Publication detail

Jointly Trained Transformers Models for Spoken Language Translation

VYDANA, H. KARAFIÁT, M. ŽMOLÍKOVÁ, K. BURGET, L. ČERNOCKÝ, J.

Original Title

Jointly Trained Transformers Models for Spoken Language Translation

Type

conference paper

Language

English

Original Abstract

End-to-End and cascade (ASR-MT) spoken language translation (SLT) systems are reaching comparable performances, however, a large degradation is observed when translating the ASR hypothesis in comparison to using oracle input text. In this work, degradation in performance is reduced by creating an End-to-End differentiable pipeline between the ASR and MT systems. In this work, we train SLT systems with ASR objective as an auxiliary loss and both the networks are connected through the neural hidden representations. This training has an End-to-End differentiable path with respect to the final objective function and utilizes the ASR objective for better optimization. This architecture has improved the BLEU score from 41.21 to 44.69. Ensembling the proposed architecture with independently trained ASR and MT systems further improved the BLEU score from 44.69 to 46.9. All the experiments are reported on English-Portuguese speech translation task using the How2 corpus. The final BLEU score is on-par with the best speech translation system on How2 dataset without using any additional training data and language model and using fewer parameters.

Keywords

Spoken Language Translation, Transformers, Joint training, How2 dataset, Auxiliary loss, ASR objective, Coupled decoding, End-to-End differentiable pipeline.

Authors

VYDANA, H.; KARAFIÁT, M.; ŽMOLÍKOVÁ, K.; BURGET, L.; ČERNOCKÝ, J.

Released

6. 6. 2021

Publisher

IEEE Signal Processing Society

Location

Toronto, Ontario

ISBN

978-1-7281-7605-5

Book

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Pages from

7513

Pages to

7517

Pages count

5

URL

BibTex

@inproceedings{BUT175791,
  author="Hari Krishna {Vydana} and Martin {Karafiát} and Kateřina {Žmolíková} and Lukáš {Burget} and Jan {Černocký}",
  title="Jointly Trained Transformers Models for Spoken Language Translation",
  booktitle="ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
  year="2021",
  pages="7513--7517",
  publisher="IEEE Signal Processing Society",
  address="Toronto, Ontario",
  doi="10.1109/ICASSP39728.2021.9414159",
  isbn="978-1-7281-7605-5",
  url="https://www.fit.vut.cz/research/publication/12522/"
}