint Conference on Neural Networks[C], 2008.
[47]陈存宝,赵力.嵌入自联想神经网络的高斯混合模型说话人辨认[J].电子与信息学报, 2010, 32(3): 528-532.
[48] Li R, Ji W J, Zhang L, et al. An improved quantum-behaved particle swarm classifier based on weighted mean best position [A]. IEEE International Conference on Intelligence Computing and Intelligent Systems[C], Shanghai, 2009: 327-331.
[49]陈刚,陈莘萌,向广利,等.基于非参数独立分量分析的说话人识别方法[J].计算机科学. 2006, 33(3): 167-170.
[50] Waghmare R K, Asutkar V G. Advance statistical modeling for speaker verification [A]. IEEE Conference on Industrial Electronics and Applications[C], Singapore, 2008: 2535-2539.
[51] Tarakanov A O. Immunocomputing for Speaker Recognition [M]. Springer Berlin/Heidelberg, 2010, Vol. 263.
[52] Bimbot F, Bonastre J F, Fredouille C, et al. A tutorial on text-independent speaker verification [J]. EURASIP Journal on Applied Signal Processing, 2004, 4: 430-451.
[53] Yuan D, Lu L, Zhao X Y, et al. Studies on model distance normalization approach in text-independent speaker verification [J]. ACTA Automatic Sinica. 2009, 35(5): 556-560.
[54] Zhao J, Dong Y, Zhao X Y, et al. Cross similarity measurement for speaker adaptive test normalization in text-independent speaker verification [J]. The Journal of China Universities of Posts and Telecommunications, 2008, 15(2): 130-134.
[55] Castro D R, Aguilar J F, Rodriguez J G, et al. Speaker verification using speaker- and test-dependent fast score normalization [J]. Pattern Recognition Letters, 2007, 28(1): 90-98.
[56]王琳琳,张利鹏,徐明星.基于分数规整的发音方式鲁棒的说话人识别[J].清华大学学报(自然科学版). 2009, 49(S1): 1278-1282.
[57]邱政权,尹俊勋,杨俊.在噪声环境下的分级说话人辨识[J].控制与决策. 2007, 22(5): 581-584.
[58] Wang W L, Zheng J W, Wang L. Improved wavelet pre-enhancement and hybrid model applied in speech recognition system [A]. 7th Asian Control Conference, Hong Kong, China, 2009.
[59]田斌,易克初.一种用于强噪声环境下语音识别的含噪Lombard及Loud语音补偿方法[J].声学学报, 2003, 28(1): 28-32.
[60] Pullella D, Kuhne M, Togneri R. Robust speaker identification using combined feature selection and missing data recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing, part11, Las Vegas, NV, USA, 2008.
[61]龙艳花,郭武,戴礼荣,等.一种基于说话者话路变化的主成分分析方法[J].模式识别与人工智能. 2009, 22(2): 270-274.
[62] Zou X, Jancovic P, Kokuer M. On the effectiveness of the ICA-based signal representation in non-Gaussian noise [A]. 9th International Conference on Signal Processing[C]. Beijing, 2008.
[63] Saon G, Padmanabhan M, Gopinath R, et al. Maximum likelihood discriminant feature spaces [A]. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing[C]. 2000, 2: 1129-1132.
[64]徐利敏,唐振民,何可可,钱博.基于自适应直方图均衡化的鲁棒性说话人辨认研究[J].自动化学报. 2008, 34(7): 752-759.
[65] Hansen J H L, Varadarajan V. Analysis and compensation of Lombard speech across noise type and Levels with application to In-Set/Out-of-Set speaker recognition [J]. IEEE transactions on audio, speech and language processing. 2009, 17(2): 366-378.
[66] Peer I, Rafaely B, Zigel Y. Reverberation matching for speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing, part 11[C]. Las Vegas, NV, USA, 2008: 4829-4832.
[67]包永强,赵力,邹采荣,等.采用归一化补偿变换的与文本无关的说话人识别[J].声学学报. 2006, 31(1): 55-60.
[68] Chen K. Towards better making a decision in speaker verification [J]. Pattern Recognition, 2003, 36(2): 329-346.
[69]高荣春,韩纪庆,张磊,等.说话人识别中基于最大后验概率的通道补偿方法[J].通信学报. 2009, 30(3): 99-103.
[70] Shabtai N R, Zigel Y, Rafaely B. The effect of GMM order and CMS on speaker recognition with reverberant speech [A]. Hands-Free Speech Communication and Microphone Arrays[C], Trento, 2008: 144-147.
[71] Gong Y E. Speech recognition in noisy environments: a survey [J]. Speech Communication, 1995, 16: 261-291.
[72] Guo W, Dai L R. Feature mapping based on GMM supervector [A]. International Conference on Audio, Language and Image Processing[C]. Shanghai, 2008: 1081-1085.
[73] Bing Xiang, Upendra V C, Ji R N. Short-time gaussianization for robust speaker verification [A]. Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing[C]. 2002: 681-684.
[74] Dehak N, Dumouchel P, Kenny P. Modeling prosodic features with joint factor analysis for speaker verification [J]. IEEE Transactions on Audio, Speech, and Language Processing, 2007, 15(7): 2095-2103.
[75] Campbell W M, Sturim D E, Reynolds D A, et al. SVM based speaker verification using a GMM supervector kernel and NAP variability compensation [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Toulouse, France, 2006, vol. 1.
[76] Deng J, Zheng T F, Wu W H. Session variability subspace projection based model compensation for speaker verification [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. 2007, 4: 57-60.
[77]郭武,戴礼荣,王仁华,等.说话人识别中的串行因子分析[J].模式识别与人工智能. 2009, 22(4): 514-518.
[78]李冬冬,吴朝晖,杨莹春,等.基于基频的情感语音聚类的说话人识别方法[J].模式识别与人工智能. 2009, 22(1):136-140.
[79] Zhang C, Hansen J. Analysis and classification of speech model: whispered through shouted [A]. Proceeding of Interspeech[C]. Antwerp, 2007.
[80] Nakagawa S, Zhang W. Takahashi M. Text-independent speaker recognition by combining speaker-specific GMM with speaker adapted syllable-based HMM [A]. Proceeding of International Conference on Acoustics, Speech and Signal Processing[C]. Montreal, 2004.
[81] Akbacak M, Hansen J. Languge normalization for bilingual speaker recognition systems [A]. Proceeding of International Conference on Acoustics, Speech and Signal Processing[C]. Hawaii, 2007.
[82] Guo W, Long Y, Li Y, et al. iFLY system for the NIST 2008 speaker recognition evaluation[A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009: 4209-4212.
[83]李战明,陈迪.一种基于小波神经网络混合模型的说话人识别方法[J].兰州理工大学学报, 33(2): 77-80.
[84] Yoma N B, Sanchez J S. MAP speaker adaptation of state duration distributions for speech recognition [J]. IEEE Transaction on Speech and Audio Processing, 2002, 10(7): 443-450.
[85] Ferras M, Barras C, Gauvain J L. Lattice-based MLLR for speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009: 4537-4540.
[86] Song H J, Jeong Y, Kim H S. A new method for speaker adaptation using bilinear model [A]. IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei, Taiwan, 2009: 4365-4368.
[87] Wan V, Renals S. Speaker verification using sequence discriminant support vector machines [J]. IEEE Transactions on Speech and Audio Processing. 2005, 13(2): 203-210.
[88] Campbell W M, Sturim D E, Reynolds D A. Support vector machines using GMM supervectors for speaker verification [J]. IEEE Signal Processing Letters. 2006, 13(5): 308-311.
[89] Weston J, Watkins C. Support vector machines for multi-class pattern recognition [A]. In: Proceedings of the European Symposium on Artificial Neural Networks[C]. Bruges, 1999: 219-224.
[90] Liu Yang, Wang R, Zeng Y S. An improvement of one-against-one method for multi-class support vector machine [A]. International Conference on Machine Learning and Cybernetics[C]. Hong Kong, 2007: 2915-2920.
[91]刘波,郝志峰,肖燕珊.交互迭代一对一分类算法[J].模式识别与人工智能, 2008, 21(4): 425-431.
[92] Qin Y P, Wang X K. Study on multi-label text classification based on SVM [A]. 6th International Conference on Fuzzy Systems and Knowledge Discovery[C]. Tianjin, 2009: 300-304.
[93] Pimenta E, Gama J. A study on error correcting output codes [A]. Portuguese Conference on Artificial Intelligence[C]. Covilha, 2005: 218-223.
[94]尹安容,谢湘,匡镜明,等. Hadamard纠错码结合支持向量机在多分类问题中的应用[J].电子学报. 2008, 36(1): 122-126.
[95]张永.基于模糊支持向量机的多类分类算法研究[D].大连:大连理工大学, 2008.
[96] Tipping M E, Smola A. Sparse Bayesian learning and the relevance vector machine [J]. Journal of Machine Learning Research, 2001, 1(3): 211-244.
[97] Tipping M E, Faul A. Fast marginal likelihood maximization for sparse Bayesian models [A]. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, 2003.
