@inproceedings{guo-etal-2022-hw,
title = "The {HW}-{TSC}{'}s Speech to Speech Translation System for {IWSLT} 2022 Evaluation",
author = "Guo, Jiaxin and
Li, Yinglu and
Wang, Minghan and
Qiao, Xiaosong and
Wang, Yuxia and
Shang, Hengchao and
Su, Chang and
Chen, Yimeng and
Zhang, Min and
Tao, Shimin and
Yang, Hao and
Qin, Ying",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Costa-juss{\`a}, Marta",
booktitle = "Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)",
month = may,
year = "2022",
address = "Dublin, Ireland (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.iwslt-1.26",
doi = "10.18653/v1/2022.iwslt-1.26",
pages = "293--297",
abstract = "The paper presents the HW-TSC{'}s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022. We design a cascade system consisted of an ASR model, machine translation model and TTS model to convert the speech from one language into another language(en-de). For the ASR part, we find that better performance can be obtained by ensembling multiple heterogeneous ASR models and performing reranking on beam candidates. And we find that the combination of context-aware reranking strategy and MT model fine-tuned on the in-domain dataset is helpful to improve the performance. Because it can mitigate the problem that the inconsistency in transcripts caused by the lack of context. Finally, we use VITS model provided officially to reproduce audio files from the translation hypothesis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2022-hw">
<titleInfo>
<title>The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation</title>
</titleInfo>
<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">Yinglu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaosong</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</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">Chang</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimin</namePart>
<namePart type="family">Tao</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">Ying</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)</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">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022. We design a cascade system consisted of an ASR model, machine translation model and TTS model to convert the speech from one language into another language(en-de). For the ASR part, we find that better performance can be obtained by ensembling multiple heterogeneous ASR models and performing reranking on beam candidates. And we find that the combination of context-aware reranking strategy and MT model fine-tuned on the in-domain dataset is helpful to improve the performance. Because it can mitigate the problem that the inconsistency in transcripts caused by the lack of context. Finally, we use VITS model provided officially to reproduce audio files from the translation hypothesis.</abstract>
<identifier type="citekey">guo-etal-2022-hw</identifier>
<identifier type="doi">10.18653/v1/2022.iwslt-1.26</identifier>
<location>
<url>https://aclanthology.org/2022.iwslt-1.26</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>293</start>
<end>297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
%A Guo, Jiaxin
%A Li, Yinglu
%A Wang, Minghan
%A Qiao, Xiaosong
%A Wang, Yuxia
%A Shang, Hengchao
%A Su, Chang
%A Chen, Yimeng
%A Zhang, Min
%A Tao, Shimin
%A Yang, Hao
%A Qin, Ying
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Costa-jussà, Marta
%S Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland (in-person and online)
%F guo-etal-2022-hw
%X The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022. We design a cascade system consisted of an ASR model, machine translation model and TTS model to convert the speech from one language into another language(en-de). For the ASR part, we find that better performance can be obtained by ensembling multiple heterogeneous ASR models and performing reranking on beam candidates. And we find that the combination of context-aware reranking strategy and MT model fine-tuned on the in-domain dataset is helpful to improve the performance. Because it can mitigate the problem that the inconsistency in transcripts caused by the lack of context. Finally, we use VITS model provided officially to reproduce audio files from the translation hypothesis.
%R 10.18653/v1/2022.iwslt-1.26
%U https://aclanthology.org/2022.iwslt-1.26
%U https://doi.org/10.18653/v1/2022.iwslt-1.26
%P 293-297
Markdown (Informal)
[The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation](https://aclanthology.org/2022.iwslt-1.26) (Guo et al., IWSLT 2022)
ACL
- Jiaxin Guo, Yinglu Li, Minghan Wang, Xiaosong Qiao, Yuxia Wang, Hengchao Shang, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, and Ying Qin. 2022. The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 293–297, Dublin, Ireland (in-person and online). Association for Computational Linguistics.