@inproceedings{wang-etal-2023-hw,
title = "The {HW}-{TSC}{'}s Speech-to-Speech Translation System for {IWSLT} 2023",
author = "Wang, Minghan and
Li, Yinglu and
Guo, Jiaxin and
Li, Zongyao and
Shang, Hengchao and
Wei, Daimeng and
Zhang, Min and
Tao, Shimin and
Yang, Hao",
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-1.25",
doi = "10.18653/v1/2023.iwslt-1.25",
pages = "277--282",
abstract = "This paper describes our work on the IWSLT2023 Speech-to-Speech task. Our proposed cascaded system consists of an ensemble of Conformer and S2T-Transformer-based ASR models, a Transformer-based MT model, and a Diffusion-based TTS model. Our primary focus in this competition was to investigate the modeling ability of the Diffusion model for TTS tasks in high-resource scenarios and the role of TTS in the overall S2S task. To this end, we proposed DTS, an end-to-end diffusion-based TTS model that takes raw text as input and generates waveform by iteratively denoising on pure Gaussian noise. Compared to previous TTS models, the speech generated by DTS is more natural and performs better in code-switching scenarios. As the training process is end-to-end, it is relatively straightforward. Our experiments demonstrate that DTS outperforms other TTS models on the GigaS2S benchmark, and also brings positive gains for the entire S2S system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-hw">
<titleInfo>
<title>The HW-TSC’s Speech-to-Speech Translation System for IWSLT 2023</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">Yinglu</namePart>
<namePart type="family">Li</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">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</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>
<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 paper describes our work on the IWSLT2023 Speech-to-Speech task. Our proposed cascaded system consists of an ensemble of Conformer and S2T-Transformer-based ASR models, a Transformer-based MT model, and a Diffusion-based TTS model. Our primary focus in this competition was to investigate the modeling ability of the Diffusion model for TTS tasks in high-resource scenarios and the role of TTS in the overall S2S task. To this end, we proposed DTS, an end-to-end diffusion-based TTS model that takes raw text as input and generates waveform by iteratively denoising on pure Gaussian noise. Compared to previous TTS models, the speech generated by DTS is more natural and performs better in code-switching scenarios. As the training process is end-to-end, it is relatively straightforward. Our experiments demonstrate that DTS outperforms other TTS models on the GigaS2S benchmark, and also brings positive gains for the entire S2S system.</abstract>
<identifier type="citekey">wang-etal-2023-hw</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.25</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.25</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>277</start>
<end>282</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The HW-TSC’s Speech-to-Speech Translation System for IWSLT 2023
%A Wang, Minghan
%A Li, Yinglu
%A Guo, Jiaxin
%A Li, Zongyao
%A Shang, Hengchao
%A Wei, Daimeng
%A Zhang, Min
%A Tao, Shimin
%A Yang, Hao
%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 wang-etal-2023-hw
%X This paper describes our work on the IWSLT2023 Speech-to-Speech task. Our proposed cascaded system consists of an ensemble of Conformer and S2T-Transformer-based ASR models, a Transformer-based MT model, and a Diffusion-based TTS model. Our primary focus in this competition was to investigate the modeling ability of the Diffusion model for TTS tasks in high-resource scenarios and the role of TTS in the overall S2S task. To this end, we proposed DTS, an end-to-end diffusion-based TTS model that takes raw text as input and generates waveform by iteratively denoising on pure Gaussian noise. Compared to previous TTS models, the speech generated by DTS is more natural and performs better in code-switching scenarios. As the training process is end-to-end, it is relatively straightforward. Our experiments demonstrate that DTS outperforms other TTS models on the GigaS2S benchmark, and also brings positive gains for the entire S2S system.
%R 10.18653/v1/2023.iwslt-1.25
%U https://aclanthology.org/2023.iwslt-1.25
%U https://doi.org/10.18653/v1/2023.iwslt-1.25
%P 277-282
Markdown (Informal)
[The HW-TSC’s Speech-to-Speech Translation System for IWSLT 2023](https://aclanthology.org/2023.iwslt-1.25) (Wang et al., IWSLT 2023)
ACL
- Minghan Wang, Yinglu Li, Jiaxin Guo, Zongyao Li, Hengchao Shang, Daimeng Wei, Min Zhang, Shimin Tao, and Hao Yang. 2023. The HW-TSC’s Speech-to-Speech Translation System for IWSLT 2023. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 277–282, Toronto, Canada (in-person and online). Association for Computational Linguistics.