[98]陈佳,颜学峰,钱锋.基于贝叶斯学习的关联向量机及其在软测量中的应用[J].华东理工大学学报:自然科学版. 2007, 33(001): 115-119.
[99] Wipf D, Nagarajan S. Beamforming using the relevance vector machine [A]. Proceedings of the 24th international conference on Machine learning[C]. Corvalis, Oregon, 2007, 1023-1030.
[100]方红,王年,章权兵,等.基于稀疏贝叶斯学习的图像重建方法[J].中国图象图形学报. 2009, 14(6): 1064-1069.
[101] Din E R, Zeng P, Yao Y. Estimation of illumination chromaticity via adaptive reduced relevance vector machine [J]. Journal of Southeast University (English Edition). 2007, 23(2): 202-205.
[102]成萍,司锡才,姜义成,等.基于稀疏贝叶斯学习的稀疏信号表示ISAR成像方法[J].电子学报. 2008, 36(3): 547-550.
[103]张旭东,陈锋,高隽,等.稀疏贝叶斯及其在时间序列预测中的应用[J].控制与决策. 2006, 21(5): 585-588.
[104]张旭东,钱玮,高隽,等.基于稀疏贝叶斯分类器的汽车车型识别[J].小型微型计算机系统. 2005, 26(10): 1839-1841.
[105] Mahalo P M B, Sayadiyan A, Faez K. Mixed type audio classification using sinusoidal parameters [A]. 3rd International Conference on Information and Communication Technologies: From Theory to Applications[C]. Damascus, Syria, 2008.
[106] Babaeean A, Tashk A B, Bandarabadi M, et al. Target tracking using wavelet features and RVM classifier [A]. Proceedings of the 2008 4th International Conference on Natural Computation[C]. Washington, DC, USA: IEEE Computer Society, 2008, 569-572.
[107] Tang H, Chen Z, Huang T S, et al. Comparison of algorithms for speaker identification under adverse far-field recording conditions with extremely short utterances [A]. IEEE International Conference on Networking, Sensing and Control[C]. Sanya, 2008, 796-801.
[108]丁二锐,曾平,丁阳,等.一种新的回归型约简多分辨率相关向量机[J].控制与决策. 2008(1): 65-69.
[109] Tipping M. The relevance vector machine [J]. Advances in Neural Information Processing System, 2000, 12: 652-658.
[110] Tipping M E, Faul A. Fast marginal likelihood maximization for sparse Bayesian models [A]. In: Proc. 9th Int. Workshop Artif. Intell[C]. Statist, Key West, FL, 2003.
[111] Faul A C, Tipping M E. Analysis of sparse Bayesian learning [A]. In: Dietterich T G, Bechker S, Ghahramani Z. Advances in Neural Information Processing Systems 14[C]. Cambridge, MA, USA: MIT Press, 2002: 383-390.
[112]王炜,吕萍,颜永红,等.一种改进的基于层次聚类的说话人自动聚类算法[J].声学学报. 2008, 33(1): 9-14.
[113] You C H, Lee K A, Li H. An SVM kernel with GMM-supervector based on the Bhattacharyya distance for speaker recognition [J]. IEEE Signal Processing Letters. 2009, 16(1): 49-52.
[114] Louradour J, Daoudi K. State-of-the-art sequence kernels for SVM speaker verification [A]. IEEE Workshop on Machine Learning for Signal Processing[C]. Cancun, 2008: 498-503.
[115] Chang C C, Lin C J. LIBSVM: a library for support vector machines [CP]. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm, Version 2.9, 2009.
[116]李滔,王俊普,吴秀清.基于特征矢量集的核Logistic回归[J].小型微型计算机系统, 2007, 27(6): 980-985.
[117] Park M Y, Hastie T. Penalized logistic regression for detecting gene interactions [J]. Biostatistics. 2007, 9(1): 30-50.
[118] Li L, Leung H. Using the number of faults to improve fault-proneness prediction of the probability models [A]. World Congress on Computer Science and Information Engineering, LosAngeles[C], California, USA, 2009.
[119] Birkenes O, Matsui T, Tanabe K. Isolated-word recognition with penalized logistic regression machines [A]. Proc. ICASSP[C], 2006.
[120] Siniscalchi S M, Svendsen T, Lee C H. A penalized logistic regression approach to detection based phone classification [A]. 9th Annual Conference of the International Speech Communication Association[C], Brisbane, Australia, 2008.
[121]李滔,王俊普,吴秀清,等.后验概率估计及其应用:基于核Logistic回归的方法[J].模式识别与人工智能. 2006, 19(6): 689-695.
[122] Rahayu S P, Purnami S W, Embong A. Applying kernel logistic regression in data mining to classify credit risk [A]. International Symposium on Information Technology[C], Kuala Lumpur, Malaysia, 2008, vol. 2, pp: 1-6.
[123] Karsmakers P, Pelckmans K, Suykens J, et al. Fixed-Size kernel logistic regression for phoneme classification [A]. 8th Annual Conference of the International Speech Communication Association[C]. Antwer, Belgium, 2007.
[124] EI Naqa I, Bradley J D, Deasy J O. Nonlinear kernel-based approaches for predicting normal tissue toxicities [A]. Proceedings of the 7th International Conference on Machine Learning and Applications[C]. Washington, DC, USA: IEEE Computer Society, 2008, 539-544.
[125] Lin C J, Weng R C, Keerthi S S. Trust region newton method for logistic regression [J]. The Journal of Machine Learning Research. 2008, 9: 627-650.
[126] Koh K, Kim S, Boyd S. A method for large-scale l1-regularized logistic regression [A]. Proceedings of the 22nd international conference on Artificial intelligence[C]. Vancouver, British Columbia, Canada: AAAI Press, 2007, 565-571.
[127] Koh K, Kim S, Boyd S. An interior-point method for large-scale l1-regularized logistic regression [J]. Journal of Machine Learning Research. 2007, 8: 1519-1555.
[128] Yajima Y, Sato T. Semi-supervised kernel logistic regression and its extension to active learning based on A-Optimality [A]. 7th IEEE International Conference on Data Mining[C]. Omaha, NE, 2007.
[129] HoiSCH, Jin R, Lyu M R. Batch mode active learning with applications to text categorization and image retrieval [J]. Knowledge and Data Engineering, IEEE Transactions on. 2009, 21(9): 1233-1248.
[130] Karsmakers P, Pelckmans K, Suykens J A K. Multi-class kernel logistic regression: a fixed-size implementation [A]. Proc. International Joint Conference on Neural Networks[C], Orlando, Florida,USA, August, 2007.
[131] Katz M, Schaffoner M, Andelic E, Kruger S E, Wendemuth A. Sparse kernel logistic regression using incremental feature selection for text-independent speaker identification [A]. Proc. Speaker and Language Recognition workshop[C], San Juan, 2006.
[132] Katz M, Kruger S E, Schaffoner M, et al. Speaker identification and verification using support vector machines and sparse kernel logistic regression [A]. International Workshop on Intelligent Computing in Pattern Analysis/Synthesis[C]. Xi’an, China, 2006.
[133] Yamada M, Sugiyama M, Matsui T. Covariate shift adaptation for semi-supervised speaker identification [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009, 1661-1664.
[134] Keerthi S S, Shevade S K, Bhattacharyya C, et al. Improvements to Platt’s SMO algorithm for SVM classifier design [J]. Neural Computation, 2001, 13(3): 637-649.
[135] Roth V, Stenhage V, Nonlinear discrminant analysis using kernel functions [A]. In: S. A. Solla, T. K. Leen, and K.-R. Muller, Editors, Advances in Neural Information Processing Systems[C]. MIT Press, 1999, Vol. 12: 558-574.
[136] Minka T P. A comparison of numerical optimizers for logistic regression [R]. CMU Statistics, 2003.
[137] Keerthi S S, Duan K B, Shevade S K, et al. A fast dual algorithm for kernel logistic regression [J]. Machine learning. 2005, 61(1): 151-165.
[138] Yun L, Ding X Q, Wang S J. Visual tracker using sequential Bayesian learning: discriminative, generative, and hybrid [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B. 2008, 38(6): 1578-1591.
[139] Tashk A R B, Faez K. Boosted Bayesian kernel classifier method for face detection [A]. 3rd International Conference on Natural Computation, Haikou, 2007: 533-537.
[140] Yang B, Zhang Z, Sun Z. Robust relevance vector regression with trimmed likelihood function [J]. IEEE Signal Processing Letters. 2007, 14(10): 746-749.
[141] Tzikas D G, Likas A C, Galatsanos N P. Sparse Bayesian modeling with adaptive kernel learning [J]. IEEE Transaction on Neural Networks. 2009, 20(6): 926-937.
[142] Chen H, Tino P, Yao X. Probabilistic classification vector machines [J]. IEEE Transactions on Neural networks/a publication of the IEEE Neural Networks Council. 2009, 20(6): 901-914.
[143] Wu H L, Liu G D, Pu Z B. Multi-class image recognition based on relevance vector machine [C]. IEEE Press, 2009.
