Research on Cross-device Voiceprint Recognition Method Based on Deep Learning

PDF(1582 KB)

Integrated Circuits and Embedded Systems ›› 2022, Vol. 22 ›› Issue (12) : 16-19.

TOPICAL DISCUSS

Research on Cross-device Voiceprint Recognition Method Based on Deep Learning

Li Wei^1,2, Wang Pengcheng¹, Zhong Xiao^1,2, La Erchelongbu¹

Author information +

History +

Abstract

Aiming at the problem that the performance of voiceprint recognition is poor under the condition of cross-device voiceprint recognition in the actual application scenario of traditional voiceprint recognition method,a cross-device voiceprint recognition method based on deep learning is proposed.The model architecture of convolutional circular network is adopted,multi-segment speech is recorded in the voiceprint registration stage for fitting modeling of voiceprint features.The voiceprint recognition stage is used to extract audio speech information in the voiceprint recognition stage,and the dual microphone supported by the DSP chip is used to collect live sound on the device side.The test results show that the recognition accuracy of the voiceprint recognition method proposed in this paper is better than the current mainstream voiceprint recognition method under the condition of cross-device voiceprint recognition,which can achieve 80% voiceprint recognition accuracy.

Key words

convolutional recurrent network / deep learning / cross-device voiceprint recognition

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Li Wei, Wang Pengcheng, Zhong Xiao, La Erchelongbu. Research on Cross-device Voiceprint Recognition Method Based on Deep Learning[J]. Integrated Circuits and Embedded Systems. 2022, 22(12): 16-19

References

[1] 郑方,李蓝天,张慧,等.声纹识别技术及其应用现状[J].信息安全研究,2016,2(1):4457.
[2] 郑方,艾斯卡尔·肉孜,王仁宇,等.生物特征识别技术综述[J].信息安全研究,2016,2(1):1226.
[3] 孔春晓.现代生物识别技术综述[J].山东公安专科学校学报,2003(4):96100.
[4] 檀蕊莲,刘建平,李哲.说话人识别技术及其应用[J].信息技术,2007(12):2325,29.
[5] Kersta L G.Voiceprint identification[J].The Journal of the Acoustical Society of America,1962,34(5):725.
[6] 周玥媛,孔钦.基于GMMUBM的声纹识别技术的特征参数研究[J].计算机技术与发展,2020,30(5):7683.
[7] Kenny P,Ouellet P,Dehak N,et al.A study of interspeaker variability in speaker verification[J].IEEE Transactions on Audio,Speech,and Language Processing,2008,16(5):980988.
[8] 林舒都,邵曦.基于ivector和深度学习的说话人识别[J].计算机技术与发展,2017,27(6):6671.
[9] Heigold G,Moreno I,Bengio S,et al.Endtoend textdependent speaker verification[C]//2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).IEEE,2016:51155119.
[10] Li C,Ma X,Jiang B,et al.Deep speaker: an endtoend neural speaker embedding system[J].arXiv preprint arXiv:1705.02304,2017.
[11] Snyder D,GarciaRomero D,Sell G,et al.Xvectors: Robust dnn embeddings for speaker recognition[C]//2018 IEEE international conference on acoustics,speech and signal processing (ICASSP).IEEE,2018:53295333.
[12] Liu Y,Qian Y,Chen N,et al.Deep feature for textdependent speaker verification[J].Speech Communication,2015(73):113.
[13] 申志生,于明.说话人识别算法的定点DSP实现[J].单片机与嵌入式系统应用,2011,11(3):7879.
[14] Hochreiter S,Schmidhuber J.Long shortterm memory[J].Neural computation,1997,9(8):17351780.
[15] 王东,游世学.跨场景声纹识别的现状与未来[J].中国安防,2022(3):3540.