@inproceedings{wei-etal-2024-hw,
title = "{HW}-{TSC}{'}s Speech to Text Translation System for {IWSLT} 2024 in {I}ndic track",
author = "Wei, Bin and
Li, Zongyao and
Guo, Jiaxin and
Wei, Daimeng and
Wu, Zhanglin and
Chen, Xiaoyu and
Rao, Zhiqiang and
Li, Shaojun and
Luo, Yuanchang and
Shang, Hengchao and
Yang, Hao and
Jiang, Yanfei",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwslt-1.8",
pages = "53--56",
abstract = "This article introduces the process of HW-TSC and the results of IWSLT 2024 Indic Track Speech to Text Translation. We designed a cascade system consisting of an ASR model and a machine translation model to translate speech from one language to another. For the ASR part, we directly use whisper large v3 as our ASR model. Our main task is to optimize the machine translation model (en2ta, en2hi, en2bn). In the process of optimizing the translation model, we first use bilingual corpus to train the baseline model. Then we use monolingual data to construct pseudo-corpus data to further enhance the baseline model. Finally, we filter the parallel corpus data through the labse filtering method and finetune the model again, which can further improve the bleu value. We also selected domain data from bilingual corpus to finetune previous model to achieve the best results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2024-hw">
<titleInfo>
<title>HW-TSC’s Speech to Text Translation System for IWSLT 2024 in Indic track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaojun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanchang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanfei</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</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">Bangkok, Thailand (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article introduces the process of HW-TSC and the results of IWSLT 2024 Indic Track Speech to Text Translation. We designed a cascade system consisting of an ASR model and a machine translation model to translate speech from one language to another. For the ASR part, we directly use whisper large v3 as our ASR model. Our main task is to optimize the machine translation model (en2ta, en2hi, en2bn). In the process of optimizing the translation model, we first use bilingual corpus to train the baseline model. Then we use monolingual data to construct pseudo-corpus data to further enhance the baseline model. Finally, we filter the parallel corpus data through the labse filtering method and finetune the model again, which can further improve the bleu value. We also selected domain data from bilingual corpus to finetune previous model to achieve the best results.</abstract>
<identifier type="citekey">wei-etal-2024-hw</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.8</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>53</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Speech to Text Translation System for IWSLT 2024 in Indic track
%A Wei, Bin
%A Li, Zongyao
%A Guo, Jiaxin
%A Wei, Daimeng
%A Wu, Zhanglin
%A Chen, Xiaoyu
%A Rao, Zhiqiang
%A Li, Shaojun
%A Luo, Yuanchang
%A Shang, Hengchao
%A Yang, Hao
%A Jiang, Yanfei
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F wei-etal-2024-hw
%X This article introduces the process of HW-TSC and the results of IWSLT 2024 Indic Track Speech to Text Translation. We designed a cascade system consisting of an ASR model and a machine translation model to translate speech from one language to another. For the ASR part, we directly use whisper large v3 as our ASR model. Our main task is to optimize the machine translation model (en2ta, en2hi, en2bn). In the process of optimizing the translation model, we first use bilingual corpus to train the baseline model. Then we use monolingual data to construct pseudo-corpus data to further enhance the baseline model. Finally, we filter the parallel corpus data through the labse filtering method and finetune the model again, which can further improve the bleu value. We also selected domain data from bilingual corpus to finetune previous model to achieve the best results.
%U https://aclanthology.org/2024.iwslt-1.8
%P 53-56
Markdown (Informal)
[HW-TSC’s Speech to Text Translation System for IWSLT 2024 in Indic track](https://aclanthology.org/2024.iwslt-1.8) (Wei et al., IWSLT 2024)
ACL
- Bin Wei, Zongyao Li, Jiaxin Guo, Daimeng Wei, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Shaojun Li, Yuanchang Luo, Hengchao Shang, Hao Yang, and Yanfei Jiang. 2024. HW-TSC’s Speech to Text Translation System for IWSLT 2024 in Indic track. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 53–56, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.