[144] Zhu J. Hastie T. Kernel logistic regression and the import vector machine [J]. Journal of Computational and Graphical Statistics, 2005, 14(1): 185-205.
[145] Tanaka K, Kurita T, Kawabe T. Selection of import vectors via binary particle swarm optimization and cross-validation for kernel logistic regression [A]. Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, 2007: 1037-1042.
[146] Huang P, Pavlovic V. Sparse logistic classifiers for interpretable protein homology detection [A]. 6th IEEE International Conference on Data Mining, 2006: 99-103.
[147] Zhong P, Wang R. Learning sparse CRFs for feature selection and classification of hyperspectral imagery [J]. IEEE Transactions on Geoscience and Remote Sensing. 2008, 46(12): 4186-4197.
[148] Zhong P, Peng Z, Wang R. Dynamic learning of SMLR for feature selection and classification of hyperspectral data [J]. Language. 2008, 5(2): 280-284.
[149] Patra S, Shanker K, Kundu D. Sparse maximum margin logistic regression for credit scoring [C]. Washington, DC, USA: IEEE Computer Society, 2008.
[150] Zhou Y F, Robles-Kelly A. Fast multiple instance learning via L1, 2 logistic regression [A]. In: ICPR 2008[C]. The 19th conference of the International Association for Pattern Recognition, Tampa Convention Center, 2008.
[151] Babacan S D, Molina R, Katsaggelos A K. Fast Bayesian compressive sensing using Laplace priors [A]. Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Washington, DC, USA: IEEE Computer Society, 2009: 2873-2876.
[152] Damoulas T, Girolami M A. Pattern recognition with a bayesian kernel combination machine [J]. Pattern Recognition Letters. 2009, 30(1): 46-54.
[153] Chien J T, Chen J C. Recursive Bayesian linear regression for adaptive classification [J]. IEEE Transactions on Signal Processing. 2009, 57(2): 565-575.
[154] Schmolck A, Everson R. Smooth relevance vector machine: a smoothness prior extension of the RVM [J]. Machine Learning. 2007, 68(2): 107-135.
[155] Shimada N, Kimura K, and Shirai Y. Efficient training of RBF networks for classification [A].In: ICANN99[C]. Proceedings of the Ninth International Conference on Artificial Neural Networks, Edinburgh, UK, 1999.
[156] MacKay D J C. The evidence framework applied to classification networks [J]. Neural Computation, 1992, 4(5): 720-736.
[157] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks [J].Science, 2006,313(5786):504–507.
[158] Wang B, Wong C M, Wan F, et al. Comparison of different classification methods for EEG-based brain computer interfaces: A case study [A]. Proceedings of the 2009 IEEE International Conference on Information and Automation[C]. Zhuhai/Macau, China, 2009.
[159] Vos F M, Caan M W A, Vermeer K A, et al. Linear and kernel fisher discriminant analysis for studying diffusion tensor images in schizophrenia [A]. 4th IEEE International Symposium on Biomedical Imaging: Macro to Nano[C], Arlington, VA, 2007.
[160] Yang D, Jin L. Handwritten Chinese character recognition using modified LDA and kernel FDA [A]. 9th International Conference on Document Analysis and Recognition[C], Washington, DC, USA: IEEE Computer Society, 2007.
[161]张成元.基于子空间分析的人脸识别算法研究[D].北京:北京交通大学, 2009.
[162] Baudat G., Anouar F. Generalized discriminate analysis using a kernel approach [J]. Neural Computation, 2000, 12(10): 2385-2404.
[163] Su H, Yang M, Xu H. A novel method of gait recognition based on Kernel Fisher Discriminant Analysis [A]. IEEE International Conference on Systems, Man and Cybernetics[C]. 2008: 830-835.
[164] Li Z, Wang F, Zhu W. An optimal kernel fisher nonlinear discriminant analysis method and applied on face recognition [A]. 2008 International Conference on Computational Intelligence and Security[C]. Washington, DC, USA: IEEE Computer Society, 2008, 2: 233-237.
[165] Wang F, Liu X, Huang C. An improved kernel fisher discriminant analysis for face recognition [A]. 2009 International Conference on Computational Intelligence and Security[C]. Washington, DC, USA: IEEE Computer Society, 2009.
[166] Zhou R Y, Guan Y P. A real-time face recognition method on video sequence using KFDA andNIB2DPCA [A]. IET Conference on Wireless, Mobile and Sensor Networks[C]. Shanghai, China, 2007: 845–848.
[167]甘俊英,柳俊峰,邵盼.基于小波分析与KFisher的人脸与虹膜融合和识别[J].现代电子技术. 2009, 32(22): 96-98.
[168] Gan J, Liu J. Fusion and recognition of face and iris feature based on wavelet feature and KFDA [A]. Proceedings of the 2009 International Conference on Wavelet Analysis and Pattern Recognition[C]. Baoding, 2009.
[169] Mika S. Kernel fisher discriminants [D]. Ph. D. dissertation, University of Technology, Berlin, Germany, 2002.
[170]杨国鹏,余旭初,陈伟,等.基于核Fisher判别分析的高光谱遥感影像分类[J].遥感学报. 2008, 12(4): 579-585.
[171] Goudelis G, Zafeiriou S, Tefas A, et al. Class-specific kernel discriminant analysis for face verification [J]. IEEE Transactions on Information Forensics and Security, 2007, 2(3): 570-587.
[172]成新民,蒋云良.基于融合两类核Fisher鉴别函数的人脸识别方法[J].武汉理工大学学报(交通科学与工程版). 2009, 33(2): 377-381.
[173] Baudat G, Anouar F. Generalized discriminant analysis using a kernel approach [J]. Neural Computation. 2000, 12(10): 2385-2404.
[174] Jadhav D V, Holambe R S. Multiresolution based kernel fisher discriminant model for face recognition [A]. Proceedings of the International Conference on Information Technology[C]. Washington, DC, USA: IEEE Computer Society, 2007: 848-853.
[175] Yu C M, Pan Q, Cheng Y M, et al. A kernel-based Bayesian classifier for fault detection and classification [A]. Proceedings of the 7th World Congress on Intelligent Control and Automation[C]. Chongqing, China, 2008.
[176] Cui J F, Guo G S, Miao M X, et al. An improved kernel method for fault diagnosis [A]. 2nd International Symposium on Systems and Control in Aerospace and Astronautics[C], Shenzhen, China, 2008.
[177] Wang Z, Li Q, Niu X, et al. Multimodal biometric recognition based on complex KFDA [A]. 5th International Conference on Information Assurance and Security[C]. Xi’an China, 2009.
[178] Zhu J, Hoi S C H, Lyu M R. Face annotation using transductive kernel fisher discriminant [J]. IEEE Transactions on Multimedia, 2008, 10(1): 86-96.
[179] He X F, Niyogi P. Locality preserving projections [A]. In Thrun S, Saul L, and Scholkopf B, editors, Advances in Neural Information Processing Systems 16[C]. MIT Press, Cambridge, MA, 2004.
[180]李波.基于流形学习的特征提取方法及其应用研究[D].安徽:中国科学技术大学, 2008.
[181]王建国.特征抽取方法研究及其在人脸识别中的应用[D].南京:南京理工大学, 2008.
[182]杨利平.保局子空间人脸特征提取及识别方法研究[D].重庆:重庆大学, 2008.
[183] Sugiyama M. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis [J]. Machine Learning Research, 2007, vol.8:1027-1061.
[184]党圣鸣,姚宏,高敬媛.基于KFD特征提取的说话人辨认[J].西北大学学报(自然科学版). 2009, 39(4): 583-585.
[185]邢玉娟,谭萍,李明.一种新的说话人识别序列特征提取方法[J].兰州理工大学学报. 2009, 35(4): 98-102.
[186] Chao Y H, Tsai W H, Wang H M, et al. Using kernel discriminant analysis to improve thecharacterization of the alternative hypothesis for speaker verification [J]. IEEE Transactions on Audio, Speech, and Language Processing. 2008, 16(8): 1675-1684.
[187]谭萍,邢玉娟,李明.基于核Fisher判别的说话人辨认[J].科学技术与工程. 2008, 8(8): 2230-2233.
[188] Li M, Xing Y, Luo R. Hierarchical speaker verification based on PCA and kernel fisher discriminant [A]. 4th International Conference on Natural Computation[C]. Washington, DC, USA: IEEE Computer Society, 2008: 152-156.
[189] Kim M S, Yang I H, Yu H J. Robust speaker identification using multimodal discriminant analysis with kernels [A]. 21st IEEE International Conference on Tools with Artificial Intelligence[C]. Washington, DC, USA: IEEE Computer Society. 2009: 319-322.
[190]徐勇,杨静宇,金忠,等.一种基于核的快速非线性鉴别分析方法[J].计算机研究与发展, 2005, 42(3): 267~374.
[191] Liu W, Wang Y H. Null space based kernel fisher discriminant analysis for face recognition [A]. Proceeding of the 6th International Conference on Automatic Face and Gesture Recognition[C], Seoul, Korea, 2004, 369-374.
