Abstract
Pre-trained models used in the transfer-learning scenario are recently becoming very popular. Such models benefit from the availability of large sets of unlabeled data. Two kinds of such models include the Wav2Vec 2.0 speech recognizer and T5 text-to-text transformer. In this paper, we describe a novel application of such models for dialog systems, where both the speech recognizer and the spoken language understanding modules are represented as Transformer models. Such composition outperforms the baseline based on the DNN-HMM speech recognizer and CNN understanding.
This research was supported by the Czech Science Foundation (GA CR), project No. GA22-27800S and by the grant of the University of West Bohemia, project No. SGS-2022–017.
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
Baevski, A., Rahman Mohamed, A.: Effectiveness of self-supervised pre-training for ASR. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7694–7698 (2020)
Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2Vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449–12460 (2020)
Deng, L., Li, X.: Machine learning paradigms for speech recognition: an overview. IEEE Trans. Audio Speech Lang. Process. 21(5), 1060–1089 (2013). https://doi.org/10.1109/TASL.2013.2244083
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the NAACL: HLT, Vol. 1, pp. 4171–4186. ACL, Minneapolis, Minnesota (2019)
He, Y., Young, S.: Spoken language understanding using the hidden vector state model. Speech Commun. 48(3), 262–275 (2006). https://doi.org/10.1016/j.specom.2005.06.002. www.sciencedirect.com/science/article/pii/S0167639305001421. Spoken Language Understanding in Conversational Systems
Henderson, M., Gašić, M., Thomson, B., Tsiakoulis, P., Yu, K., Young, S.: Discriminative spoken language understanding using word confusion networks. In: 2012 IEEE Spoken Language Technology Workshop (SLT), pp. 176–181 (2012). https://doi.org/10.1109/SLT.2012.6424218
Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790–2799. PMLR (2019)
Jurčíček, F., Zahradil, J., Jelínek, L.: A human-human train timetable dialogue corpus. In: Proceedings of EUROSPEECH, Lisboa, pp. 1525–1528 (2005). ftp://ftp.cs.pitt.edu/web/projects/nlp/conf/interspeech2005/IS2005/PDF/AUTHOR/IS051430.PDF
Karita, S., Soplin, N.E.Y., Watanabe, S., Delcroix, M., Ogawa, A., Nakatani, T.: Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration. In: Proceedings Interspeech 2019, pp. 1408–1412 (2019). https://doi.org/10.21437/Interspeech.2019-1938
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1–67 (2020)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2020). arXiv preprint arXiv:1910.10683
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wang, C., et al.: VoxPopuli: a large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 993–1003. Association for Computational Linguistics (2021). https://aclanthology.org/2021.acl-long.80
Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45. Association for Computational Linguistics (2020)
Švec, J., Chýlek, A., Šmídl, L.: Hierarchical discriminative model for spoken language understanding based on convolutional neural network. In: Proceedings Interspeech 2015, pp. 1864–1868 (2015). https://doi.org/10.21437/Interspeech.2015-72
Švec, J., Chýlek, A., Šmídl, L., Ircing, P.: A study of different weighting schemes for spoken language understanding based on convolutional neural networks. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6065–6069 (2016). https://doi.org/10.1109/ICASSP.2016.7472842
Švec, J., Šmídl, L., Ircing, P.: Hierarchical discriminative model for spoken language understanding. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8322–8326 (2013). https://doi.org/10.1109/ICASSP.2013.6639288
Acknowledgement
Computational resources were supplied by the project “e-Infrastruktura CZ" (e-INFRA CZ LM2018140) supported by the Ministry of Education, Youth and Sports of the Czech Republic.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Švec, J., Frémund, A., Bulín, M., Lehečka, J. (2022). Transfer Learning of Transformers for Spoken Language Understanding. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech, and Dialogue. TSD 2022. Lecture Notes in Computer Science(), vol 13502. Springer, Cham. https://doi.org/10.1007/978-3-031-16270-1_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-16270-1_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16269-5
Online ISBN: 978-3-031-16270-1
eBook Packages: Computer ScienceComputer Science (R0)