BIT’s System for Multilingual Track

Zhipeng Wang; Yuhang Guo; Shuoying Chen

BIT’s System for Multilingual Track

Zhipeng Wang, Yuhang Guo^*, Shuoying Chen

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with the input is speech from one language, and the output is text from 10 target languages. Our system consists of CNN and Transformer, convolutional neural networks downsample speech features and extract local information, while transformer extract global features and output the final results. In our system, we use speech recognition tasks to pre-train encoder parameters, and then use speech translation corpus to train the multilingual speech translation model. We have also adopted other methods to optimize the model, such as data augmentation, model ensemble, etc. Our system can obtain satisfactory results on test sets of 10 languages in the MUST-C corpus.

Original language	English
Title of host publication	20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference
Editors	Elizabeth Salesky, Marcello Federico, Marine Carpuat
Publisher	Association for Computational Linguistics
Pages	455-460
Number of pages	6
ISBN (Electronic)	9781959429845
Publication status	Published - 2023
Event	20th International Conference on Spoken Language Translation, IWSLT 2023 - Hybrid, Toronto, Canada Duration: 13 Jul 2023 → 14 Jul 2023

Publication series

Name	20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

Conference

Conference	20th International Conference on Spoken Language Translation, IWSLT 2023
Country/Territory	Canada
City	Hybrid, Toronto
Period	13/07/23 → 14/07/23

Cite this

Wang, Z., Guo, Y., & Chen, S. (2023). BIT’s System for Multilingual Track. In E. Salesky, M. Federico, & M. Carpuat (Eds.), 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference (pp. 455-460). (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference). Association for Computational Linguistics.

Wang, Zhipeng ; Guo, Yuhang ; Chen, Shuoying. / BIT’s System for Multilingual Track. 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. editor / Elizabeth Salesky ; Marcello Federico ; Marine Carpuat. Association for Computational Linguistics, 2023. pp. 455-460 (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference).

@inproceedings{b38278066eff47e8bf72423e3a0b1979,

title = "BIT{\textquoteright}s System for Multilingual Track",

abstract = "This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with the input is speech from one language, and the output is text from 10 target languages. Our system consists of CNN and Transformer, convolutional neural networks downsample speech features and extract local information, while transformer extract global features and output the final results. In our system, we use speech recognition tasks to pre-train encoder parameters, and then use speech translation corpus to train the multilingual speech translation model. We have also adopted other methods to optimize the model, such as data augmentation, model ensemble, etc. Our system can obtain satisfactory results on test sets of 10 languages in the MUST-C corpus.",

author = "Zhipeng Wang and Yuhang Guo and Shuoying Chen",

note = "Publisher Copyright: {\textcopyright} IWSLT 2023.All rights reserved.; 20th International Conference on Spoken Language Translation, IWSLT 2023 ; Conference date: 13-07-2023 Through 14-07-2023",

year = "2023",

language = "English",

series = "20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference",

publisher = "Association for Computational Linguistics",

pages = "455--460",

editor = "Elizabeth Salesky and Marcello Federico and Marine Carpuat",

booktitle = "20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference",

}

Wang, Z, Guo, Y & Chen, S 2023, BIT’s System for Multilingual Track. in E Salesky, M Federico & M Carpuat (eds), 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference, Association for Computational Linguistics, pp. 455-460, 20th International Conference on Spoken Language Translation, IWSLT 2023, Hybrid, Toronto, Canada, 13/07/23.

BIT’s System for Multilingual Track. / Wang, Zhipeng; Guo, Yuhang; Chen, Shuoying.
20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. ed. / Elizabeth Salesky; Marcello Federico; Marine Carpuat. Association for Computational Linguistics, 2023. p. 455-460 (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - BIT’s System for Multilingual Track

AU - Wang, Zhipeng

AU - Guo, Yuhang

AU - Chen, Shuoying

PY - 2023

Y1 - 2023

N2 - This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with the input is speech from one language, and the output is text from 10 target languages. Our system consists of CNN and Transformer, convolutional neural networks downsample speech features and extract local information, while transformer extract global features and output the final results. In our system, we use speech recognition tasks to pre-train encoder parameters, and then use speech translation corpus to train the multilingual speech translation model. We have also adopted other methods to optimize the model, such as data augmentation, model ensemble, etc. Our system can obtain satisfactory results on test sets of 10 languages in the MUST-C corpus.

AB - This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with the input is speech from one language, and the output is text from 10 target languages. Our system consists of CNN and Transformer, convolutional neural networks downsample speech features and extract local information, while transformer extract global features and output the final results. In our system, we use speech recognition tasks to pre-train encoder parameters, and then use speech translation corpus to train the multilingual speech translation model. We have also adopted other methods to optimize the model, such as data augmentation, model ensemble, etc. Our system can obtain satisfactory results on test sets of 10 languages in the MUST-C corpus.

UR - http://www.scopus.com/inward/record.url?scp=85174974748&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85174974748

T3 - 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

SP - 455

EP - 460

BT - 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

A2 - Salesky, Elizabeth

A2 - Federico, Marcello

A2 - Carpuat, Marine

PB - Association for Computational Linguistics

T2 - 20th International Conference on Spoken Language Translation, IWSLT 2023

Y2 - 13 July 2023 through 14 July 2023

ER -

Wang Z, Guo Y, Chen S. BIT’s System for Multilingual Track. In Salesky E, Federico M, Carpuat M, editors, 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. Association for Computational Linguistics. 2023. p. 455-460. (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference).

BIT’s System for Multilingual Track

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this