[192] Duda R, Hart P, Stock D. Pattern classification [M]. The Second Edition. New York: John Wikey&Sons, 2010.
[193] Cheng Y Q, Zhuang Y M, Yang J Y. Optimal fisher discriminant analysis using the rank decomposition [J]. Pattern Recognition. 1992, 25(1): 101-111.
[194] Liang Y H, Wang Z Y, Guo S, et al. Pedestrian detection using KPCA and FLD algorithms [A]. Proceedings of the IEEE International Conference on Automation and Logistics[C]. Jinan, China, 2007.
[195] Chen L F, Liao H Y, Ko M T. A new lda-based face recognition system which can solve the small sample size problem [J]. Pattern Recognition. 2000, 33(10): 1713-1726.
[196] Dong J, Mu Z. Multi-pose ear recognition based on force field transformation [A]. 2nd International Symposium on Intelligent Information Technology Application[C]. 2008.
[197]成新民,蒋云良,胡文军,等.基于核的Fisher非线性最佳鉴别分析在人脸识别中的应用[J].中国图象图形学报. 2007, 12(8): 1395-1400.
[198] Yu H, Yang J. A direct lda algorithm for high-dimensional data with application to face recognition [J]. Pattern Recognition. 2001, 34(10): 2067-2070.
[199] Sugiyama M. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis [J]. Journal of Machine Learning Research, 2007, 8: 1027-1061.
[200] Belkin M. and Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation [J]. Neural Computation, 2003, 15(6):1373–1396.
[201] Zelnik-Manor L. and Perona P. Self-tuning spectral clustering [A]. In L. K. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems[C], MIT Press, Cambridge, MA, 2005: 1601–1608.
[202] D.M.J. Tax, R.P.W. Duin, Support vector data description [J], Machine Learning, 54(1), 2004, 45-66.
[203] Hong Gu, Guangzhou Zhao, Hongbo Wang, Shape Representation and recognition in high dimensional feature space [A]. International Conference on Computational Intelligence and Natural Computing[C]. Wuhan, China, 2009.
[204] Changjun CHEN, Yongzhao ZHAN, Chuanjun WEN, Hierarchical face recognition based on SVDD and SVM [A]. International Conference on Environmental Science and Information Application Technology[C]. Wuhan, China, 2009.
[205] V.M.O. Alves, A.L.I. Oliveira, E.R. Silva, et al. Handwritten digit segmentation in images of historical documents with one-class classifiers [A]. 20th IEEE International Conference on Tools with Artificial Intelligence[C]. Vol. 2, 2008, pp: 41-44.
[206] P. Varchol, D. Levicky, J. Juhar, Optimalization of GMM for text independent speaker verification system [A]. 18th International Conference on Radioelektronika[C]. Prague, 2008.
[207] B. Sch?lkopf, J. C. Platt, Estimating the support of a high-dimensional distribution [J]. Neural Computation, 2001, 13 (7): 1443-1471.
[208] G.R.G. Lanckriet, L.E. Ghaoui, M. Jordan, Robust novelty detection with single-class MPM [A]. Advances in Neural Information Processing Systems[C]. Cambridge: MIT Press, 2002: 905-912.
[209] I.W. Tsang, T.K. James, S. Li, Learning the kernel in Mahalanobis one-class support vector machines [A]. Proceedings of the International Joint Conference on Neural Networks[C]. Vancouver, Canada, 2006.
[210] A. Dolia, C. Harris, J. Shawe-Taylor, Kernel ellipsoidal trimming [J]. Computational Statistics and Data Analysis, 2007, 52(1): 309-324.
[211] T. Mu, A.K. Nandi, Multiclass classification based on extended support vector data description [J]. IEEE Transaction on System, Man and Cybernetics- Part B: Cybernetics, 2009, 39(5): 1206-1216.
[212] K.Y. Lee, D.W. Kim, K.H. Lee, D. Lee, Density-Induced support vector data description [J]. IEEE Transaction on Neural Networks, 2007, 18(1): 284-289.
[213]冯爱民,薛晖,刘学军,等.增强型单类支持向量机[J].计算机研究与发展, 2008, 45(11): 1858-1864.
[214] Chu C S, Tsang I W, Kwok J T. Scaling up support vector data description by using core-sets [A]. Proceedings of IEEE International Joint Conference on Neural Networks[C]. 2004, 1: 425-430.
[215]陆从德,张太镒,胡金燕.基于乘性规则的支持向量域分类器[J].计算机学报, 2004, 27(5): 690-694.
[216]赵英刚,陈奇,何钦铭.基于支持向量域数据描述的快速学习算法[J].仪器仪表学报, 2006, 27(6): 798-800.
[217] D.M.J. Tax, DDtools_the data description toolbox for Matlab (version 1.7.3). http: // ict.ewi.tudelft.nl/ ~davidt/dd_tools.html, 2009.
[218] David M J T. One-class classifier results [DB/OL]. http://ict.ewi.tudelft.nl/~davidt/occ/index.html, 2009/2010-2-20.
[219]陈斌,李斌,潘志松,等.流形嵌入的支持向量数据描述[J].模式识别与人工智能. 2009, 22(4): 548-553.
[2] Sun Z N, Tan T N. Ordinal measures for iris recognition [J]. IEEE Transactions on pattern Analysis and Machine Intelligence, 2009, 31(12): 2211-2226.
[3] Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[4] Xu X, Mu Z. Feature fusion method based on KCCA for ear and profile face based multimodal recognition [A]. Proceeding of the IEEE International Conference on Automation and Logistics[C]. Jinan, China, 2007.
[5]高志贤,周焕英,何永红. DNA在生物传感器金电极上的固定化技术研究进展[J].中华预防医学杂志, 2009, 43(12): 1109-1113.
[6]陈实,马天骏,高有行.用行人轮廓的分布直方图分类和识别步态[J].计算机研究与发展, 2009, 46(2): 295-301.
[7] Zhang D, Lu G M, Li W, et al. Palmprint recognition using 3-D information [J]. IEEE Transaction on System, Man and Cybernetics, Part C: Applications and Review, 2009, 39(5): 505-519.
[8] Gong W G, Yang L P, Chen D. Pitch synchronous based feature extraction for noise-robust speaker verification [A]. Congress on Image and Signal Processing[C]. 2008: 295-298.
[9] Zulfiqar A, Muhammad A, Enriquez A M M. A speaker identification system using MFCC features with VQ technique [A]. 3rd International Symposium on Intelligent Information Technology Application[C]. 2009, vol. 3: 115-118.
[10]陈渤.基于核方法的雷达高分辨距离像目标识别技术研究[D].西安:西安电子科技大学, 2008.
[11] Louradour, J. and K. Daoudi, State-of-the-art sequence kernels for SVM speaker verification [A]. IEEE Workshop on Machine Learning for Signal Processing[C]. Cancun, 2008: 498--503.
[12]于雪莲.基于核方法和流形学习的雷达目标距离像识别研究[D].成都:电子科技大学, 2008.
[13]任双桥.支撑矢量机理论与应用研究[D].长沙:国防科学技术大学, 2006.
[14]周晓飞.几种新型分类器设计及其在人脸识别应用中的研究[D].南京:南京理工大学, 2008.
[15]李青.优化核方法[D].西安:电子科技大学, 2006.
[16] Zhen B, Wu X H, Liu Z M, Chi H S, On the importance of components of the MFCC in speech and speaker recognition [J]. Acta Scicentiarum Naturalum Universities Pekinesis, 2001, 37(3): 371–378.
[17] Zhu J W, Sun S F, Dan Z P, et al. MFCC extraction based on F-Ratio and correlated distance criterion in speaker recognition [A]. International Conference on Multimedia Information Networking and Security[C], 2009.
[18] Zeng Yu-Min W Z. Combination of Pitch synchronous analysis and fisher criterion for speaker identification [J]. Journal of Electronics. 2007, 24(6): 828-834.
[19] Wang C, Miao Z, Meng X. Differential MFCC and vector quantization used for real-time speaker recognition system [A]. 1st International Congress on Image and Signal Processing[C], Sanya, Hainan, China, 2008.
[20] Grimaldi M, Cummins F. Speaker identification using instantaneous frequencies [J]. IEEE Transactionson Audio, Speech, and Language Processing. 2008, 16(6): 1097-1111.
[21] Long Y H, Ma B, Li H Z, et al. Exploiting prosodic information for Speaker Recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009: 4225-4228.
[22] Qiu Z Q, Yin J X, Fan C Y. Using redundant parallel architecture to improve speaker recognition performance [J]. Control Theory Application. 2008, 6(2): 221-223.
[23] Truong T K, Lin C C, Chen S H, et al. Feature comparison among various wavelets in speaker recognition using support vector machine [A]. Proceedings of the 8th IEEE International Symposium on Multimedia[C]. Washington, DC, USA: IEEE Computer Society, 2006: 811-816.
[24] Claussen H, Rosca J, Damper R. Mutual features for robust identification and verification [A]. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Las Vegas, NV, USA, 2008: 1849-1852.
