@inproceedings{zhou-etal-2023-submission,
title = "Submission of {USTC}`s System for the {IWSLT} 2023 - Offline Speech Translation Track",
author = "Zhou, Xinyuan and
Cui, Jianwei and
Ye, Zhongyi and
Wang, Yichi and
Xu, Luzhen and
Zhang, Hanyi and
Zhang, Weitai and
Dai, Lirong",
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-1.15/",
doi = "10.18653/v1/2023.iwslt-1.15",
pages = "194--201",
abstract = "This paper describes the submissions of the research group USTC-NELSLIP to the 2023 IWSLT Offline Speech Translation competition, which involves translating spoken English into written Chinese. We utilize both cascaded models and end-to-end models for this task. To improve the performance of the cascaded models, we introduce Whisper to reduce errors in the intermediate source language text, achieving a significant improvement in ASR recognition performance. For end-to-end models, we propose Stacked Acoustic-and-Textual En- coding extension (SATE-ex), which feeds the output of the acoustic decoder into the textual decoder for information fusion and to prevent error propagation. Additionally, we improve the performance of the end-to-end system in translating speech by combining the SATE-ex model with the encoder-decoder model through ensembling."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2023-submission">
<titleInfo>
<title>Submission of USTC‘s System for the IWSLT 2023 - Offline Speech Translation Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyuan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianwei</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyi</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luzhen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weitai</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lirong</namePart>
<namePart type="family">Dai</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 the submissions of the research group USTC-NELSLIP to the 2023 IWSLT Offline Speech Translation competition, which involves translating spoken English into written Chinese. We utilize both cascaded models and end-to-end models for this task. To improve the performance of the cascaded models, we introduce Whisper to reduce errors in the intermediate source language text, achieving a significant improvement in ASR recognition performance. For end-to-end models, we propose Stacked Acoustic-and-Textual En- coding extension (SATE-ex), which feeds the output of the acoustic decoder into the textual decoder for information fusion and to prevent error propagation. Additionally, we improve the performance of the end-to-end system in translating speech by combining the SATE-ex model with the encoder-decoder model through ensembling.</abstract>
<identifier type="citekey">zhou-etal-2023-submission</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.15</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.15/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>194</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Submission of USTC‘s System for the IWSLT 2023 - Offline Speech Translation Track
%A Zhou, Xinyuan
%A Cui, Jianwei
%A Ye, Zhongyi
%A Wang, Yichi
%A Xu, Luzhen
%A Zhang, Hanyi
%A Zhang, Weitai
%A Dai, Lirong
%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 zhou-etal-2023-submission
%X This paper describes the submissions of the research group USTC-NELSLIP to the 2023 IWSLT Offline Speech Translation competition, which involves translating spoken English into written Chinese. We utilize both cascaded models and end-to-end models for this task. To improve the performance of the cascaded models, we introduce Whisper to reduce errors in the intermediate source language text, achieving a significant improvement in ASR recognition performance. For end-to-end models, we propose Stacked Acoustic-and-Textual En- coding extension (SATE-ex), which feeds the output of the acoustic decoder into the textual decoder for information fusion and to prevent error propagation. Additionally, we improve the performance of the end-to-end system in translating speech by combining the SATE-ex model with the encoder-decoder model through ensembling.
%R 10.18653/v1/2023.iwslt-1.15
%U https://aclanthology.org/2023.iwslt-1.15/
%U https://doi.org/10.18653/v1/2023.iwslt-1.15
%P 194-201
Markdown (Informal)
[Submission of USTC’s System for the IWSLT 2023 - Offline Speech Translation Track](https://aclanthology.org/2023.iwslt-1.15/) (Zhou et al., IWSLT 2023)
ACL
- Xinyuan Zhou, Jianwei Cui, Zhongyi Ye, Yichi Wang, Luzhen Xu, Hanyi Zhang, Weitai Zhang, and Lirong Dai. 2023. Submission of USTC’s System for the IWSLT 2023 - Offline Speech Translation Track. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 194–201, Toronto, Canada (in-person and online). Association for Computational Linguistics.