@inproceedings{zhang-etal-2022-niutranss,
title = "The {N}iu{T}rans{'}s Submission to the {IWSLT}22 {E}nglish-to-{C}hinese Offline Speech Translation Task",
author = "Zhang, Yuhao and
Huang, Canan and
Xu, Chen and
Liu, Xiaoqian and
Li, Bei and
Ma, Anxiang and
Xiao, Tong and
Zhu, Jingbo",
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-1.19",
doi = "10.18653/v1/2022.iwslt-1.19",
pages = "232--238",
abstract = "This paper describes NiuTrans{'}s submission to the IWSLT22 English-to-Chinese (En-Zh) offline speech translation task. The end-to-end and bilingual system is built by constrained English and Chinese data and translates the English speech to Chinese text without intermediate transcription. Our speech translation models are composed of different pre-trained acoustic models and machine translation models by two kinds of adapters. We compared the effect of the standard speech feature (e.g. log Mel-filterbank) and the pre-training speech feature and try to make them interact. The final submission is an ensemble of three potential speech translation models. Our single best and ensemble model achieves 18.66 BLEU and 19.35 BLEU separately on MuST-C En-Zh tst-COMMON set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-niutranss">
<titleInfo>
<title>The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Canan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anxiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Zhu</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 NiuTrans’s submission to the IWSLT22 English-to-Chinese (En-Zh) offline speech translation task. The end-to-end and bilingual system is built by constrained English and Chinese data and translates the English speech to Chinese text without intermediate transcription. Our speech translation models are composed of different pre-trained acoustic models and machine translation models by two kinds of adapters. We compared the effect of the standard speech feature (e.g. log Mel-filterbank) and the pre-training speech feature and try to make them interact. The final submission is an ensemble of three potential speech translation models. Our single best and ensemble model achieves 18.66 BLEU and 19.35 BLEU separately on MuST-C En-Zh tst-COMMON set.</abstract>
<identifier type="citekey">zhang-etal-2022-niutranss</identifier>
<identifier type="doi">10.18653/v1/2022.iwslt-1.19</identifier>
<location>
<url>https://aclanthology.org/2022.iwslt-1.19</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>232</start>
<end>238</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task
%A Zhang, Yuhao
%A Huang, Canan
%A Xu, Chen
%A Liu, Xiaoqian
%A Li, Bei
%A Ma, Anxiang
%A Xiao, Tong
%A Zhu, Jingbo
%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 zhang-etal-2022-niutranss
%X This paper describes NiuTrans’s submission to the IWSLT22 English-to-Chinese (En-Zh) offline speech translation task. The end-to-end and bilingual system is built by constrained English and Chinese data and translates the English speech to Chinese text without intermediate transcription. Our speech translation models are composed of different pre-trained acoustic models and machine translation models by two kinds of adapters. We compared the effect of the standard speech feature (e.g. log Mel-filterbank) and the pre-training speech feature and try to make them interact. The final submission is an ensemble of three potential speech translation models. Our single best and ensemble model achieves 18.66 BLEU and 19.35 BLEU separately on MuST-C En-Zh tst-COMMON set.
%R 10.18653/v1/2022.iwslt-1.19
%U https://aclanthology.org/2022.iwslt-1.19
%U https://doi.org/10.18653/v1/2022.iwslt-1.19
%P 232-238
Markdown (Informal)
[The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task](https://aclanthology.org/2022.iwslt-1.19) (Zhang et al., IWSLT 2022)
ACL
- Yuhao Zhang, Canan Huang, Chen Xu, Xiaoqian Liu, Bei Li, Anxiang Ma, Tong Xiao, and Jingbo Zhu. 2022. The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 232–238, Dublin, Ireland (in-person and online). Association for Computational Linguistics.