[25] Liu Y L, Yang H W, Zhou H. Speaker identification based on EMD [A]. IEEE International Conference on Network Infrastructure and Digital Content[C], 2009.
[26] Thiruvaran T, Ambikairajah E, Epps J. Extraction of FM components from speech signals using all-pole model [J]. Electronics Letters. 2008, 44(6): 448-449.
[27] Das A, Manyam O K, Tapaswi M, et al. Multilingual spoken-password based user authentication in emerging economies using cellular phone networks [A]. In proceedings of the IEEE Workshop on Spoken Language Technology (SLT)[C], Goa, India, 2008: 5-8.
[28] Gudnason J, Brookes M. Voice source Cepstrum coefficients for speaker identification [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Las Vegas, NV, USA, 2008: 4821-4824.
[29] Kalgaonkar K, Raj B. Ultrasonic Doppler sensor for speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Las Vegas, NV, USA, 2008.
[30] Centingul H E, Yemez Y, Engin E, et al. Discriminative analysis of lip motion features for speaker identification and speech-reading [J]. IEEE Transactions on Image Processing, 2006, 15(10): 2879-2891.
[31] Faraj M I, Bigun J. Synergy of Lip-Motion and acoustic features in biometric speech and speaker recognition [J]. IEEE Transactions on Computers, 2007, 56(9): 1169-1175.
[32]吴朝晖,杨莹春.说话人识别模型与方法[M].北京:清华大学出版社, 2009.
[33] Chao Y H, Wang H M, Chang R C. Gmm-based Bhattacharyya kernel fisher discriminant analysis for speaker recognition [A]. International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 2005.
[34] Campbell W M, Campbell J P, Reynolds D A, et al. Support vector machines for speaker and language recognition [J]. Computer Speech & Language, 2006, 20(2/3): 210-229.
[35] Moreno P J, Ho P P. A new SVM approach to speaker identification and verification using probabilistic distance kernels [C]. EUROSPEECH, 2003.
[36] You C H, Lee K A, Li H. A GMM supervector kernel with the Bhattacharyya distance for SVM based speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C], Taipei, Taiwan, 2009: 4221-4224.
[37] Campbell W M, Sturim D E, Reynolds D A. Support vector machines using GMM supervector for speaker verification [J]. IEEE Signal Processing Letters, 2006, 13(5): 308-311.
[38] Campbell W M, Campbell J P, Gleason T P, et al. Speaker verification using support vector machinesand high-level features [J]. IEEE Transaction on Audio, Speech, and Language Processing, 2007, 15(7): 2085-2094.
[39]刘明辉,戴蓓蒨,解焱陆,等.基于GMM多维概率输出的SVM话者确认[J].模式识别与人工智能, 2008, 21(1): 28-32.
[40] Zhao Z D, Zhang J, Tian J F, et al. An effective identification method for speaker recognition based on PCA and double VQ [A]. Proceeding of the 8th International Conference on Machine Learning and Cybernetics[C], Baoding, 2009.
[41] Lin L, Wang S. A Kernel method for speaker recognition with little data [A]. 8th International Conference on Signal Processing[C]. 2006, 1.
[42]崔连延,徐林,顾树生,等.基于减法聚类与改进的模糊C-均值聚类算法的说话人识别方法的研究[J].信息与控制. 2008, 37(3): 358-361.
[43]林琳,王树勋,陈建,等.基于可区分性加权的模糊核说话人识别[J].电子学报. 2008, 36(7): 1446-1450.
[44]白莹,赵振东,戚银城,等.基于小波神经网络的与文本无关说话人识别方法研究[J].电子与信息学报. 2006(06): 1036-1039.
[45]姚潇,武妍,王守觉,等.一种基于并行覆盖前馈优先神经网络的说话人识别方法[J].计算机科学. 2008, 35(8): 125-128.
[46] Joshi S, Prahallad K, Yegnanarayana. AANN-HMM models for speaker verification and speech recognition [A]. In Proceedings of International Joint Conference on Neural Networks[C], 2008.
[47]陈存宝,赵力.嵌入自联想神经网络的高斯混合模型说话人辨认[J].电子与信息学报, 2010, 32(3): 528-532.
[48] Li R, Ji W J, Zhang L, et al. An improved quantum-behaved particle swarm classifier based on weighted mean best position [A]. IEEE International Conference on Intelligence Computing and Intelligent Systems[C], Shanghai, 2009: 327-331.
[49]陈刚,陈莘萌,向广利,等.基于非参数独立分量分析的说话人识别方法[J].计算机科学. 2006, 33(3): 167-170.
[50] Waghmare R K, Asutkar V G. Advance statistical modeling for speaker verification [A]. IEEE Conference on Industrial Electronics and Applications[C], Singapore, 2008: 2535-2539.
[51] Tarakanov A O. Immunocomputing for Speaker Recognition [M]. Springer Berlin/Heidelberg, 2010, Vol. 263.
[52] Bimbot F, Bonastre J F, Fredouille C, et al. A tutorial on text-independent speaker verification [J]. EURASIP Journal on Applied Signal Processing, 2004, 4: 430-451.
[53] Yuan D, Lu L, Zhao X Y, et al. Studies on model distance normalization approach in text-independent speaker verification [J]. ACTA Automatic Sinica. 2009, 35(5): 556-560.
[54] Zhao J, Dong Y, Zhao X Y, et al. Cross similarity measurement for speaker adaptive test normalization in text-independent speaker verification [J]. The Journal of China Universities of Posts and Telecommunications, 2008, 15(2): 130-134.
[55] Castro D R, Aguilar J F, Rodriguez J G, et al. Speaker verification using speaker- and test-dependent fast score normalization [J]. Pattern Recognition Letters, 2007, 28(1): 90-98.
[56]王琳琳,张利鹏,徐明星.基于分数规整的发音方式鲁棒的说话人识别[J].清华大学学报(自然科学版). 2009, 49(S1): 1278-1282.
[57]邱政权,尹俊勋,杨俊.在噪声环境下的分级说话人辨识[J].控制与决策. 2007, 22(5): 581-584.
[58] Wang W L, Zheng J W, Wang L. Improved wavelet pre-enhancement and hybrid model applied in speech recognition system [A]. 7th Asian Control Conference, Hong Kong, China, 2009.
[59]田斌,易克初.一种用于强噪声环境下语音识别的含噪Lombard及Loud语音补偿方法[J].声学学报, 2003, 28(1): 28-32.
[60] Pullella D, Kuhne M, Togneri R. Robust speaker identification using combined feature selection and missing data recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing, part11, Las Vegas, NV, USA, 2008.
[61]龙艳花,郭武,戴礼荣,等.一种基于说话者话路变化的主成分分析方法[J].模式识别与人工智能. 2009, 22(2): 270-274.
[62] Zou X, Jancovic P, Kokuer M. On the effectiveness of the ICA-based signal representation in non-Gaussian noise [A]. 9th International Conference on Signal Processing[C]. Beijing, 2008.
[63] Saon G, Padmanabhan M, Gopinath R, et al. Maximum likelihood discriminant feature spaces [A]. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing[C]. 2000, 2: 1129-1132.
[64]徐利敏,唐振民,何可可,钱博.基于自适应直方图均衡化的鲁棒性说话人辨认研究[J].自动化学报. 2008, 34(7): 752-759.
[65] Hansen J H L, Varadarajan V. Analysis and compensation of Lombard speech across noise type and Levels with application to In-Set/Out-of-Set speaker recognition [J]. IEEE transactions on audio, speech and language processing. 2009, 17(2): 366-378.
[66] Peer I, Rafaely B, Zigel Y. Reverberation matching for speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing, part 11[C]. Las Vegas, NV, USA, 2008: 4829-4832.
[67]包永强,赵力,邹采荣,等.采用归一化补偿变换的与文本无关的说话人识别[J].声学学报. 2006, 31(1): 55-60.
[68] Chen K. Towards better making a decision in speaker verification [J]. Pattern Recognition, 2003, 36(2): 329-346.
[69]高荣春,韩纪庆,张磊,等.说话人识别中基于最大后验概率的通道补偿方法[J].通信学报. 2009, 30(3): 99-103.
[70] Shabtai N R, Zigel Y, Rafaely B. The effect of GMM order and CMS on speaker recognition with reverberant speech [A]. Hands-Free Speech Communication and Microphone Arrays[C], Trento, 2008: 144-147.
[71] Gong Y E. Speech recognition in noisy environments: a survey [J]. Speech Communication, 1995, 16: 261-291.
[72] Guo W, Dai L R. Feature mapping based on GMM supervector [A]. International Conference on Audio, Language and Image Processing[C]. Shanghai, 2008: 1081-1085.
[73] Bing Xiang, Upendra V C, Ji R N. Short-time gaussianization for robust speaker verification [A]. Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing[C]. 2002: 681-684.
[74] Dehak N, Dumouchel P, Kenny P. Modeling prosodic features with joint factor analysis for speaker verification [J]. IEEE Transactions on Audio, Speech, and Language Processing, 2007, 15(7): 2095-2103.
