@inproceedings{yan-etal-2023-cmus,
title = "{CMU}{'}s {IWSLT} 2023 Simultaneous Speech Translation System",
author = "Yan, Brian and
Shi, Jiatong and
Maiti, Soumi and
Chen, William and
Li, Xinjian and
Peng, Yifan and
Arora, Siddhant and
Watanabe, Shinji",
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-1.20",
doi = "10.18653/v1/2023.iwslt-1.20",
pages = "235--240",
abstract = "This paper describes CMU{'}s submission to the IWSLT 2023 simultaneous speech translation shared task for translating English speech to both German text and speech in a streaming fashion. We first build offline speech-to-text (ST) models using the joint CTC/attention framework. These models also use WavLM front-end features and mBART decoder initialization. We adapt our offline ST models for simultaneous speech-to-text translation (SST) by 1) incrementally encoding chunks of input speech, re-computing encoder states for each new chunk and 2) incrementally decoding output text, pruning beam search hypotheses to 1-best after processing each chunk. We then build text-to-speech (TTS) models using the VITS framework and achieve simultaneous speech-to-speech translation (SS2ST) by cascading our SST and TTS models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2023-cmus">
<titleInfo>
<title>CMU’s IWSLT 2023 Simultaneous Speech Translation System</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">Jiatong</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumi</namePart>
<namePart type="family">Maiti</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">Xinjian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Arora</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>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 CMU’s submission to the IWSLT 2023 simultaneous speech translation shared task for translating English speech to both German text and speech in a streaming fashion. We first build offline speech-to-text (ST) models using the joint CTC/attention framework. These models also use WavLM front-end features and mBART decoder initialization. We adapt our offline ST models for simultaneous speech-to-text translation (SST) by 1) incrementally encoding chunks of input speech, re-computing encoder states for each new chunk and 2) incrementally decoding output text, pruning beam search hypotheses to 1-best after processing each chunk. We then build text-to-speech (TTS) models using the VITS framework and achieve simultaneous speech-to-speech translation (SS2ST) by cascading our SST and TTS models.</abstract>
<identifier type="citekey">yan-etal-2023-cmus</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.20</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.20</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>235</start>
<end>240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMU’s IWSLT 2023 Simultaneous Speech Translation System
%A Yan, Brian
%A Shi, Jiatong
%A Maiti, Soumi
%A Chen, William
%A Li, Xinjian
%A Peng, Yifan
%A Arora, Siddhant
%A Watanabe, Shinji
%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 yan-etal-2023-cmus
%X This paper describes CMU’s submission to the IWSLT 2023 simultaneous speech translation shared task for translating English speech to both German text and speech in a streaming fashion. We first build offline speech-to-text (ST) models using the joint CTC/attention framework. These models also use WavLM front-end features and mBART decoder initialization. We adapt our offline ST models for simultaneous speech-to-text translation (SST) by 1) incrementally encoding chunks of input speech, re-computing encoder states for each new chunk and 2) incrementally decoding output text, pruning beam search hypotheses to 1-best after processing each chunk. We then build text-to-speech (TTS) models using the VITS framework and achieve simultaneous speech-to-speech translation (SS2ST) by cascading our SST and TTS models.
%R 10.18653/v1/2023.iwslt-1.20
%U https://aclanthology.org/2023.iwslt-1.20
%U https://doi.org/10.18653/v1/2023.iwslt-1.20
%P 235-240
Markdown (Informal)
[CMU’s IWSLT 2023 Simultaneous Speech Translation System](https://aclanthology.org/2023.iwslt-1.20) (Yan et al., IWSLT 2023)
ACL
- Brian Yan, Jiatong Shi, Soumi Maiti, William Chen, Xinjian Li, Yifan Peng, Siddhant Arora, and Shinji Watanabe. 2023. CMU’s IWSLT 2023 Simultaneous Speech Translation System. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 235–240, Toronto, Canada (in-person and online). Association for Computational Linguistics.