基于CNN与MFCC的城市场景声音识别
|
摘要
城市环境中包含着各种各样的杂音,针对这种复杂的声音识别环境,该文提出一种基于MFCC与CNN的声音识别方法.首先对城市环境声音样本进行梅尔特征提取,取得特征图之后由卷积神经网络进行训练、测试获得CNN特征,最后由SVM分类器识别分类,并将其与常见的音频识别方法对比分析,在识别速度和识别率上均有所优化,实验表明,此方法在复杂环境下能够得到较好的声音识别效果.
There are all kinds of noises in the urban environment.In view of this complex voice recognition environment,this paper proposes a voice recognition method based on MFCC and CNN.At first,meier feature extraction is carried out on urban environmental sound samples,and then the feature map is obtained,and then the CNN feature is trained and tested by convolutional neural network.Finally,the classification is recognized by SVM classifier.Compared with the common audio recognition methods,the method is optimized in recognition speed and recognition rate,which proves that the method can obtain better sound recognition effect in complex environment.
There are all kinds of noises in the urban environment.In view of this complex voice recognition environment,this paper proposes a voice recognition method based on MFCC and CNN.At first,meier feature extraction is carried out on urban environmental sound samples,and then the feature map is obtained,and then the CNN feature is trained and tested by convolutional neural network.Finally,the classification is recognized by SVM classifier.Compared with the common audio recognition methods,the method is optimized in recognition speed and recognition rate,which proves that the method can obtain better sound recognition effect in complex environment.
引文
[1]麻旻,李祥.一种基于MATLAB实现的男女声识别算法[J].仪表技术,2018(7).
[2]全璐,侯文,李秉臻,等.BP神经网络的枪声识别[J].电声技术,2018(2).
[3]陈秋菊,李应.基于优化正交匹配追踪和深度置信网的声音识别[J].计算机应用,2017,37(2):505-511.
[4]Andics A,Mcqueen J M,Petersson K M,et al.Neural mechanisms for voice recognition[J].Neuroimage,2010,52(4):1528-1540.
[5]Mcclelland J.Learning internal representations by error propagation[C]//Cambridge:MIT Press,1986:318-362.
[6]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[7]Lecun Y,Boser B,Denker J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation,2014,1(4):541-551.
[8]CHIN Tenglin,CHONG Pingjou,CHENG Jianglin.GA-based reinforcement learning for neural networks[J].International Journal of Systems Science,1998,29(3):233-247.
[9]Hinton G,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[10]Simard P,Le Cun,Dender J.Efficient pattern recognition using a new transformation distance[C]//Advances in Neural Information Processing Systems 5.NIPS,1992.
[11]Hubel D H,Wiesel T N.Receptive fields,binocular interaction and functional architecture in the cat's visual cortex[J].J Physiol,1962,160(1):106-154.
[12]Jian W,He J,Kai C,et al.Collaborative filtering and deep learning based recommendation system for cold start items[J].Expert Systems with Applications,2017,69:29-39.
[13]Chang L,Deng X M,Zhou M Q,et al.Convolutional neural networks in image understanding[J].Acta Automatica Sinica,2016.
[14]Girshick R,Donahue J,Darrell T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2015,38(1):142-158.
[15]史秋莹,郑铁然.基于深度学习的环境声音识别[J].智能计算机与应用,2018(5).
[16]张文涛,韩莹莹,黎恒.基于卷积神经网络的交通声音事件识别方法[J].现代电子技术,2018(14).
[2]全璐,侯文,李秉臻,等.BP神经网络的枪声识别[J].电声技术,2018(2).
[3]陈秋菊,李应.基于优化正交匹配追踪和深度置信网的声音识别[J].计算机应用,2017,37(2):505-511.
[4]Andics A,Mcqueen J M,Petersson K M,et al.Neural mechanisms for voice recognition[J].Neuroimage,2010,52(4):1528-1540.
[5]Mcclelland J.Learning internal representations by error propagation[C]//Cambridge:MIT Press,1986:318-362.
[6]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[7]Lecun Y,Boser B,Denker J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation,2014,1(4):541-551.
[8]CHIN Tenglin,CHONG Pingjou,CHENG Jianglin.GA-based reinforcement learning for neural networks[J].International Journal of Systems Science,1998,29(3):233-247.
[9]Hinton G,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[10]Simard P,Le Cun,Dender J.Efficient pattern recognition using a new transformation distance[C]//Advances in Neural Information Processing Systems 5.NIPS,1992.
[11]Hubel D H,Wiesel T N.Receptive fields,binocular interaction and functional architecture in the cat's visual cortex[J].J Physiol,1962,160(1):106-154.
[12]Jian W,He J,Kai C,et al.Collaborative filtering and deep learning based recommendation system for cold start items[J].Expert Systems with Applications,2017,69:29-39.
[13]Chang L,Deng X M,Zhou M Q,et al.Convolutional neural networks in image understanding[J].Acta Automatica Sinica,2016.
[14]Girshick R,Donahue J,Darrell T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2015,38(1):142-158.
[15]史秋莹,郑铁然.基于深度学习的环境声音识别[J].智能计算机与应用,2018(5).
[16]张文涛,韩莹莹,黎恒.基于卷积神经网络的交通声音事件识别方法[J].现代电子技术,2018(14).