@inproceedings{bertin-lemee-etal-2022-robust,
title = "Robust Translation of {F}rench Live Speech Transcripts",
author = "Bertin-Lem{\'e}e, Elise and
Klein, Guillaume and
Crego, Josep and
Senellart, Jean",
editor = "Campbell, Janice and
Larocca, Stephen and
Marciano, Jay and
Savenkov, Konstantin and
Yanishevsky, Alex",
booktitle = "Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)",
month = sep,
year = "2022",
address = "Orlando, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2022.amta-upg.32",
pages = "455--464",
abstract = "Despite a narrowed performance gap with direct approaches, cascade solutions, involving automatic speech recognition (ASR) and machine translation (MT) are still largely employed in speech translation (ST). Direct approaches employing a single model to translate the input speech signal suffer from the critical bottleneck of data scarcity. In addition, multiple industry applications display speech transcripts alongside translations, making cascade approaches more realistic and practical. In the context of cascaded simultaneous ST, we propose several solutions to adapt a neural MT network to take as input the transcripts output by an ASR system. Adaptation is achieved by enriching speech transcripts and MT data sets so that they more closely resemble each other, thereby improving the system robustness to error propagation and enhancing result legibility for humans. We address aspects such as sentence boundaries, capitalisation, punctuation, hesitations, repetitions, homophones, etc. while taking into account the low latency requirement of simultaneous ST systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bertin-lemee-etal-2022-robust">
<titleInfo>
<title>Robust Translation of French Live Speech Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elise</namePart>
<namePart type="family">Bertin-Lemée</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Crego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Senellart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janice</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Larocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Marciano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Savenkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Yanishevsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Orlando, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite a narrowed performance gap with direct approaches, cascade solutions, involving automatic speech recognition (ASR) and machine translation (MT) are still largely employed in speech translation (ST). Direct approaches employing a single model to translate the input speech signal suffer from the critical bottleneck of data scarcity. In addition, multiple industry applications display speech transcripts alongside translations, making cascade approaches more realistic and practical. In the context of cascaded simultaneous ST, we propose several solutions to adapt a neural MT network to take as input the transcripts output by an ASR system. Adaptation is achieved by enriching speech transcripts and MT data sets so that they more closely resemble each other, thereby improving the system robustness to error propagation and enhancing result legibility for humans. We address aspects such as sentence boundaries, capitalisation, punctuation, hesitations, repetitions, homophones, etc. while taking into account the low latency requirement of simultaneous ST systems.</abstract>
<identifier type="citekey">bertin-lemee-etal-2022-robust</identifier>
<location>
<url>https://aclanthology.org/2022.amta-upg.32</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>455</start>
<end>464</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robust Translation of French Live Speech Transcripts
%A Bertin-Lemée, Elise
%A Klein, Guillaume
%A Crego, Josep
%A Senellart, Jean
%Y Campbell, Janice
%Y Larocca, Stephen
%Y Marciano, Jay
%Y Savenkov, Konstantin
%Y Yanishevsky, Alex
%S Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F bertin-lemee-etal-2022-robust
%X Despite a narrowed performance gap with direct approaches, cascade solutions, involving automatic speech recognition (ASR) and machine translation (MT) are still largely employed in speech translation (ST). Direct approaches employing a single model to translate the input speech signal suffer from the critical bottleneck of data scarcity. In addition, multiple industry applications display speech transcripts alongside translations, making cascade approaches more realistic and practical. In the context of cascaded simultaneous ST, we propose several solutions to adapt a neural MT network to take as input the transcripts output by an ASR system. Adaptation is achieved by enriching speech transcripts and MT data sets so that they more closely resemble each other, thereby improving the system robustness to error propagation and enhancing result legibility for humans. We address aspects such as sentence boundaries, capitalisation, punctuation, hesitations, repetitions, homophones, etc. while taking into account the low latency requirement of simultaneous ST systems.
%U https://aclanthology.org/2022.amta-upg.32
%P 455-464
Markdown (Informal)
[Robust Translation of French Live Speech Transcripts](https://aclanthology.org/2022.amta-upg.32) (Bertin-Lemée et al., AMTA 2022)
ACL
- Elise Bertin-Lemée, Guillaume Klein, Josep Crego, and Jean Senellart. 2022. Robust Translation of French Live Speech Transcripts. In Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track), pages 455–464, Orlando, USA. Association for Machine Translation in the Americas.