[75] Campbell W M, Sturim D E, Reynolds D A, et al. SVM based speaker verification using a GMM supervector kernel and NAP variability compensation [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Toulouse, France, 2006, vol. 1.
[76] Deng J, Zheng T F, Wu W H. Session variability subspace projection based model compensation for speaker verification [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. 2007, 4: 57-60.
[77]郭武,戴礼荣,王仁华,等.说话人识别中的串行因子分析[J].模式识别与人工智能. 2009, 22(4): 514-518.
[78]李冬冬,吴朝晖,杨莹春,等.基于基频的情感语音聚类的说话人识别方法[J].模式识别与人工智能. 2009, 22(1):136-140.
[79] Zhang C, Hansen J. Analysis and classification of speech model: whispered through shouted [A]. Proceeding of Interspeech[C]. Antwerp, 2007.
[80] Nakagawa S, Zhang W. Takahashi M. Text-independent speaker recognition by combining speaker-specific GMM with speaker adapted syllable-based HMM [A]. Proceeding of International Conference on Acoustics, Speech and Signal Processing[C]. Montreal, 2004.
[81] Akbacak M, Hansen J. Languge normalization for bilingual speaker recognition systems [A]. Proceeding of International Conference on Acoustics, Speech and Signal Processing[C]. Hawaii, 2007.
[82] Guo W, Long Y, Li Y, et al. iFLY system for the NIST 2008 speaker recognition evaluation[A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009: 4209-4212.
[83]李战明,陈迪.一种基于小波神经网络混合模型的说话人识别方法[J].兰州理工大学学报, 33(2): 77-80.
[84] Yoma N B, Sanchez J S. MAP speaker adaptation of state duration distributions for speech recognition [J]. IEEE Transaction on Speech and Audio Processing, 2002, 10(7): 443-450.
[85] Ferras M, Barras C, Gauvain J L. Lattice-based MLLR for speaker recognition [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009: 4537-4540.
[86] Song H J, Jeong Y, Kim H S. A new method for speaker adaptation using bilinear model [A]. IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei, Taiwan, 2009: 4365-4368.
[87] Wan V, Renals S. Speaker verification using sequence discriminant support vector machines [J]. IEEE Transactions on Speech and Audio Processing. 2005, 13(2): 203-210.
[88] Campbell W M, Sturim D E, Reynolds D A. Support vector machines using GMM supervectors for speaker verification [J]. IEEE Signal Processing Letters. 2006, 13(5): 308-311.
[89] Weston J, Watkins C. Support vector machines for multi-class pattern recognition [A]. In: Proceedings of the European Symposium on Artificial Neural Networks[C]. Bruges, 1999: 219-224.
[90] Liu Yang, Wang R, Zeng Y S. An improvement of one-against-one method for multi-class support vector machine [A]. International Conference on Machine Learning and Cybernetics[C]. Hong Kong, 2007: 2915-2920.
[91]刘波,郝志峰,肖燕珊.交互迭代一对一分类算法[J].模式识别与人工智能, 2008, 21(4): 425-431.
[92] Qin Y P, Wang X K. Study on multi-label text classification based on SVM [A]. 6th International Conference on Fuzzy Systems and Knowledge Discovery[C]. Tianjin, 2009: 300-304.
[93] Pimenta E, Gama J. A study on error correcting output codes [A]. Portuguese Conference on Artificial Intelligence[C]. Covilha, 2005: 218-223.
[94]尹安容,谢湘,匡镜明,等. Hadamard纠错码结合支持向量机在多分类问题中的应用[J].电子学报. 2008, 36(1): 122-126.
[95]张永.基于模糊支持向量机的多类分类算法研究[D].大连:大连理工大学, 2008.
[96] Tipping M E, Smola A. Sparse Bayesian learning and the relevance vector machine [J]. Journal of Machine Learning Research, 2001, 1(3): 211-244.
[97] Tipping M E, Faul A. Fast marginal likelihood maximization for sparse Bayesian models [A]. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, 2003.
[98]陈佳,颜学峰,钱锋.基于贝叶斯学习的关联向量机及其在软测量中的应用[J].华东理工大学学报:自然科学版. 2007, 33(001): 115-119.
[99] Wipf D, Nagarajan S. Beamforming using the relevance vector machine [A]. Proceedings of the 24th international conference on Machine learning[C]. Corvalis, Oregon, 2007, 1023-1030.
[100]方红,王年,章权兵,等.基于稀疏贝叶斯学习的图像重建方法[J].中国图象图形学报. 2009, 14(6): 1064-1069.
[101] Din E R, Zeng P, Yao Y. Estimation of illumination chromaticity via adaptive reduced relevance vector machine [J]. Journal of Southeast University (English Edition). 2007, 23(2): 202-205.
[102]成萍,司锡才,姜义成,等.基于稀疏贝叶斯学习的稀疏信号表示ISAR成像方法[J].电子学报. 2008, 36(3): 547-550.
[103]张旭东,陈锋,高隽,等.稀疏贝叶斯及其在时间序列预测中的应用[J].控制与决策. 2006, 21(5): 585-588.
[104]张旭东,钱玮,高隽,等.基于稀疏贝叶斯分类器的汽车车型识别[J].小型微型计算机系统. 2005, 26(10): 1839-1841.
[105] Mahalo P M B, Sayadiyan A, Faez K. Mixed type audio classification using sinusoidal parameters [A]. 3rd International Conference on Information and Communication Technologies: From Theory to Applications[C]. Damascus, Syria, 2008.
[106] Babaeean A, Tashk A B, Bandarabadi M, et al. Target tracking using wavelet features and RVM classifier [A]. Proceedings of the 2008 4th International Conference on Natural Computation[C]. Washington, DC, USA: IEEE Computer Society, 2008, 569-572.
[107] Tang H, Chen Z, Huang T S, et al. Comparison of algorithms for speaker identification under adverse far-field recording conditions with extremely short utterances [A]. IEEE International Conference on Networking, Sensing and Control[C]. Sanya, 2008, 796-801.
[108]丁二锐,曾平,丁阳,等.一种新的回归型约简多分辨率相关向量机[J].控制与决策. 2008(1): 65-69.
[109] Tipping M. The relevance vector machine [J]. Advances in Neural Information Processing System, 2000, 12: 652-658.
[110] Tipping M E, Faul A. Fast marginal likelihood maximization for sparse Bayesian models [A]. In: Proc. 9th Int. Workshop Artif. Intell[C]. Statist, Key West, FL, 2003.
[111] Faul A C, Tipping M E. Analysis of sparse Bayesian learning [A]. In: Dietterich T G, Bechker S, Ghahramani Z. Advances in Neural Information Processing Systems 14[C]. Cambridge, MA, USA: MIT Press, 2002: 383-390.
[112]王炜,吕萍,颜永红,等.一种改进的基于层次聚类的说话人自动聚类算法[J].声学学报. 2008, 33(1): 9-14.
[113] You C H, Lee K A, Li H. An SVM kernel with GMM-supervector based on the Bhattacharyya distance for speaker recognition [J]. IEEE Signal Processing Letters. 2009, 16(1): 49-52.
[114] Louradour J, Daoudi K. State-of-the-art sequence kernels for SVM speaker verification [A]. IEEE Workshop on Machine Learning for Signal Processing[C]. Cancun, 2008: 498-503.
[115] Chang C C, Lin C J. LIBSVM: a library for support vector machines [CP]. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm, Version 2.9, 2009.
[116]李滔,王俊普,吴秀清.基于特征矢量集的核Logistic回归[J].小型微型计算机系统, 2007, 27(6): 980-985.
[117] Park M Y, Hastie T. Penalized logistic regression for detecting gene interactions [J]. Biostatistics. 2007, 9(1): 30-50.
[118] Li L, Leung H. Using the number of faults to improve fault-proneness prediction of the probability models [A]. World Congress on Computer Science and Information Engineering, LosAngeles[C], California, USA, 2009.
[119] Birkenes O, Matsui T, Tanabe K. Isolated-word recognition with penalized logistic regression machines [A]. Proc. ICASSP[C], 2006.
[120] Siniscalchi S M, Svendsen T, Lee C H. A penalized logistic regression approach to detection based phone classification [A]. 9th Annual Conference of the International Speech Communication Association[C], Brisbane, Australia, 2008.
[121]李滔,王俊普,吴秀清,等.后验概率估计及其应用:基于核Logistic回归的方法[J].模式识别与人工智能. 2006, 19(6): 689-695.
[122] Rahayu S P, Purnami S W, Embong A. Applying kernel logistic regression in data mining to classify credit risk [A]. International Symposium on Information Technology[C], Kuala Lumpur, Malaysia, 2008, vol. 2, pp: 1-6.
[123] Karsmakers P, Pelckmans K, Suykens J, et al. Fixed-Size kernel logistic regression for phoneme classification [A]. 8th Annual Conference of the International Speech Communication Association[C]. Antwer, Belgium, 2007.
[124] EI Naqa I, Bradley J D, Deasy J O. Nonlinear kernel-based approaches for predicting normal tissue toxicities [A]. Proceedings of the 7th International Conference on Machine Learning and Applications[C]. Washington, DC, USA: IEEE Computer Society, 2008, 539-544.
