Abstract
In this article we propose to study several approaches to adapt a system between two languages. To train the state of the art x-vector Speaker Verification system, we need a huge amount of labeled speech data. If this constraint is satisfied in English (due to Voxceleb), it is not in our target domain: French. We use a supervised Contrastive Learning to transfer knowledge between source and target domain. Among the two other proposed adaptation approaches (Multilingual Learning and Transfert Learning) we show that the one based on Contrastive Learning gives the best performance: about 30% relative gain in term of Equal Error Rate with respect to the baseline system. We also show the robustness of the Contrastive Learning with respect to the duration (from very short to short) as well as to distortion presence (noise, reverberation).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ajili, M., Bonastre, J.F., Kahn, J., Rossato, S., Bernard, G.: FABIOLE, a speech database for forensic speaker comparison. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 726–733. European Language Resources Association (ELRA), Portorož, May 2016. https://www.aclweb.org/anthology/L16-1115
Alam, M.J., Bhattacharya, G., Kenny, P.: Speaker verification in mismatched conditions with frustratingly easy domain adaptation. In: Proceedings of Speaker Odyssey: The Speaker and Language Recognition Workshop, pp. 176–180 (2018). https://doi.org/10.21437/Odyssey.2018-25
Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: Proceedings of the 12th Language Resources and Evaluation Conference (LREC 2020) (2020)
Bousquet, P., Rouvier, M.: On robustness of unsupervised domain adaptation for speaker recognition. In: Kubin, G., Kacic, Z. (eds.) Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15–19 September 2019, pp. 2958–2962. ISCA (2019). https://doi.org/10.21437/Interspeech.2019-1524
Brummer, N., et al.: But+ omilia system description voxceleb speaker recognition challenge 2020 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. CoRR abs/2002.05709 (2020). https://arxiv.org/abs/2002.05709
Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: deep speaker recognition. CoRR abs/1806.05622 (2018). http://arxiv.org/abs/1806.05622
Ganvir, S., Lal, N.: Automatic speaker recognition using transfer learning approach of deep learning models. In: 2021 6th International Conference on Inventive Computation Technologies (ICICT), pp. 595–601 (2021). https://doi.org/10.1109/ICICT50816.2021.9358539
Giraudel, A., Carré, M., Mapelli, V., Kahn, J., Galibert, O., Quintard, L.: The REPERE corpus: a multimodal corpus for person recognition, pp. 1102–1107 (2012). http://www.lrec-conf.org/proceedings/lrec2012/summaries/707.html
Guillermo Barbadillo, S.P.: Veridas solution for SdSV challenge technical report (2019)
Kahn, J., Galibert, O., Quintard, L., Carré, M., Giraudel, A., Joly, P.: A presentation of the repere challenge. In: 2012 10th International Workshop on Content-Based Multimedia Indexing (CBMI), pp. 1–6 (2012). https://doi.org/10.1109/CBMI.2012.6269851
Ko, T., Peddinti, V., Povey, D., Seltzer, M.L., Khudanpur, S.: A study on data augmentation of reverberant speech for robust speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5220–5224 (2017). https://doi.org/10.1109/ICASSP.2017.7953152
Lee, K.A., Wang, Q., Koshinaka, T.: The coral+ algorithm for unsupervised domain adaptation of PLDA. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5821–5825. IEEE (2019)
Lee, K.A., et al.: The NEC-TT 2018 speaker verification system. In: Interspeech, pp. 4355–4359 (2019)
Pierre-Michel Bousquet, M.R.: The LIA system description for SdSV challenge task 2 (2019). https://sdsvc.github.io/2020/descriptions/Team42_Task2.pdf
Povey, D., et al.: The kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, December 2011. iEEE Catalog No.: CFP11SRW-USB
Rouvier, M., Bousquet, P., Ajili, M., Kheder, W.B., Matrouf, D., Bonastre, J.: LIA system description for NIST SRE 2016 (2016). http://arxiv.org/abs/1612.05168
Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus. CoRR abs/1510.08484 (2015). http://arxiv.org/abs/1510.08484
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 (2018). https://doi.org/10.1109/ICASSP.2018.8461375
Thienpondt, J., Desplanques, B., Demuynck, K.: The IDLAB voxceleb speaker recognition challenge 2020 system description. CoRR abs/2010.12468 (2020). https://arxiv.org/abs/2010.12468
Torgashov, N.: ID R&D system description to voxceleb speaker recognition challenge 2020 (2020)
Villalba, J., et al.: The JHU-MIT system description for NIST SRE18 (2018). https://sdsvc.github.io/2020/descriptions/Team10_Both.pdf
Villalba, J., Dehak, N.: The JHU system description for SDSV2020 challenge (2019)
Wang, Q., Okabe, K., Lee, K.A., Koshinaka, T.: A generalized framework for domain adaptation of PLDA in speaker recognition. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6619–6623. IEEE (2020)
Xia, W., Zhang, C., Weng, C., Yu, M., Yu, D.: Self-supervised text-independent speaker verification using prototypical momentum contrastive learning (2020). https://arxiv.org/abs/2012.07178
Zeinali, H., Wang, S., Silnova, A., Matejka, P., Plchot, O.: BUT system description to voxceleb speaker recognition challenge 2019. CoRR abs/1910.12592 (2019). http://arxiv.org/abs/1910.12592
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Brignatz, V., Duret, J., Matrouf, D., Rouvier, M. (2021). Language Adaptation for Speaker Recognition Systems Using Contrastive Learning. In: Karpov, A., Potapova, R. (eds) Speech and Computer. SPECOM 2021. Lecture Notes in Computer Science(), vol 12997. Springer, Cham. https://doi.org/10.1007/978-3-030-87802-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-87802-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87801-6
Online ISBN: 978-3-030-87802-3
eBook Packages: Computer ScienceComputer Science (R0)