@inproceedings{yan-etal-2024-cmus,
title = "{CMU}{'}s {IWSLT} 2024 Offline Speech Translation System: A Cascaded Approach For Long-Form Robustness",
author = "Yan, Brian and
Fernandes, Patrick and
Tian, Jinchuan and
Ouyang, Siqi and
Chen, William and
Livescu, Karen and
Li, Lei and
Neubig, Graham and
Watanabe, Shinji",
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-1.22",
pages = "164--169",
abstract = "This work describes CMU{'}s submission to the IWSLT 2024 Offline Speech Translation (ST) Shared Task for translating English speech to German, Chinese, and Japanese text. We are the first participants to employ a long-form strategy which directly processes unsegmented recordings without the need for a separate voice-activity detection stage (VAD). We show that the Whisper automatic speech recognition (ASR) model has a hallucination problem when applied out-of-the-box to recordings containing non-speech noises, but a simple noisy fine-tuning approach can greatly enhance Whisper{'}s long-form robustness across multiple domains. Then, we feed English ASR outputs into fine-tuned NLLB machine translation (MT) models which are decoded using COMET-based Minimum Bayes Risk. Our VAD-free ASR+MT cascade is tested on TED talks, TV series, and workout videos and shown to outperform prior winning IWSLT submissions and large open-source models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2024-cmus">
<titleInfo>
<title>CMU’s IWSLT 2024 Offline Speech Translation System: A Cascaded Approach For Long-Form Robustness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Fernandes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinchuan</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Livescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</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 work describes CMU’s submission to the IWSLT 2024 Offline Speech Translation (ST) Shared Task for translating English speech to German, Chinese, and Japanese text. We are the first participants to employ a long-form strategy which directly processes unsegmented recordings without the need for a separate voice-activity detection stage (VAD). We show that the Whisper automatic speech recognition (ASR) model has a hallucination problem when applied out-of-the-box to recordings containing non-speech noises, but a simple noisy fine-tuning approach can greatly enhance Whisper’s long-form robustness across multiple domains. Then, we feed English ASR outputs into fine-tuned NLLB machine translation (MT) models which are decoded using COMET-based Minimum Bayes Risk. Our VAD-free ASR+MT cascade is tested on TED talks, TV series, and workout videos and shown to outperform prior winning IWSLT submissions and large open-source models.</abstract>
<identifier type="citekey">yan-etal-2024-cmus</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.22</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>164</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMU’s IWSLT 2024 Offline Speech Translation System: A Cascaded Approach For Long-Form Robustness
%A Yan, Brian
%A Fernandes, Patrick
%A Tian, Jinchuan
%A Ouyang, Siqi
%A Chen, William
%A Livescu, Karen
%A Li, Lei
%A Neubig, Graham
%A Watanabe, Shinji
%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 yan-etal-2024-cmus
%X This work describes CMU’s submission to the IWSLT 2024 Offline Speech Translation (ST) Shared Task for translating English speech to German, Chinese, and Japanese text. We are the first participants to employ a long-form strategy which directly processes unsegmented recordings without the need for a separate voice-activity detection stage (VAD). We show that the Whisper automatic speech recognition (ASR) model has a hallucination problem when applied out-of-the-box to recordings containing non-speech noises, but a simple noisy fine-tuning approach can greatly enhance Whisper’s long-form robustness across multiple domains. Then, we feed English ASR outputs into fine-tuned NLLB machine translation (MT) models which are decoded using COMET-based Minimum Bayes Risk. Our VAD-free ASR+MT cascade is tested on TED talks, TV series, and workout videos and shown to outperform prior winning IWSLT submissions and large open-source models.
%U https://aclanthology.org/2024.iwslt-1.22
%P 164-169
Markdown (Informal)
[CMU’s IWSLT 2024 Offline Speech Translation System: A Cascaded Approach For Long-Form Robustness](https://aclanthology.org/2024.iwslt-1.22) (Yan et al., IWSLT 2024)
ACL
- Brian Yan, Patrick Fernandes, Jinchuan Tian, Siqi Ouyang, William Chen, Karen Livescu, Lei Li, Graham Neubig, and Shinji Watanabe. 2024. CMU’s IWSLT 2024 Offline Speech Translation System: A Cascaded Approach For Long-Form Robustness. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 164–169, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.