@inproceedings{besacier-etal-2014-word,
title = "Word confidence estimation for speech translation",
author = "Besacier, L. and
Lecouteux, B. and
Luong, N. Q. and
Hour, K. and
Hadjsalah, M.",
editor = {Federico, Marcello and
St{\"u}ker, Sebastian and
Yvon, Fran{\c{c}}ois},
booktitle = "Proceedings of the 11th International Workshop on Spoken Language Translation: Papers",
month = dec # " 4-5",
year = "2014",
address = "Lake Tahoe, California",
url = "https://aclanthology.org/2014.iwslt-papers.3",
pages = "169--175",
abstract = "Word Confidence Estimation (WCE) for machine translation (MT) or automatic speech recognition (ASR) consists in judging each word in the (MT or ASR) hypothesis as correct or incorrect by tagging it with an appropriate label. In the past, this task has been treated separately in ASR or MT contexts and we propose here a joint estimation of word confidence for a spoken language translation (SLT) task involving both ASR and MT. This research work is possible because we built a specific corpus which is first presented. This corpus contains 2643 speech utterances for which a quintuplet containing: ASR output (src-asr), verbatim transcript (src-ref), text translation output (tgt-mt), speech translation output (tgt-slt) and post-edition of translation (tgt-pe), is made available. The rest of the paper illustrates how such a corpus (made available to the research community) can be used for evaluating word confidence estimators in ASR, MT or SLT scenarios. WCE for SLT could help rescoring SLT output graphs, improving translators productivity (for translation of lectures or movie subtitling) or it could be useful in interactive speech-to-speech translation scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="besacier-etal-2014-word">
<titleInfo>
<title>Word confidence estimation for speech translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Lecouteux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">N</namePart>
<namePart type="given">Q</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="family">Hour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="family">Hadjsalah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-dec 4-5</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Workshop on Spoken Language Translation: Papers</title>
</titleInfo>
<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">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Lake Tahoe, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Confidence Estimation (WCE) for machine translation (MT) or automatic speech recognition (ASR) consists in judging each word in the (MT or ASR) hypothesis as correct or incorrect by tagging it with an appropriate label. In the past, this task has been treated separately in ASR or MT contexts and we propose here a joint estimation of word confidence for a spoken language translation (SLT) task involving both ASR and MT. This research work is possible because we built a specific corpus which is first presented. This corpus contains 2643 speech utterances for which a quintuplet containing: ASR output (src-asr), verbatim transcript (src-ref), text translation output (tgt-mt), speech translation output (tgt-slt) and post-edition of translation (tgt-pe), is made available. The rest of the paper illustrates how such a corpus (made available to the research community) can be used for evaluating word confidence estimators in ASR, MT or SLT scenarios. WCE for SLT could help rescoring SLT output graphs, improving translators productivity (for translation of lectures or movie subtitling) or it could be useful in interactive speech-to-speech translation scenarios.</abstract>
<identifier type="citekey">besacier-etal-2014-word</identifier>
<location>
<url>https://aclanthology.org/2014.iwslt-papers.3</url>
</location>
<part>
<date>2014-dec 4-5</date>
<extent unit="page">
<start>169</start>
<end>175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word confidence estimation for speech translation
%A Besacier, L.
%A Lecouteux, B.
%A Luong, N. Q.
%A Hour, K.
%A Hadjsalah, M.
%Y Federico, Marcello
%Y Stüker, Sebastian
%Y Yvon, François
%S Proceedings of the 11th International Workshop on Spoken Language Translation: Papers
%D 2014
%8 dec 4 5
%C Lake Tahoe, California
%F besacier-etal-2014-word
%X Word Confidence Estimation (WCE) for machine translation (MT) or automatic speech recognition (ASR) consists in judging each word in the (MT or ASR) hypothesis as correct or incorrect by tagging it with an appropriate label. In the past, this task has been treated separately in ASR or MT contexts and we propose here a joint estimation of word confidence for a spoken language translation (SLT) task involving both ASR and MT. This research work is possible because we built a specific corpus which is first presented. This corpus contains 2643 speech utterances for which a quintuplet containing: ASR output (src-asr), verbatim transcript (src-ref), text translation output (tgt-mt), speech translation output (tgt-slt) and post-edition of translation (tgt-pe), is made available. The rest of the paper illustrates how such a corpus (made available to the research community) can be used for evaluating word confidence estimators in ASR, MT or SLT scenarios. WCE for SLT could help rescoring SLT output graphs, improving translators productivity (for translation of lectures or movie subtitling) or it could be useful in interactive speech-to-speech translation scenarios.
%U https://aclanthology.org/2014.iwslt-papers.3
%P 169-175
Markdown (Informal)
[Word confidence estimation for speech translation](https://aclanthology.org/2014.iwslt-papers.3) (Besacier et al., IWSLT 2014)
ACL
- L. Besacier, B. Lecouteux, N. Q. Luong, K. Hour, and M. Hadjsalah. 2014. Word confidence estimation for speech translation. In Proceedings of the 11th International Workshop on Spoken Language Translation: Papers, pages 169–175, Lake Tahoe, California.