@inproceedings{wang-etal-2023-bits,
title = "{BIT}{'}s System for Multilingual Track",
author = "Wang, Zhipeng and
Guo, Yuhang and
Chen, Shuoying",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.44",
doi = "10.18653/v1/2023.iwslt-1.44",
pages = "455--460",
abstract = "This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with input being English speech and output being text in 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-bits">
<titleInfo>
<title>BIT’s System for Multilingual Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuoying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with input being English speech and output being text in 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.</abstract>
<identifier type="citekey">wang-etal-2023-bits</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.44</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.44</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>455</start>
<end>460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BIT’s System for Multilingual Track
%A Wang, Zhipeng
%A Guo, Yuhang
%A Chen, Shuoying
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F wang-etal-2023-bits
%X This paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with input being English speech and output being text in 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.
%R 10.18653/v1/2023.iwslt-1.44
%U https://aclanthology.org/2023.iwslt-1.44
%U https://doi.org/10.18653/v1/2023.iwslt-1.44
%P 455-460
Markdown (Informal)
[BIT’s System for Multilingual Track](https://aclanthology.org/2023.iwslt-1.44) (Wang et al., IWSLT 2023)
ACL
- Zhipeng Wang, Yuhang Guo, and Shuoying Chen. 2023. BIT’s System for Multilingual Track. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 455–460, Toronto, Canada (in-person and online). Association for Computational Linguistics.