Abstract
Background noise significantly impacts speech intelligibility, reducing the accuracy and reliability of the speaker verification system. Most existing noise reduction algorithms are specific to certain types of noise and have limitations, making them ineffective on eliminating background noise. Therefore, the extraction of robust features and the development of noise-resistant models that adapt to various noisy environments remain crucial challenges in the field of speaker verification. In this paper, we propose a Conformer-based Audio Scoring Conformer with Fast Fourier Convolution (ASF-Conformer), which is a speaker verification model. Firstly, the audio scoring module is introduced to evaluate and weight the audio features, aiming to select more robust features in noisy environments. Secondly, we introduce Fast Fourier Convolution as a replacement for the Conformer’s convolution module, improving the model’s ability to capture global features while reducing the model parameters. Finally, this paper conducts comparative tests with the current mainstream models on public dataset VoxCeleb1, and synthesized noisy dataset Mu-VoxCeleb1. The experimental results demonstrate that the proposed ASF-Conformer model, compared to the ECAPA-TDNN model with essentially the same parameters, outperforms ECAPA-TDNN by 2% and 18% respectively when evaluated using the EER metrics on the VoxCeleb1 and Mu-VoxCeleb1 datasets. These results highlight the effectiveness of the proposed model in enhancing the accuracy of speaker verification tasks, especially in noisy environments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cai, D., Cai, W., Li, M.: Within-sample variability-invariant loss for robust speaker recognition under noisy environments. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6469–6473. IEEE (2020). https://doi.org/10.1109/ICASSP40776.2020.9053407
Chen, L., Liang, Y., Shi, X., Zhou, Y., Wu, C.: Crossed-time delay neural network for speaker recognition. In: Lokoč, J., et al. (eds.) MMM 2021. LNCS, vol. 12572, pp. 1–10. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67832-6_1
Chen, S., et al.: Continuous speech separation with conformer. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5749–5753. IEEE (2021). https://doi.org/10.1109/ICASSP39728.2021.9413423
Chung, J.S., et al.: In defence of metric learning for speaker recognition. arXiv preprint arXiv:2003.11982 (2020)
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)
Desplanques, B., Thienpondt, J., Demuynck, K.: Ecapa-tdnn: emphasized channel attention, propagation and aggregation in tdnn based speaker verification. arXiv preprint arXiv:2005.07143 (2020)
Hong, J., Kim, M., Choi, J., Ro, Y.M.: Watch or listen: robust audio-visual speech recognition with visual corruption modeling and reliability scoring. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18783–18794 (2023). https://doi.org/10.1109/CVPR52729.2023.01801
Jin, M., Yoo, C.D.: Speaker verification and identification. In: Behavioral Biometrics for Human Identification: Intelligent Applications, pp. 264–289. IGI Global (2010)
Jung, J.w., Heo, H.S., Kim, J.h., Shim, H.J., Yu, H.J.: Rawnet: advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification. arXiv preprint arXiv:1904.08104 (2019)
Kim, J.h., Heo, J., Shim, H.j., Yu, H.J.: Extended u-net for speaker verification in noisy environments. arXiv preprint arXiv:2206.13044 (2022)
Koizumi, Y., et al.: Df-conformer: integrated architecture of conv-tasnet and conformer using linear complexity self-attention for speech enhancement. In: 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 161–165. IEEE (2021). https://doi.org/10.1109/WASPAA52581.2021.9632794
Li, Y., Lin, X.: Dual-stream time-delay neural network with dynamic global filter for speaker verification. arXiv preprint arXiv:2303.11020 (2023)
Liu, T., Das, R.K., Lee, K.A., Li, H.: Mfa: Tdnn with multi-scale frequency-channel attention for text-independent speaker verification with short utterances. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7517–7521. IEEE (2022). https://doi.org/10.1109/ICASSP43922.2022.9747021
Matejka, P., Novotnỳ, O., Plchot, O., Burget, L., Sánchez, M.D., Cernockỳ, J.: Analysis of score normalization in multilingual speaker recognition. In: Interspeech, pp. 1567–1571 (2017). https://doi.org/10.21437/Interspeech. 2017–803
Nagrani, A., Chung, J.S., Zisserman, A.: Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)
Pelecanos, J., Sridharan, S.: Feature warping for robust speaker verification. In: Proceedings of 2001 A Speaker Odyssey: The Speaker Recognition Workshop, pp. 213–218. European Speech Communication Association (2001)
Snyder, D., Chen, G., Povey, D.: Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)
Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust dnn embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329–5333. IEEE (2018). https://doi.org/10.1109/ICASSP.2018.8461375
Thienpondt, J., Desplanques, B., Demuynck, K.: Integrating frequency translational invariance in tdnns and frequency positional information in 2d resnets to enhance speaker verification. arXiv preprint arXiv:2104.02370 (2021)
Variani, E., Lei, X., McDermott, E., Moreno, I.L., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4052–4056. IEEE (2014). https://doi.org/10.1109/ICASSP.2014.6854363
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)
Wang, C., et al.: Unispeech: unified speech representation learning with labeled and unlabeled data. In: International Conference on Machine Learning, pp. 10937–10947. PMLR (2021)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems 32 (2019)
Zhang, Y., et al.: Mfa-conformer: multi-scale feature aggregation conformer for automatic speaker verification. arXiv preprint arXiv:2203.15249 (2022)
Zhou, T., Zhao, Y., Wu, J.: Resnext and res2net structures for speaker verification. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 301–307. IEEE (2021). https://doi.org/10.1109/SLT48900.2021.9383531
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, X., Liu, H., Liu, C., Zhang, H., Huo, Z. (2024). ASF-Conformer: Audio Scoring Conformer with FFC for Speaker Verification in Noisy Environments. In: Rudinac, S., et al. MultiMedia Modeling. MMM 2024. Lecture Notes in Computer Science, vol 14556. Springer, Cham. https://doi.org/10.1007/978-3-031-53311-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-53311-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53310-5
Online ISBN: 978-3-031-53311-2
eBook Packages: Computer ScienceComputer Science (R0)