@inproceedings{ko-etal-2024-naist,
title = "{NAIST} Simultaneous Speech Translation System for {IWSLT} 2024",
author = "Ko, Yuka and
Fukuda, Ryo and
Nishikawa, Yuta and
Kano, Yasumasa and
Yanagita, Tomoya and
Doi, Kosuke and
Makinae, Mana and
Tan, Haotian and
Sakai, Makoto and
Sakti, Sakriani and
Sudoh, Katsuhito and
Nakamura, Satoshi",
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-1.23",
doi = "10.18653/v1/2024.iwslt-1.23",
pages = "170--182",
abstract = "This paper describes NAIST{'}s submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-German, Japanese, Chinese speech-to-text translation and English-to-Japanese speech-to-speech translation. We develop a multilingual end-to-end speech-to-text translation model combining two pre-trained language models, HuBERT and mBART. We trained this model with two decoding policies, Local Agreement (LA) and AlignAtt. The submitted models employ the LA policy because it outperformed the AlignAtt policy in previous models. Our speech-to-speech translation method is a cascade of the above speech-to-text model and an incremental text-to-speech (TTS) module that incorporates a phoneme estimation model, a parallel acoustic model, and a parallel WaveGAN vocoder. We improved our incremental TTS by applying the Transformer architecture with the AlignAtt policy for the estimation model. The results show that our upgraded TTS module contributed to improving the system performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ko-etal-2024-naist">
<titleInfo>
<title>NAIST Simultaneous Speech Translation System for IWSLT 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuka</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Fukuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Nishikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasumasa</namePart>
<namePart type="family">Kano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoya</namePart>
<namePart type="family">Yanagita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Doi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mana</namePart>
<namePart type="family">Makinae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haotian</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</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 describes NAIST’s submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-German, Japanese, Chinese speech-to-text translation and English-to-Japanese speech-to-speech translation. We develop a multilingual end-to-end speech-to-text translation model combining two pre-trained language models, HuBERT and mBART. We trained this model with two decoding policies, Local Agreement (LA) and AlignAtt. The submitted models employ the LA policy because it outperformed the AlignAtt policy in previous models. Our speech-to-speech translation method is a cascade of the above speech-to-text model and an incremental text-to-speech (TTS) module that incorporates a phoneme estimation model, a parallel acoustic model, and a parallel WaveGAN vocoder. We improved our incremental TTS by applying the Transformer architecture with the AlignAtt policy for the estimation model. The results show that our upgraded TTS module contributed to improving the system performance.</abstract>
<identifier type="citekey">ko-etal-2024-naist</identifier>
<identifier type="doi">10.18653/v1/2024.iwslt-1.23</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.23</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>170</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NAIST Simultaneous Speech Translation System for IWSLT 2024
%A Ko, Yuka
%A Fukuda, Ryo
%A Nishikawa, Yuta
%A Kano, Yasumasa
%A Yanagita, Tomoya
%A Doi, Kosuke
%A Makinae, Mana
%A Tan, Haotian
%A Sakai, Makoto
%A Sakti, Sakriani
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%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 ko-etal-2024-naist
%X This paper describes NAIST’s submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-German, Japanese, Chinese speech-to-text translation and English-to-Japanese speech-to-speech translation. We develop a multilingual end-to-end speech-to-text translation model combining two pre-trained language models, HuBERT and mBART. We trained this model with two decoding policies, Local Agreement (LA) and AlignAtt. The submitted models employ the LA policy because it outperformed the AlignAtt policy in previous models. Our speech-to-speech translation method is a cascade of the above speech-to-text model and an incremental text-to-speech (TTS) module that incorporates a phoneme estimation model, a parallel acoustic model, and a parallel WaveGAN vocoder. We improved our incremental TTS by applying the Transformer architecture with the AlignAtt policy for the estimation model. The results show that our upgraded TTS module contributed to improving the system performance.
%R 10.18653/v1/2024.iwslt-1.23
%U https://aclanthology.org/2024.iwslt-1.23
%U https://doi.org/10.18653/v1/2024.iwslt-1.23
%P 170-182
Markdown (Informal)
[NAIST Simultaneous Speech Translation System for IWSLT 2024](https://aclanthology.org/2024.iwslt-1.23) (Ko et al., IWSLT 2024)
ACL
- Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Tomoya Yanagita, Kosuke Doi, Mana Makinae, Haotian Tan, Makoto Sakai, Sakriani Sakti, Katsuhito Sudoh, and Satoshi Nakamura. 2024. NAIST Simultaneous Speech Translation System for IWSLT 2024. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 170–182, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.