Abstract
In this paper we present an efficient method for training models for speaker recognition using small or under-resourced datasets. This method requires less data than other SOTA (State-Of-The-Art) methods, e.g. the Angular Prototypical and GE2E loss functions, while achieving similar results to those methods. This is done using the knowledge of the reconstruction of a phoneme in the speaker’s voice. For this purpose, a new dataset was built, composed of 40 male speakers, who read sentences in Portuguese, totaling approximately 3h. We compare the three best architectures trained using our method to select the best one, which is the one with a shallow architecture. Then, we compared this model with the SOTA method for the speaker recognition task: the Fast ResNet–34 trained with approximately 2,000 h, using the loss functions Angular Prototypical and GE2E. Three experiments were carried out with datasets in different languages. Among these three experiments, our model achieved the second best result in two experiments and the best result in one of them. This highlights the importance of our method, which proved to be a great competitor to SOTA speaker recognition models, with 500x less data and a simpler approach.
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
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)
Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 4218–4222 (2020)
Arik, S., Chen, J., Peng, K., Ping, W., Zhou, Y.: Neural voice cloning with a few samples. In: Advances in Neural Information Processing Systems, pp. 10019–10029 (2018)
Bowater, R.J., Porter, L.L.: Voice recognition of telephone conversations. US Patent 6,278,772 (21 August 2001)
Bredin, H.: TristouNet: triplet loss for speaker turn embedding. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5430–5434. IEEE (2017)
Cheng, J.M., Wang, H.C.: A method of estimating the equal error rate for automatic speaker verification. In: 2004 International Symposium on Chinese Spoken Language Processing, pp. 285–288. IEEE (2004)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 539–546. IEEE (2005)
Chung, J.S., et al.: In defence of metric learning for speaker recognition. In: Proceedings of the Interspeech 2020, pp. 2977–2981 (2020)
Cooper, E., et al.: Zero-shot multi-speaker text-to-speech with state-of-the-art neural speaker embeddings. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020, pp. 6184–6188. IEEE (2020)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690–4699 (2019)
Ertaş, F.: Fundamentals of speaker recognition. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi 6(2–3) (2011)
Ferrucci, D., et al.: Building Watson: an overview of the DeepQA project. AI Mag. 31(3), 59–79 (2010)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Gruber, T.: Siri, a virtual personal assistant-bringing intelligence to the interface (2009)
Heo, H.S., Lee, B.J., Huh, J., Chung, J.S.: Clova baseline system for the VoxCeleb speaker recognition challenge 2020. arXiv preprint arXiv:2009.14153 (2020)
Ioffe, S.: Probabilistic linear discriminant analysis. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 531–542. Springer, Heidelberg (2006). https://doi.org/10.1007/11744085_41
Kekre, H., Kulkarni, V.: Closed set and open set speaker identification using amplitude distribution of different transforms. In: 2013 International Conference on Advances in Technology and Engineering (ICATE), pp. 1–8. IEEE (2013)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220 (2017)
Logan, B., et al.: Mel frequency cepstral coefficients for music modeling. In: ISMIR, vol. 270, pp. 1–11 (2000)
McFee, B., et al.: librosa: audio and music signal analysis in Python. In: Proceedings of the 14th Python in Science Conference, pp. 18–25 (2015)
Michalski, R.S., Carbonell, J.G., Mitchell, T.M.: Machine learning: an artificial intelligence approach. Springer Science & Business Media (2013). https://doi.org/10.1007/978-3-662-12405-5
Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: Proceedings of the Interspeech 2017, pp. 2616–2620 (2017)
Nazaré, T.S., da Costa, G.B.P., Contato, W.A., Ponti, M.: Deep convolutional neural networks and noisy images. In: Mendoza, M., Velastín, S. (eds.) CIARP 2017. LNCS, vol. 10657, pp. 416–424. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75193-1_50
Nussbaumer, H.J.: The fast Fourier transform. In: Fast Fourier Transform and Convolution Algorithms, vol. 2, pp. 80–111. Springer, Heidelberg (1981). https://doi.org/10.1007/978-3-662-00551-4_4
Ping, W., et al.: Deep Voice 3: scaling text-to-speech with convolutional sequence learning. In: International Conference on Learning Representations (2018)
Ramoji, S., Krishnan V, P., Singh, P., Ganapathy, S.: Pairwise discriminative neural PLDA for speaker verification. arXiv preprint arXiv:2001.07034 (2020)
Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
Seara, I.: Estudo Estatístico dos Fonemas do Português Brasileiro Falado na Capital de Santa Catarina para Elaboração de Frases Foneticamente Balanceadas. Ph.D. thesis, Dissertação de Mestrado, Universidade Federal de Santa Catarina ... (1994)
Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Interspeech, pp. 999–1003 (2017)
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)
Tang, Y.: TF.Learn: Tensorflow’s high-level module for distributed machine learning. arXiv preprint arXiv:1612.04251 (2016)
Veaux, C., Yamagishi, J., MacDonald, K., et al.: Superseded-CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit. University of Edinburgh, The Centre for Speech Technology Research (CSTR) (2016)
Wan, L., Wang, Q., Papir, A., Moreno, I.L.: Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4879–4883. IEEE (2018)
Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin Softmax for face verification. IEEE Sig. Process. Lett. 25(7), 926–930 (2018)
Wang, J., Wang, K.C., Law, M.T., Rudzicz, F., Brudno, M.: Centroid-based deep metric learning for speaker recognition. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 3652–3656. IEEE (2019)
Zhou, Y., Tian, X., Xu, H., Das, R.K., Li, H.: Cross-lingual voice conversion with bilingual Phonetic PosteriorGram and average modeling. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 6790–6794. IEEE (2019)
Acknowledgments
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001, as well as CNPq (National Council of Technological and Scientific Development) grant 304266/2020-5. Also, we would like to thank the CyberLabs and Itaipu Technological Park (Parque Tecnológico Itaipu—PTI) for financial support for this paper. We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPU used in part of the experiments presented in this research.
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
Casanova, E. et al. (2021). Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models. In: Britto, A., Valdivia Delgado, K. (eds) Intelligent Systems. BRACIS 2021. Lecture Notes in Computer Science(), vol 13074. Springer, Cham. https://doi.org/10.1007/978-3-030-91699-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-91699-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91698-5
Online ISBN: 978-3-030-91699-2
eBook Packages: Computer ScienceComputer Science (R0)