[125] Lin C J, Weng R C, Keerthi S S. Trust region newton method for logistic regression [J]. The Journal of Machine Learning Research. 2008, 9: 627-650.
[126] Koh K, Kim S, Boyd S. A method for large-scale l1-regularized logistic regression [A]. Proceedings of the 22nd international conference on Artificial intelligence[C]. Vancouver, British Columbia, Canada: AAAI Press, 2007, 565-571.
[127] Koh K, Kim S, Boyd S. An interior-point method for large-scale l1-regularized logistic regression [J]. Journal of Machine Learning Research. 2007, 8: 1519-1555.
[128] Yajima Y, Sato T. Semi-supervised kernel logistic regression and its extension to active learning based on A-Optimality [A]. 7th IEEE International Conference on Data Mining[C]. Omaha, NE, 2007.
[129] HoiSCH, Jin R, Lyu M R. Batch mode active learning with applications to text categorization and image retrieval [J]. Knowledge and Data Engineering, IEEE Transactions on. 2009, 21(9): 1233-1248.
[130] Karsmakers P, Pelckmans K, Suykens J A K. Multi-class kernel logistic regression: a fixed-size implementation [A]. Proc. International Joint Conference on Neural Networks[C], Orlando, Florida,USA, August, 2007.
[131] Katz M, Schaffoner M, Andelic E, Kruger S E, Wendemuth A. Sparse kernel logistic regression using incremental feature selection for text-independent speaker identification [A]. Proc. Speaker and Language Recognition workshop[C], San Juan, 2006.
[132] Katz M, Kruger S E, Schaffoner M, et al. Speaker identification and verification using support vector machines and sparse kernel logistic regression [A]. International Workshop on Intelligent Computing in Pattern Analysis/Synthesis[C]. Xi’an, China, 2006.
[133] Yamada M, Sugiyama M, Matsui T. Covariate shift adaptation for semi-supervised speaker identification [A]. IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Taipei, Taiwan, 2009, 1661-1664.
[134] Keerthi S S, Shevade S K, Bhattacharyya C, et al. Improvements to Platt’s SMO algorithm for SVM classifier design [J]. Neural Computation, 2001, 13(3): 637-649.
[135] Roth V, Stenhage V, Nonlinear discrminant analysis using kernel functions [A]. In: S. A. Solla, T. K. Leen, and K.-R. Muller, Editors, Advances in Neural Information Processing Systems[C]. MIT Press, 1999, Vol. 12: 558-574.
[136] Minka T P. A comparison of numerical optimizers for logistic regression [R]. CMU Statistics, 2003.
[137] Keerthi S S, Duan K B, Shevade S K, et al. A fast dual algorithm for kernel logistic regression [J]. Machine learning. 2005, 61(1): 151-165.
[138] Yun L, Ding X Q, Wang S J. Visual tracker using sequential Bayesian learning: discriminative, generative, and hybrid [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B. 2008, 38(6): 1578-1591.
[139] Tashk A R B, Faez K. Boosted Bayesian kernel classifier method for face detection [A]. 3rd International Conference on Natural Computation, Haikou, 2007: 533-537.
[140] Yang B, Zhang Z, Sun Z. Robust relevance vector regression with trimmed likelihood function [J]. IEEE Signal Processing Letters. 2007, 14(10): 746-749.
[141] Tzikas D G, Likas A C, Galatsanos N P. Sparse Bayesian modeling with adaptive kernel learning [J]. IEEE Transaction on Neural Networks. 2009, 20(6): 926-937.
[142] Chen H, Tino P, Yao X. Probabilistic classification vector machines [J]. IEEE Transactions on Neural networks/a publication of the IEEE Neural Networks Council. 2009, 20(6): 901-914.
[143] Wu H L, Liu G D, Pu Z B. Multi-class image recognition based on relevance vector machine [C]. IEEE Press, 2009.
[144] Zhu J. Hastie T. Kernel logistic regression and the import vector machine [J]. Journal of Computational and Graphical Statistics, 2005, 14(1): 185-205.
[145] Tanaka K, Kurita T, Kawabe T. Selection of import vectors via binary particle swarm optimization and cross-validation for kernel logistic regression [A]. Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, 2007: 1037-1042.
[146] Huang P, Pavlovic V. Sparse logistic classifiers for interpretable protein homology detection [A]. 6th IEEE International Conference on Data Mining, 2006: 99-103.
[147] Zhong P, Wang R. Learning sparse CRFs for feature selection and classification of hyperspectral imagery [J]. IEEE Transactions on Geoscience and Remote Sensing. 2008, 46(12): 4186-4197.
[148] Zhong P, Peng Z, Wang R. Dynamic learning of SMLR for feature selection and classification of hyperspectral data [J]. Language. 2008, 5(2): 280-284.
[149] Patra S, Shanker K, Kundu D. Sparse maximum margin logistic regression for credit scoring [C]. Washington, DC, USA: IEEE Computer Society, 2008.
[150] Zhou Y F, Robles-Kelly A. Fast multiple instance learning via L1, 2 logistic regression [A]. In: ICPR 2008[C]. The 19th conference of the International Association for Pattern Recognition, Tampa Convention Center, 2008.
[151] Babacan S D, Molina R, Katsaggelos A K. Fast Bayesian compressive sensing using Laplace priors [A]. Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing[C]. Washington, DC, USA: IEEE Computer Society, 2009: 2873-2876.
[152] Damoulas T, Girolami M A. Pattern recognition with a bayesian kernel combination machine [J]. Pattern Recognition Letters. 2009, 30(1): 46-54.
[153] Chien J T, Chen J C. Recursive Bayesian linear regression for adaptive classification [J]. IEEE Transactions on Signal Processing. 2009, 57(2): 565-575.
[154] Schmolck A, Everson R. Smooth relevance vector machine: a smoothness prior extension of the RVM [J]. Machine Learning. 2007, 68(2): 107-135.
[155] Shimada N, Kimura K, and Shirai Y. Efficient training of RBF networks for classification [A].In: ICANN99[C]. Proceedings of the Ninth International Conference on Artificial Neural Networks, Edinburgh, UK, 1999.
[156] MacKay D J C. The evidence framework applied to classification networks [J]. Neural Computation, 1992, 4(5): 720-736.
[157] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks [J].Science, 2006,313(5786):504–507.
[158] Wang B, Wong C M, Wan F, et al. Comparison of different classification methods for EEG-based brain computer interfaces: A case study [A]. Proceedings of the 2009 IEEE International Conference on Information and Automation[C]. Zhuhai/Macau, China, 2009.
[159] Vos F M, Caan M W A, Vermeer K A, et al. Linear and kernel fisher discriminant analysis for studying diffusion tensor images in schizophrenia [A]. 4th IEEE International Symposium on Biomedical Imaging: Macro to Nano[C], Arlington, VA, 2007.
[160] Yang D, Jin L. Handwritten Chinese character recognition using modified LDA and kernel FDA [A]. 9th International Conference on Document Analysis and Recognition[C], Washington, DC, USA: IEEE Computer Society, 2007.
[161]张成元.基于子空间分析的人脸识别算法研究[D].北京:北京交通大学, 2009.
[162] Baudat G., Anouar F. Generalized discriminate analysis using a kernel approach [J]. Neural Computation, 2000, 12(10): 2385-2404.
[163] Su H, Yang M, Xu H. A novel method of gait recognition based on Kernel Fisher Discriminant Analysis [A]. IEEE International Conference on Systems, Man and Cybernetics[C]. 2008: 830-835.
[164] Li Z, Wang F, Zhu W. An optimal kernel fisher nonlinear discriminant analysis method and applied on face recognition [A]. 2008 International Conference on Computational Intelligence and Security[C]. Washington, DC, USA: IEEE Computer Society, 2008, 2: 233-237.
[165] Wang F, Liu X, Huang C. An improved kernel fisher discriminant analysis for face recognition [A]. 2009 International Conference on Computational Intelligence and Security[C]. Washington, DC, USA: IEEE Computer Society, 2009.
[166] Zhou R Y, Guan Y P. A real-time face recognition method on video sequence using KFDA andNIB2DPCA [A]. IET Conference on Wireless, Mobile and Sensor Networks[C]. Shanghai, China, 2007: 845–848.
[167]甘俊英,柳俊峰,邵盼.基于小波分析与KFisher的人脸与虹膜融合和识别[J].现代电子技术. 2009, 32(22): 96-98.
[168] Gan J, Liu J. Fusion and recognition of face and iris feature based on wavelet feature and KFDA [A]. Proceedings of the 2009 International Conference on Wavelet Analysis and Pattern Recognition[C]. Baoding, 2009.
[169] Mika S. Kernel fisher discriminants [D]. Ph. D. dissertation, University of Technology, Berlin, Germany, 2002.
[170]杨国鹏,余旭初,陈伟,等.基于核Fisher判别分析的高光谱遥感影像分类[J].遥感学报. 2008, 12(4): 579-585.
