@inproceedings{zhang-etal-2024-nyas,
title = "The {NYA}{'}s Offline Speech Translation System for {IWSLT} 2024",
author = "Zhang, Yingxin and
Ma, Guodong and
Du, Binbin",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwslt-1.6",
pages = "39--45",
abstract = "This paper reports the NYA{'}s submissions to IWSLT 2024 Offline Speech Translation (ST) task on the sub-tasks including English to Chinese, Japanese, and German. In detail, we participate in the unconstrained training track using the cascaded ST structure. For the automatic speech recognition (ASR) model, we use the Whisper large-v3 model. For the neural machine translation (NMT) model, the wider and deeper Transformer is adapted as the backbone model. Furthermore, we use data augmentation technologies to augment training data and data filtering strategies to improve the quality of training data. In addition, we explore many MT technologies such as Back Translation, Forward Translation, R-Drop, and Domain Adaptation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-nyas">
<titleInfo>
<title>The NYA’s Offline Speech Translation System for IWSLT 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingxin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binbin</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</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">Bangkok, Thailand (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports the NYA’s submissions to IWSLT 2024 Offline Speech Translation (ST) task on the sub-tasks including English to Chinese, Japanese, and German. In detail, we participate in the unconstrained training track using the cascaded ST structure. For the automatic speech recognition (ASR) model, we use the Whisper large-v3 model. For the neural machine translation (NMT) model, the wider and deeper Transformer is adapted as the backbone model. Furthermore, we use data augmentation technologies to augment training data and data filtering strategies to improve the quality of training data. In addition, we explore many MT technologies such as Back Translation, Forward Translation, R-Drop, and Domain Adaptation.</abstract>
<identifier type="citekey">zhang-etal-2024-nyas</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.6</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>39</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The NYA’s Offline Speech Translation System for IWSLT 2024
%A Zhang, Yingxin
%A Ma, Guodong
%A Du, Binbin
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F zhang-etal-2024-nyas
%X This paper reports the NYA’s submissions to IWSLT 2024 Offline Speech Translation (ST) task on the sub-tasks including English to Chinese, Japanese, and German. In detail, we participate in the unconstrained training track using the cascaded ST structure. For the automatic speech recognition (ASR) model, we use the Whisper large-v3 model. For the neural machine translation (NMT) model, the wider and deeper Transformer is adapted as the backbone model. Furthermore, we use data augmentation technologies to augment training data and data filtering strategies to improve the quality of training data. In addition, we explore many MT technologies such as Back Translation, Forward Translation, R-Drop, and Domain Adaptation.
%U https://aclanthology.org/2024.iwslt-1.6
%P 39-45
Markdown (Informal)
[The NYA’s Offline Speech Translation System for IWSLT 2024](https://aclanthology.org/2024.iwslt-1.6) (Zhang et al., IWSLT 2024)
ACL
- Yingxin Zhang, Guodong Ma, and Binbin Du. 2024. The NYA’s Offline Speech Translation System for IWSLT 2024. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 39–45, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.