@inproceedings{wang-etal-2022-hw-tscs,
title = "The {HW}-{TSC}{'}s Simultaneous Speech Translation System for {IWSLT} 2022 Evaluation",
author = "Wang, Minghan and
Guo, Jiaxin and
Li, Yinglu and
Qiao, Xiaosong and
Wang, Yuxia and
Li, Zongyao 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-1.21",
doi = "10.18653/v1/2022.iwslt-1.21",
pages = "247--254",
abstract = "This paper presents our work in the participation of IWSLT 2022 simultaneous speech translation evaluation. For the track of text-to-text (T2T), we participate in three language pairs and build wait-k based simultaneous MT (SimulMT) model for the task. The model was pretrained on WMT21 news corpora, and was further improved with in-domain fine-tuning and self-training. For the speech-to-text (S2T) track, we designed both cascade and end-to-end form in three language pairs. The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track. The end-to-end system is a simultaneous speech translation (SimulST) model based on wait-k strategy, which is directly trained on a synthetic corpus produced by translating all texts of ASR corpora into specific target language with an offline MT model. It also contains a heuristic sentence breaking strategy, preventing it from finishing the translation before the the end of the speech. We evaluate our systems on the MUST-C tst-COMMON dataset and show that the end-to-end system is competitive to the cascade one. Meanwhile, we also demonstrate that the SimulMT model can be efficiently optimized by these approaches, resulting in the improvements of 1-2 BLEU points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-hw-tscs">
<titleInfo>
<title>The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation</title>
</titleInfo>
<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">Yinglu</namePart>
<namePart type="family">Li</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">Zongyao</namePart>
<namePart type="family">Li</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 presents our work in the participation of IWSLT 2022 simultaneous speech translation evaluation. For the track of text-to-text (T2T), we participate in three language pairs and build wait-k based simultaneous MT (SimulMT) model for the task. The model was pretrained on WMT21 news corpora, and was further improved with in-domain fine-tuning and self-training. For the speech-to-text (S2T) track, we designed both cascade and end-to-end form in three language pairs. The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track. The end-to-end system is a simultaneous speech translation (SimulST) model based on wait-k strategy, which is directly trained on a synthetic corpus produced by translating all texts of ASR corpora into specific target language with an offline MT model. It also contains a heuristic sentence breaking strategy, preventing it from finishing the translation before the the end of the speech. We evaluate our systems on the MUST-C tst-COMMON dataset and show that the end-to-end system is competitive to the cascade one. Meanwhile, we also demonstrate that the SimulMT model can be efficiently optimized by these approaches, resulting in the improvements of 1-2 BLEU points.</abstract>
<identifier type="citekey">wang-etal-2022-hw-tscs</identifier>
<identifier type="doi">10.18653/v1/2022.iwslt-1.21</identifier>
<location>
<url>https://aclanthology.org/2022.iwslt-1.21</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>247</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation
%A Wang, Minghan
%A Guo, Jiaxin
%A Li, Yinglu
%A Qiao, Xiaosong
%A Wang, Yuxia
%A Li, Zongyao
%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-tscs
%X This paper presents our work in the participation of IWSLT 2022 simultaneous speech translation evaluation. For the track of text-to-text (T2T), we participate in three language pairs and build wait-k based simultaneous MT (SimulMT) model for the task. The model was pretrained on WMT21 news corpora, and was further improved with in-domain fine-tuning and self-training. For the speech-to-text (S2T) track, we designed both cascade and end-to-end form in three language pairs. The cascade system is composed of a chunking-based streaming ASR model and the SimulMT model used in the T2T track. The end-to-end system is a simultaneous speech translation (SimulST) model based on wait-k strategy, which is directly trained on a synthetic corpus produced by translating all texts of ASR corpora into specific target language with an offline MT model. It also contains a heuristic sentence breaking strategy, preventing it from finishing the translation before the the end of the speech. We evaluate our systems on the MUST-C tst-COMMON dataset and show that the end-to-end system is competitive to the cascade one. Meanwhile, we also demonstrate that the SimulMT model can be efficiently optimized by these approaches, resulting in the improvements of 1-2 BLEU points.
%R 10.18653/v1/2022.iwslt-1.21
%U https://aclanthology.org/2022.iwslt-1.21
%U https://doi.org/10.18653/v1/2022.iwslt-1.21
%P 247-254
Markdown (Informal)
[The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation](https://aclanthology.org/2022.iwslt-1.21) (Wang et al., IWSLT 2022)
ACL
- Minghan Wang, Jiaxin Guo, Yinglu Li, Xiaosong Qiao, Yuxia Wang, Zongyao Li, Chang Su, Yimeng Chen, Min Zhang, Shimin Tao, Hao Yang, and Ying Qin. 2022. The HW-TSC’s Simultaneous Speech Translation System for IWSLT 2022 Evaluation. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 247–254, Dublin, Ireland (in-person and online). Association for Computational Linguistics.