A Deep Neural Network Model for Speaker Identification
Source abstract
Abstract
Speaker identification is a classification task which aims to identify a subject from a given time-series sequential data. Since the speech signal is a continuous one-dimensional time series, most of the current research methods are based on convolutional neural network (CNN) or recurrent neural network (RNN). Indeed, these methods perform well in many tasks, but there is no attempt to combine these two network models to study the speaker identification task. Due to the spectrogram that a speech signal contains, the spatial features of voiceprint (which corresponds to the voice spectrum) and CNN are effective for spatial feature extraction (which corresponds to modeling spectral correlations in acoustic features). At the same time, the speech signal is in a time series, and deep RNN can better represent long utterances than shallow networks. Considering the advantage of gated recurrent unit (GRU) (compared with traditional RNN) in the segmentation of sequence data, we decide to use stacked GRU layers in our model for frame-level feature extraction. In this paper, we propose a deep neural network (DNN) model based on a two-dimensional convolutional neural network (2-D CNN) and gated recurrent unit (GRU) for speaker identification. In the network model design, the convolutional layer is used for voiceprint feature extraction and reduces dimensionality in both the time and frequency domains, allowing for faster GRU layer computation. In addition, the stacked GRU recurrent network layers can learn a speaker’s acoustic features. During this research, we tried to use various neural network structures, including 2-D CNN, deep RNN, and deep LSTM. The above network models were evaluated on the Aishell-1 speech dataset. The experimental results showed that our proposed DNN model, which we call deep GRU, achieved a high recognition accuracy of 98.96%. At the same time, the results also demonstrate the effectiveness of the proposed deep GRU network model versus other models for speaker identification. Through further optimization, this method could be applied to other research similar to the study of speaker identification.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Speech Recognition and Synthesis · Music and Audio Processing · Speech and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China
University of Chinese Academy of Sciences, Beijing 100049, China
References (57)
Show source-provided references
1. An Overview of Text-Independent Speaker Recognition: From Features to Supervectors10.1016/j.specom.2009.08.009 ↗
2. Recent Advances in Speaker Recognition10.1016/S0167-8655(97)00073-1 ↗
3. Reynolds, D.A. (2002, January 13–17). An Overview of Automatic Speaker Recognition Technology. Proceedings of the 2002 IEEE International Conference Acoust. Speech Signal Process, Orlando, FL, USA.10.1109/ICASSP.2002.5745552 ↗
4. Speaker Recognition: A Tutorial10.1109/5.628714 ↗
5. Robust text-independent speaker identification using Gaussian mixture speaker models10.1109/89.365379 ↗
6. An Overview of Speaker Identification: Accuracy and Robustness Issues10.1109/MCAS.2011.941079 ↗
7. Li, B. (2011, January 22–24). On identity authentication technology of distance education system based on voiceprint recognition. Proceedings of the 30th Chinese Control Conference, Yantai, China.
8. Chen, Y.-H., Ignacio, L.-M., Sainath, T.N., Mirkó, V., Raziel, A., and Carolina, P. (2015, January 6–10). Locally-connected and convolutional neural networks for small footprint speaker; recognition. Proceedings of the Sixteenth Annual Conference of the International Speech Communication Association, Dresden, Germany.10.21437/Interspeech.2015-297 ↗
9. Parveen, S., Qadeer, A., and Green, P. (2000, January 16–20). Speaker recognition with recurrent neural networks. Proceedings of the Sixth International Conference on Spoken Language Processing, Beijing, China.10.21437/ICSLP.2000-270 ↗
10. Speaker recognition for Hindi speech signal using MFCC-GMM approach10.1016/j.procs.2017.12.112 ↗
11. Ren, J., Hu, Y., Tai, Y.-W., Wang, C., Xu, L., Sun, W., and Yan, Q. (2016, January 12–17). Look, listen and learn—A multimodal LSTM for speaker identification. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.10.1609/aaai.v30i1.10471 ↗
12. Bu, H., Du, J., Na, X., Wu, B., and Zheng, H. (2017, January 1–3). AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline. Proceedings of the 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA), Seoul, Korea.10.1109/ICSDA.2017.8384449 ↗
13. Steps toward Artificial Intelligence10.1109/JRPROC.1961.287775 ↗
14. Machine learning: Trends, perspectives, and prospects10.1126/science.aaa8415 ↗
15. Wang, L., Minami, K., Yamamoto, K., and Nakagawa, S. (2010, January 14–19). Speaker Identification by Combining MFCC and Phase Information in Noisy Environments. Proceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, USA.10.1109/ICASSP.2010.5495586 ↗
16. Gudnason, J., and Brookes, M. (April, January 31). Voice source cepstrum coefficients for speaker identification. Proceedings of the 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA.10.1109/ICASSP.2008.4518736 ↗
17. Lawson, A., Vabishchevich, P., Huggins, M., Ardis, P., Battles, B., and Stauffer, A. (2008, January 22–27). Survey and Evaluation of Acoustic Features for Speaker Recognition. Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic.10.1109/ICASSP.2011.5947590 ↗
18. Georgescu, A., and Cucu, H. (2018, January 14–16). GMM-UBM Modeling for Speaker Recognition on a Romanian Large Speech Corpora. Proceedings of the 2018 International Conference on Communications (COMM), Bucharest, Romania.10.1109/ICComm.2018.8484814 ↗
19. Speaker Identification in the Shouted Environment Using Suprasegmental Hidden Markov Models10.1016/j.sigpro.2008.05.012 ↗
20. Deep Learning-Based Hybrid Intelligent Intrusion Detection System
21. Shafik, A., Sedik, A., Abd El-Rahiem, B., El-Rabaie, E.-S.M., El Banby, G.M., Abd El-Samie, F.E., Khalaf, A.A.M., Song, O.-Y., and Iliyasu, A.M. (2021). Speaker identification based on Radon transform and CNNs in the presence of different types of interference for Robotic Applications. Appl. Acoust., 177.10.1016/j.apacoust.2020.107665 ↗
22. Lukic, Y., Vogt, C., Dürr, O., and Stadelmann, T. (2016, January 13–16). Speaker Identification and Clustering Using Convolutional Neural Networks. Proceedings of the 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), Vietri sul Mare, Italy.10.1109/MLSP.2016.7738816 ↗
23. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
24. Graves, A., Jaitly, N., and Mohamed, A. (2013, January 8–12). Hybrid speech recognition with Deep Bidirectional LSTM. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.10.1109/ASRU.2013.6707742 ↗
25. Mikolov, T., Karafiát, M., Burget, L., Cernocký, J., and Khudanpur, S. (2010, January 26–30). Recurrent Neural Network Based Language Model. Proceedings of the INTERSPEECH 2010 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan.10.21437/Interspeech.2010-343 ↗
26. Gelly, G., Gauvain, J.-L., Le, V.B., and Messaoudi, A. (2016, January 8–12). A Divide-and-Conquer Approach for Language Identification Based on Recurrent Neural Networks. Proceedings of the INTERSPEECH, San Francisco, CA, USA.10.21437/Interspeech.2016-180 ↗
27. LSTM recurrent networks learn simple context-free and context-sensitive languages10.1109/72.963769 ↗
28. A Novel Connectionist System for Unconstrained Handwriting Recognition10.1109/TPAMI.2008.137 ↗
29. Eyben, F., Wöllmer, M., Schuller, B., Graves, A., Schlüter, R., and Ney, H. (December, January 13). From speech to letters—Using a novel neural network architecture for grapheme based ASR. Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, Moreno, Italy.10.1109/ASRU.2009.5373257 ↗
30. Wollmer, M., Eyben, F., Schuller, B., Rigoll, G., and Ney, H. (2011, January 22–27). A Multi-Stream ASR Framework for BLSTM Modeling of Conversational Speech. Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic.10.1109/ICASSP.2011.5947444 ↗
31. Kim, S., Kim, I., Vecchietti, L.F., and Har, D. (2020). Pose Estimation Utilizing a Gated Recurrent Unit Network for Visual Localization. Appl. Sci., 10.10.3390/app10248876 ↗
32. Zhang, X., Kuehnelt, H., and De Roeck, W. (2021). Traffic Noise Prediction Applying Multivariate Bi-Directional Recurrent Neural Network. Appl. Sci., 11.10.3390/app11062714 ↗
33. Althelaya, K.A., El-Alfy, E.M., and Mohammed, S. (2018, January 25–26). Stock market forecast using multivariate analysis with bidirectional and stacked (LSTM, GRU). Proceeding of the 2018 21st Saudi Computer Society National Computer Conference (NCC), Riyadh, Saudi Arabia.10.1109/NCG.2018.8593076 ↗
34. Air pollution forecasting based on attention-based LSTM neural network and ensemble learning10.1111/exsy.12511 ↗
35. Nagrani, A., Chung, J.S., and Zisserman, A. (2017). Voxceleb: A large-scale speaker identification dataset. arXiv.10.21437/Interspeech.2017-950 ↗
36. Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Bengio, C.L.Y., and Courville, A. (2017). Towards end-to-end speech recognition with deep convolutional neural networks. arXiv.10.21437/Interspeech.2016-1446 ↗
37. Wang, Y., Deng, X., Pu, S., and Huang, Z. (2017). Residual convolutional CTC networks for automatic speech recognition. arXiv.
38. Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., and Chen, G. (2016, January 20–22). Deep speech 2: End-to-end speech recognition in english and mandarin. Proceedings of the International Conference on Machine Learning, PMLR, New York, NY, USA.
39. Sainath, T.N., Weiss, R.J., Senior, A., Wilson, K.W., and Vinyals, O. (2015, January 6–10). Learning the speech front-end with raw waveform CLDNNs. Proceedings of the Sixteenth Annual Conference of the International Speech Communication Association, Dresden, Germany.10.21437/Interspeech.2015-1 ↗
40. Sak, H., Senior, A.W., and Beaufays, F. (2014). Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. arXiv.10.21437/Interspeech.2014-80 ↗
41. Liu, Y., Hou, D., Bao, J., and Qi, Y. (2017, January 11–12). Multi-step Ahead Time Series Forecasting for Different Data Patterns Based on LSTM Recurrent Neural Network. Proceedings of the 2017 14th Web Information Systems and Applications Conference (WISA), Liuzhou, China.
42. Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation. arXiv.10.3115/v1/D14-1179 ↗
43. Manabe, K., Asami, Y., Yamada, T., and Sugimori, H. (2021). Improvement in the Convolutional Neural Network for Computed Tomography Images. Appl. Sci., 11.10.3390/app11041505 ↗
44. Lin, Y.-Y., Zheng, W.-Z., Chu, W.C., Han, J.-Y., Hung, Y.-H., Ho, G.-M., Chang, C.-Y., and Lai, Y.-H. (2021). A Speech Command Control-Based Recognition System for Dysarthric Patients Based on Deep Learning Technology. Appl. Sci., 11.10.3390/app11062477 ↗
45. Deconvolutive Short-Time Fourier Transform Spectrogram10.1109/LSP.2009.2020887 ↗
46. Naderi, N., and Nasersharif, B. (2017, January 2–4). Ultiresolution convolutional neural network for robust speech recognition. Proceedings of the 2017 Iranian Conference on Electrical Engineering (ICEE), Tehran, Iran.10.1109/IranianCEE.2017.7985272 ↗
47. Fei, Z., and Zhang, J.-S. (2011, January 4–6). Softmax Discriminant Classifier. Proceedings of the 2011 Third International Conference on Multimedia Information Networking and Security, Shanghai, China.
48. Ioffe, S., and Szegedy, C. (2015, January 7–9). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France.
49. Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer normalization. arXiv.
50. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep Sparse Rectifier Neural Networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
51. Maas, A.L., Hannun, A.Y., and Ng, A.Y. (2013). Rectifier nonlinearities improve neural network acoustic models. Proc. Icml, 30.
52. Hestness, J., Narang, S., Ardalani, N., Diamos, G., Jun, H., Kianinejad, H., Patwary, M., Ali, M., Yang, Y., and Zhou, Y. (2017). Deep learning scaling is predictable, empirically. arXiv.
53. Gowdy, J.N., and Tufekci, Z. (2000, January 5–9). Mel-scaled discrete wavelet coefficients for speech recognition. Proceedings of the 2000 IEEE International Conference on Acoustics, Speech and Signal Processing, Istanbul, Turkey. Proceedings (Cat. No.00CH37100).
54. The NumPy Array: A Structure for Efficient Numerical Computation10.1109/MCSE.2011.37 ↗
55. Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv.
56. Dozat, T. (2016, January 19). Incorporating Nesterov Momentum into Adam. Available online: https://openreview.net/forum?id=OM0jvwB8jIp57ZJjtNEZ.
57. Feng, Y., Cai, X., and Ji, R. (2016, January 17–20). Evaluation of the deep nonlinear metric learning based speaker identification on the large scale of voiceprint corpus. Proceedings of the 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), Tianjin, China.