[171] Goudelis G, Zafeiriou S, Tefas A, et al. Class-specific kernel discriminant analysis for face verification [J]. IEEE Transactions on Information Forensics and Security, 2007, 2(3): 570-587.
[172]成新民,蒋云良.基于融合两类核Fisher鉴别函数的人脸识别方法[J].武汉理工大学学报(交通科学与工程版). 2009, 33(2): 377-381.
[173] Baudat G, Anouar F. Generalized discriminant analysis using a kernel approach [J]. Neural Computation. 2000, 12(10): 2385-2404.
[174] Jadhav D V, Holambe R S. Multiresolution based kernel fisher discriminant model for face recognition [A]. Proceedings of the International Conference on Information Technology[C]. Washington, DC, USA: IEEE Computer Society, 2007: 848-853.
[175] Yu C M, Pan Q, Cheng Y M, et al. A kernel-based Bayesian classifier for fault detection and classification [A]. Proceedings of the 7th World Congress on Intelligent Control and Automation[C]. Chongqing, China, 2008.
[176] Cui J F, Guo G S, Miao M X, et al. An improved kernel method for fault diagnosis [A]. 2nd International Symposium on Systems and Control in Aerospace and Astronautics[C], Shenzhen, China, 2008.
[177] Wang Z, Li Q, Niu X, et al. Multimodal biometric recognition based on complex KFDA [A]. 5th International Conference on Information Assurance and Security[C]. Xi’an China, 2009.
[178] Zhu J, Hoi S C H, Lyu M R. Face annotation using transductive kernel fisher discriminant [J]. IEEE Transactions on Multimedia, 2008, 10(1): 86-96.
[179] He X F, Niyogi P. Locality preserving projections [A]. In Thrun S, Saul L, and Scholkopf B, editors, Advances in Neural Information Processing Systems 16[C]. MIT Press, Cambridge, MA, 2004.
[180]李波.基于流形学习的特征提取方法及其应用研究[D].安徽:中国科学技术大学, 2008.
[181]王建国.特征抽取方法研究及其在人脸识别中的应用[D].南京:南京理工大学, 2008.
[182]杨利平.保局子空间人脸特征提取及识别方法研究[D].重庆:重庆大学, 2008.
[183] Sugiyama M. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis [J]. Machine Learning Research, 2007, vol.8:1027-1061.
[184]党圣鸣,姚宏,高敬媛.基于KFD特征提取的说话人辨认[J].西北大学学报(自然科学版). 2009, 39(4): 583-585.
[185]邢玉娟,谭萍,李明.一种新的说话人识别序列特征提取方法[J].兰州理工大学学报. 2009, 35(4): 98-102.
[186] Chao Y H, Tsai W H, Wang H M, et al. Using kernel discriminant analysis to improve thecharacterization of the alternative hypothesis for speaker verification [J]. IEEE Transactions on Audio, Speech, and Language Processing. 2008, 16(8): 1675-1684.
[187]谭萍,邢玉娟,李明.基于核Fisher判别的说话人辨认[J].科学技术与工程. 2008, 8(8): 2230-2233.
[188] Li M, Xing Y, Luo R. Hierarchical speaker verification based on PCA and kernel fisher discriminant [A]. 4th International Conference on Natural Computation[C]. Washington, DC, USA: IEEE Computer Society, 2008: 152-156.
[189] Kim M S, Yang I H, Yu H J. Robust speaker identification using multimodal discriminant analysis with kernels [A]. 21st IEEE International Conference on Tools with Artificial Intelligence[C]. Washington, DC, USA: IEEE Computer Society. 2009: 319-322.
[190]徐勇,杨静宇,金忠,等.一种基于核的快速非线性鉴别分析方法[J].计算机研究与发展, 2005, 42(3): 267~374.
[191] Liu W, Wang Y H. Null space based kernel fisher discriminant analysis for face recognition [A]. Proceeding of the 6th International Conference on Automatic Face and Gesture Recognition[C], Seoul, Korea, 2004, 369-374.
[192] Duda R, Hart P, Stock D. Pattern classification [M]. The Second Edition. New York: John Wikey&Sons, 2010.
[193] Cheng Y Q, Zhuang Y M, Yang J Y. Optimal fisher discriminant analysis using the rank decomposition [J]. Pattern Recognition. 1992, 25(1): 101-111.
[194] Liang Y H, Wang Z Y, Guo S, et al. Pedestrian detection using KPCA and FLD algorithms [A]. Proceedings of the IEEE International Conference on Automation and Logistics[C]. Jinan, China, 2007.
[195] Chen L F, Liao H Y, Ko M T. A new lda-based face recognition system which can solve the small sample size problem [J]. Pattern Recognition. 2000, 33(10): 1713-1726.
[196] Dong J, Mu Z. Multi-pose ear recognition based on force field transformation [A]. 2nd International Symposium on Intelligent Information Technology Application[C]. 2008.
[197]成新民,蒋云良,胡文军,等.基于核的Fisher非线性最佳鉴别分析在人脸识别中的应用[J].中国图象图形学报. 2007, 12(8): 1395-1400.
[198] Yu H, Yang J. A direct lda algorithm for high-dimensional data with application to face recognition [J]. Pattern Recognition. 2001, 34(10): 2067-2070.
[199] Sugiyama M. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis [J]. Journal of Machine Learning Research, 2007, 8: 1027-1061.
[200] Belkin M. and Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation [J]. Neural Computation, 2003, 15(6):1373–1396.
[201] Zelnik-Manor L. and Perona P. Self-tuning spectral clustering [A]. In L. K. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems[C], MIT Press, Cambridge, MA, 2005: 1601–1608.
[202] D.M.J. Tax, R.P.W. Duin, Support vector data description [J], Machine Learning, 54(1), 2004, 45-66.
[203] Hong Gu, Guangzhou Zhao, Hongbo Wang, Shape Representation and recognition in high dimensional feature space [A]. International Conference on Computational Intelligence and Natural Computing[C]. Wuhan, China, 2009.
[204] Changjun CHEN, Yongzhao ZHAN, Chuanjun WEN, Hierarchical face recognition based on SVDD and SVM [A]. International Conference on Environmental Science and Information Application Technology[C]. Wuhan, China, 2009.
[205] V.M.O. Alves, A.L.I. Oliveira, E.R. Silva, et al. Handwritten digit segmentation in images of historical documents with one-class classifiers [A]. 20th IEEE International Conference on Tools with Artificial Intelligence[C]. Vol. 2, 2008, pp: 41-44.
[206] P. Varchol, D. Levicky, J. Juhar, Optimalization of GMM for text independent speaker verification system [A]. 18th International Conference on Radioelektronika[C]. Prague, 2008.
[207] B. Sch?lkopf, J. C. Platt, Estimating the support of a high-dimensional distribution [J]. Neural Computation, 2001, 13 (7): 1443-1471.
[208] G.R.G. Lanckriet, L.E. Ghaoui, M. Jordan, Robust novelty detection with single-class MPM [A]. Advances in Neural Information Processing Systems[C]. Cambridge: MIT Press, 2002: 905-912.
[209] I.W. Tsang, T.K. James, S. Li, Learning the kernel in Mahalanobis one-class support vector machines [A]. Proceedings of the International Joint Conference on Neural Networks[C]. Vancouver, Canada, 2006.
[210] A. Dolia, C. Harris, J. Shawe-Taylor, Kernel ellipsoidal trimming [J]. Computational Statistics and Data Analysis, 2007, 52(1): 309-324.
[211] T. Mu, A.K. Nandi, Multiclass classification based on extended support vector data description [J]. IEEE Transaction on System, Man and Cybernetics- Part B: Cybernetics, 2009, 39(5): 1206-1216.
[212] K.Y. Lee, D.W. Kim, K.H. Lee, D. Lee, Density-Induced support vector data description [J]. IEEE Transaction on Neural Networks, 2007, 18(1): 284-289.
[213]冯爱民,薛晖,刘学军,等.增强型单类支持向量机[J].计算机研究与发展, 2008, 45(11): 1858-1864.
[214] Chu C S, Tsang I W, Kwok J T. Scaling up support vector data description by using core-sets [A]. Proceedings of IEEE International Joint Conference on Neural Networks[C]. 2004, 1: 425-430.
[215]陆从德,张太镒,胡金燕.基于乘性规则的支持向量域分类器[J].计算机学报, 2004, 27(5): 690-694.
[216]赵英刚,陈奇,何钦铭.基于支持向量域数据描述的快速学习算法[J].仪器仪表学报, 2006, 27(6): 798-800.
[217] D.M.J. Tax, DDtools_the data description toolbox for Matlab (version 1.7.3). http: // ict.ewi.tudelft.nl/ ~davidt/dd_tools.html, 2009.
[218] David M J T. One-class classifier results [DB/OL]. http://ict.ewi.tudelft.nl/~davidt/occ/index.html, 2009/2010-2-20.
[219]陈斌,李斌,潘志松,等.流形嵌入的支持向量数据描述[J].模式识别与人工智能. 2009, 22(4): 548-553.