@inproceedings{wang-etal-2022-hw,
title = "The {HW}-{TSC}{'}s Offline Speech Translation System for {IWSLT} 2022 Evaluation",
author = "Li, Yinglu and
Wang, Minghan and
Guo, Jiaxin and
Qiao, Xiaosong and
Wang, Yuxia and
Wei, Daimeng 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-1.20",
doi = "10.18653/v1/2022.iwslt-1.20",
pages = "239--246",
abstract = "This paper describes the HW-TSC{'}s designation of the Offline Speech Translation System submitted for IWSLT 2022 Evaluation. We explored both cascade and end-to-end system on three language tracks (en-de, en-zh and en-ja), and we chose the cascade one as our primary submission. For the automatic speech recognition (ASR) model of cascade system, there are three ASR models including Conformer, S2T-Transformer and U2 trained on the mixture of five datasets. During inference, transcripts are generated with the help of domain controlled generation strategy. Context-aware reranking and ensemble based anti-interference strategy are proposed to produce better ASR outputs. For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora. Our cascade system shows competitive performance than the known offline systems in the industry and academia.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-hw">
<titleInfo>
<title>The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation</title>
</titleInfo>
<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">Jiaxin</namePart>
<namePart type="family">Guo</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">Daimeng</namePart>
<namePart type="family">Wei</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>This paper describes the HW-TSC’s designation of the Offline Speech Translation System submitted for IWSLT 2022 Evaluation. We explored both cascade and end-to-end system on three language tracks (en-de, en-zh and en-ja), and we chose the cascade one as our primary submission. For the automatic speech recognition (ASR) model of cascade system, there are three ASR models including Conformer, S2T-Transformer and U2 trained on the mixture of five datasets. During inference, transcripts are generated with the help of domain controlled generation strategy. Context-aware reranking and ensemble based anti-interference strategy are proposed to produce better ASR outputs. For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora. Our cascade system shows competitive performance than the known offline systems in the industry and academia.</abstract>
<identifier type="citekey">wang-etal-2022-hw</identifier>
<identifier type="doi">10.18653/v1/2022.iwslt-1.20</identifier>
<location>
<url>https://aclanthology.org/2022.iwslt-1.20</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>239</start>
<end>246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
%A Li, Yinglu
%A Wang, Minghan
%A Guo, Jiaxin
%A Qiao, Xiaosong
%A Wang, Yuxia
%A Wei, Daimeng
%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 wang-etal-2022-hw
%X This paper describes the HW-TSC’s designation of the Offline Speech Translation System submitted for IWSLT 2022 Evaluation. We explored both cascade and end-to-end system on three language tracks (en-de, en-zh and en-ja), and we chose the cascade one as our primary submission. For the automatic speech recognition (ASR) model of cascade system, there are three ASR models including Conformer, S2T-Transformer and U2 trained on the mixture of five datasets. During inference, transcripts are generated with the help of domain controlled generation strategy. Context-aware reranking and ensemble based anti-interference strategy are proposed to produce better ASR outputs. For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora. Our cascade system shows competitive performance than the known offline systems in the industry and academia.
%R 10.18653/v1/2022.iwslt-1.20
%U https://aclanthology.org/2022.iwslt-1.20
%U https://doi.org/10.18653/v1/2022.iwslt-1.20
%P 239-246
Markdown (Informal)
[The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation](https://aclanthology.org/2022.iwslt-1.20) (Li et al., IWSLT 2022)
ACL
- Yinglu Li, Minghan Wang, Jiaxin Guo, Xiaosong Qiao, Yuxia Wang, Daimeng Wei, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, and Ying Qin. 2022. The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 239–246, Dublin, Ireland (in-person and online). Association for Computational Linguistics.