Weighted Cluster-Range Loss and Criticality-Enhancement Loss for Speaker Recognition
Source abstract
Abstract
While traditional i-vector based methods are popular in the field of speaker recognition, deep learning has recently found more and more applications to the end-to-end models due to its attractive performance. One effective practice is the integration of attention mechanism into the Convolution Neural Networks (CNNs). In this work, a light-weight dual-path attention block is proposed by combining the self-attention and Convolutional Block Attention Module (CBAM), which helps to capture more multi-source features with neglectable extra time expense. Additionally, a Weighted Cluster-Range Loss (WCRL) is proposed to enhance the identification performance of Cluster-Range Loss (CRL) on indecisive samples. Besides, to address the low efficiency in the initial training stage of CRL, a novel Criticality-Enhancement Loss (CEL) is also presented. Both of the proposed loss functions could significantly promote the training efficiency and globally improve the recognition performance. Experimental results are presented to show the effectiveness of the proposed scheme, which achieves a competitive top-1 accuracy of 92.0%, top-5 accuracy of 97.6%, and Equal Error Rate (EER) of 3.5% on the VoxCeleb1 dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Speech Recognition and Synthesis · Speech and Audio Processing · Music and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
References (44)
Show source-provided references
1. An overview of speaker identification: Accuracy and robustness issues10.1109/MCAS.2011.941079 ↗
2. Report: A vector quantization approach to speaker recognition10.1002/j.1538-7305.1987.tb00198.x ↗
3. Speaker identification and verification using Gaussian mixture speaker models10.1016/0167-6393(95)00009-D ↗
4. Robust text-independent speaker identification using Gaussian mixture speaker models10.1109/89.365379 ↗
5. Speaker verification using adapted Gaussian mixture models10.1006/dspr.1999.0361 ↗
6. Support vector machines for speaker and language recognition10.1016/j.csl.2005.06.003 ↗
7. Front-end factor analysis for speaker verification10.1109/TASL.2010.2064307 ↗
8. Deep CNNs with self-attention for speaker identification10.1109/ACCESS.2019.2917470 ↗
9. Self-attention based speaker recognition using Cluster-Range Loss10.1016/j.neucom.2019.08.046 ↗
10. Sarkar, A.K., Matrouf, D., Bousquet, P.M., and Bonastre, J.F. (2012, January 9–13). Study of the effect of i-vector modeling on short and mismatch utterance duration for speaker verification. Proceedings of the Thirteenth Annual Conference of the International Speech Communication Association, Portland, OR, USA.10.21437/Interspeech.2012-347 ↗
11. Lei, Y., Scheffer, N., Ferrer, L., and McLaren, M. (2014, January 4–9). A novel scheme for speaker recognition using a phonetically-aware deep neural network. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy.10.1109/ICASSP.2014.6853887 ↗
12. Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., and Khudanpur, S. (2018, January 15–20). X-vectors: Robust dnn embeddings for speaker recognition. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8461375 ↗
13. Konig, Y., Heck, L., Weintraub, M., and Sonmez, K. (, January April). Nonlinear discriminant feature extraction for robust text-independent speaker recognition. Proceedings of the RLA2C, ESCA workshop on Speaker Recognition and its Commercial and Forensic Applications, Avignon, Spain.
14. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
15. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
16. Nagrani, A., Chung, J.S., and Zisserman, A. (2017). Voxceleb: A large-scale speaker identification dataset. arXiv.10.21437/Interspeech.2017-950 ↗
17. Yadav, S., and Rai, A. (2018, January 2–6). Learning Discriminative Features for Speaker Identification and Verification. Proceedings of the Interspeech, Hyderabad, India.10.21437/Interspeech.2018-1015 ↗
18. Cai, W., Chen, J., and Li, M. (2018). Exploring the encoding layer and loss function in end-to-end speaker and language recognition system. arXiv.10.21437/Odyssey.2018-11 ↗
19. Chung, J.S., Nagrani, A., and Zisserman, A. (2018). Voxceleb2: Deep speaker recognition. arXiv.10.21437/Interspeech.2018-1929 ↗
20. Cheng, J., Dong, L., and Lapata, M. (2016). Long short-term memory-networks for machine reading. arXiv.10.18653/v1/D16-1053 ↗
21. Parikh, A.P., Täckström, O., Das, D., and Uszkoreit, J. (2016). A decomposable attention model for natural language inference. arXiv.10.18653/v1/D16-1244 ↗
22. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
23. Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., and Bengio, Y. (2015, January 7–12). Attention-based models for speech recognition. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
