采用信噪比判决的双LD3320语音识别控制系统的设计
|
摘要
设计了由两块语音识别芯片LD3320构成的语音识别控制系统,包括硬件和软件的设计,硬件设计主要运用了LD3320、STM32F407等微处理器,软件设计主要应用基于信噪比判决的多结果筛选算法,最后,通过实验验证系统设计的有效性。从实验的结果看,双LD3320语音识别控制系统的识别率比单LD3320的识别结果提高10.48%。该系统体积小、功耗低、性能稳定、实时性好,在智能家居等领域具有较高的实用价值。
The speech recognition control system composed of two speech recognition chips LD3320 is designed, including the design of hardware and software. The hardware design mainly uses LD3320, STM32 F407, etc. The software design mainly uses the multi-result screening algorithm based on the SNR judgment. Finally, the effectiveness of the system design is verified by experiments. Based on the experimental results, it can be seen that the recognition rate of the speech recognition control system of dual LD3320 is 10.48 %, which is higher than that of a single LD3320 system. The system has the advantages of small size, low power consumption, good stability and real-time performance, which has high practical value in intelligent home and other fields.
The speech recognition control system composed of two speech recognition chips LD3320 is designed, including the design of hardware and software. The hardware design mainly uses LD3320, STM32 F407, etc. The software design mainly uses the multi-result screening algorithm based on the SNR judgment. Finally, the effectiveness of the system design is verified by experiments. Based on the experimental results, it can be seen that the recognition rate of the speech recognition control system of dual LD3320 is 10.48 %, which is higher than that of a single LD3320 system. The system has the advantages of small size, low power consumption, good stability and real-time performance, which has high practical value in intelligent home and other fields.
引文
[1] MELTZNER,GEOFFREY S,HEATON,et al.Development of sEMG sensors and algorithms for silent speech recognition[J]. Journal of Neural Engineering,2018,15(4):11.
[2] BENJAMIN LECOUTEUX,MICHEL VACHER.Distant speech processing for smart home:comparison of ASR approaches in scattered microphone network for voice command[J]. International Journal of Speech Technology,2018,21(3):601-618.
[3] FOLTYNSKI PIOTR,LADYZYNSKI PIOTR,et al.Efficacy of automatic bolus calculator with automatic speech recognition in patients with type 1 diabetes:a randomized cross-over trial[J]. Journal of Diabetes,2018,10(7):600-608.
[4] RASA LILEIKYT,LORI LAMEL,JEAN LUC GAUVAIN,et al.Conversational telephone speech recognition for Lithuanian[J]. Computer Speech&Language,2018,49:71-82.
[5]王中心,王东方,王亚伟,等.基于LD3320语音识别模块的智能家居声控系统[J].物联网技术,2016,11:19-21.
[6]林航.基于LD3320的智能家庭语音控制系统设计[J].宁德师范学院学报(自然科学版),2017,29(4):12-28.
[7]徐莹,孙春志,吴晨光.基于LD3320的智能家居一体化声控系统的设计[J].商丘师范学院学报,2016,32(6):37-41.
[8] ZHANG Z J,WANG C Y. The four-axis aircraft design of the quadrotor system based on STM32 MCU[J]. Journal of Jining Normal University, 2017,39(6):27-32.
[9]倪水平,常慧刚,徐玉平.基于信噪比估计的自适应频谱感知算法[J].计算机应用研究,2017,35(9):2725-2728.
[2] BENJAMIN LECOUTEUX,MICHEL VACHER.Distant speech processing for smart home:comparison of ASR approaches in scattered microphone network for voice command[J]. International Journal of Speech Technology,2018,21(3):601-618.
[3] FOLTYNSKI PIOTR,LADYZYNSKI PIOTR,et al.Efficacy of automatic bolus calculator with automatic speech recognition in patients with type 1 diabetes:a randomized cross-over trial[J]. Journal of Diabetes,2018,10(7):600-608.
[4] RASA LILEIKYT,LORI LAMEL,JEAN LUC GAUVAIN,et al.Conversational telephone speech recognition for Lithuanian[J]. Computer Speech&Language,2018,49:71-82.
[5]王中心,王东方,王亚伟,等.基于LD3320语音识别模块的智能家居声控系统[J].物联网技术,2016,11:19-21.
[6]林航.基于LD3320的智能家庭语音控制系统设计[J].宁德师范学院学报(自然科学版),2017,29(4):12-28.
[7]徐莹,孙春志,吴晨光.基于LD3320的智能家居一体化声控系统的设计[J].商丘师范学院学报,2016,32(6):37-41.
[8] ZHANG Z J,WANG C Y. The four-axis aircraft design of the quadrotor system based on STM32 MCU[J]. Journal of Jining Normal University, 2017,39(6):27-32.
[9]倪水平,常慧刚,徐玉平.基于信噪比估计的自适应频谱感知算法[J].计算机应用研究,2017,35(9):2725-2728.