@inproceedings{huang-etal-2023-xiaomi,
title = "The Xiaomi {AI} Lab{'}s Speech Translation Systems for {IWSLT} 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task",
author = "Huang, Wuwei and
Liu, Mengge and
Li, Xiang and
Tian, Yanzhi and
Yang, Fengyu and
Zhang, Wen and
Luan, Jian and
Wang, Bin and
Guo, Yuhang and
Su, Jinsong",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.39",
doi = "10.18653/v1/2023.iwslt-1.39",
pages = "411--419",
abstract = "This system description paper introduces the systems submitted by Xiaomi AI Lab to the three tracks of the IWSLT 2023 Evaluation Campaign, namely the offline speech translation (Offline-ST) track, the offline speech-to-speech translation (Offline-S2ST) track, and the simultaneous speech translation (Simul-ST) track. All our submissions for these three tracks only involve the English-Chinese language direction. Our English-Chinese speech translation systems are constructed using large-scale pre-trained models as the foundation. Specifically, we fine-tune these models{'} corresponding components for various downstream speech translation tasks. Moreover, we implement several popular techniques, such as data filtering, data augmentation, speech segmentation, and model ensemble, to improve the system{'}s overall performance. Extensive experiments show that our systems achieve a significant improvement over the strong baseline systems in terms of the automatic evaluation metric.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2023-xiaomi">
<titleInfo>
<title>The Xiaomi AI Lab’s Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wuwei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengge</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanzhi</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengyu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Luan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinsong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</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">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This system description paper introduces the systems submitted by Xiaomi AI Lab to the three tracks of the IWSLT 2023 Evaluation Campaign, namely the offline speech translation (Offline-ST) track, the offline speech-to-speech translation (Offline-S2ST) track, and the simultaneous speech translation (Simul-ST) track. All our submissions for these three tracks only involve the English-Chinese language direction. Our English-Chinese speech translation systems are constructed using large-scale pre-trained models as the foundation. Specifically, we fine-tune these models’ corresponding components for various downstream speech translation tasks. Moreover, we implement several popular techniques, such as data filtering, data augmentation, speech segmentation, and model ensemble, to improve the system’s overall performance. Extensive experiments show that our systems achieve a significant improvement over the strong baseline systems in terms of the automatic evaluation metric.</abstract>
<identifier type="citekey">huang-etal-2023-xiaomi</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.39</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.39</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>411</start>
<end>419</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Xiaomi AI Lab’s Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task
%A Huang, Wuwei
%A Liu, Mengge
%A Li, Xiang
%A Tian, Yanzhi
%A Yang, Fengyu
%A Zhang, Wen
%A Luan, Jian
%A Wang, Bin
%A Guo, Yuhang
%A Su, Jinsong
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F huang-etal-2023-xiaomi
%X This system description paper introduces the systems submitted by Xiaomi AI Lab to the three tracks of the IWSLT 2023 Evaluation Campaign, namely the offline speech translation (Offline-ST) track, the offline speech-to-speech translation (Offline-S2ST) track, and the simultaneous speech translation (Simul-ST) track. All our submissions for these three tracks only involve the English-Chinese language direction. Our English-Chinese speech translation systems are constructed using large-scale pre-trained models as the foundation. Specifically, we fine-tune these models’ corresponding components for various downstream speech translation tasks. Moreover, we implement several popular techniques, such as data filtering, data augmentation, speech segmentation, and model ensemble, to improve the system’s overall performance. Extensive experiments show that our systems achieve a significant improvement over the strong baseline systems in terms of the automatic evaluation metric.
%R 10.18653/v1/2023.iwslt-1.39
%U https://aclanthology.org/2023.iwslt-1.39
%U https://doi.org/10.18653/v1/2023.iwslt-1.39
%P 411-419
Markdown (Informal)
[The Xiaomi AI Lab’s Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task](https://aclanthology.org/2023.iwslt-1.39) (Huang et al., IWSLT 2023)
ACL
- Wuwei Huang, Mengge Liu, Xiang Li, Yanzhi Tian, Fengyu Yang, Wen Zhang, Jian Luan, Bin Wang, Yuhang Guo, and Jinsong Su. 2023. The Xiaomi AI Lab’s Speech Translation Systems for IWSLT 2023 Offline Task, Simultaneous Task and Speech-to-Speech Task. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 411–419, Toronto, Canada (in-person and online). Association for Computational Linguistics.