24. Zhang, H., Goodfellow, I., Metaxas, D., and Odena, A. (2018). Self-attention generative adversarial networks. arXiv.
25. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., and Tang, X. (2017, January 21–26). Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.683 ↗
26. Woo, S., Park, J., Lee, J.Y., and So Kweon, I. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
27. Park, J., Woo, S., Lee, J.Y., and Kweon, I.S. (2018). Bam: Bottleneck attention module. arXiv.
28. Shaw, P., Uszkoreit, J., and Vaswani, A. (2018). Self-attention with relative position representations. arXiv.10.18653/v1/N18-2074 ↗
29. Shen, T., Zhou, T., Long, G., Jiang, J., Wang, S., and Zhang, C. (2018, January 13–19). Reinforced Self-Attention Network: A Hybrid of Hard and Soft Attention for Sequence Modeling. Proceedings of the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/604 ↗
30. Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 16–20). Dual attention network for scene segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00326 ↗
31. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
32. Chung, J.S., Huh, J., Mun, S., Lee, M., Heo, H.S., Choe, S., Ham, C., Jung, S., Lee, B.J., and Han, I. (2020). In defence of metric learning for speaker recognition. arXiv.10.21437/Interspeech.2020-1064 ↗
33. Liu, W., Wen, Y., Yu, Z., and Yang, M. (2016, January 19–24). Large-margin softmax loss for convolutional neural networks. Proceedings of the ICML, New York, NY, USA.
34. Wang, J., Zhou, F., Wen, S., Liu, X., and Lin, Y. (2017, January 22–29). Deep metric learning with angular loss. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.283 ↗
35. Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., Li, Z., and Liu, W. (2018, January 18–23). Cosface: Large margin cosine loss for deep face recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00552 ↗
36. Deng, J., Guo, J., Xue, N., and Zafeiriou, S. (2019, January 16–20). Arcface: Additive angular margin loss for deep face recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00482 ↗
37. Schroff, F., Kalenichenko, D., and Philbin, J. (2015, January 7–12). Facenet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298682 ↗
38. Spatial pyramid-enhanced NetVLAD with weighted triplet loss for place recognition10.1109/TNNLS.2019.2908982 ↗
39. Liu, H., Tian, Y., Yang, Y., Pang, L., and Huang, T. (2016, January 27–30). Deep relative distance learning: Tell the difference between similar vehicles. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.238 ↗
40. Wan, L., Wang, Q., Papir, A., and Moreno, I.L. (2018, January 15–20). Generalized end-to-end loss for speaker verification. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8462665 ↗
41. Li, C., Ma, X., Jiang, B., Li, X., Zhang, X., Liu, X., Cao, Y., Kannan, A., and Zhu, Z. (2017). Deep speaker: An end-to-end neural speaker embedding system. arXiv.
42. Fan, Y., Kang, J., Li, L., Li, K., Chen, H., Cheng, S., Zhang, P., Zhou, Z., Cai, Y., and Wang, D. (2020, January 4–8). CN-CELEB: A challenging Chinese speaker recognition dataset. Proceedings of the ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9054017 ↗
43. Shon, S., Tang, H., and Glass, J. (2018, January 18–21). Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model. Proceedings of the 2018 IEEE Spoken Language Technology Workshop (SLT), Athens, Greece.10.1109/SLT.2018.8639622 ↗
44. Chopra, S., Hadsell, R., and LeCun, Y. (2005, January 20–25). Learning a similarity metric discriminatively, with application to face verification. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA.