@inproceedings{ruiz-federico-2014-assessing,
title = "Assessing the impact of speech recognition errors on machine translation quality",
author = "Ruiz, Nicholas and
Federico, Marcello",
editor = "Al-Onaizan, Yaser and
Simard, Michel",
booktitle = "Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track",
month = oct # " 22-26",
year = "2014",
address = "Vancouver, Canada",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2014.amta-researchers.20",
pages = "261--274",
abstract = "In spoken language translation, it is crucial that an automatic speech recognition (ASR) system produces outputs that can be adequately translated by a statistical machine translation (SMT) system. While word error rate (WER) is the standard metric of ASR quality, the assumption that each ASR error type is weighted equally is violated in a SMT system that relies on structured input. In this paper, we outline a statistical framework for analyzing the impact of specific ASR error types on translation quality in a speech translation pipeline. Our approach is based on linear mixed-effects models, which allow the analysis of ASR errors on a translation quality metric. The mixed-effects models take into account the variability of ASR systems and the difficulty of each speech utterance being translated in a specific experimental setting. We use mixed-effects models to verify that the ASR errors that compose the WER metric do not contribute equally to translation quality and that interactions exist between ASR errors that cumulatively affect a SMT system{'}s ability to translate an utterance. Our experiments are carried out on the English to French language pair using eight ASR systems and seven post-edited machine translation references from the IWSLT 2013 evaluation campaign. We report significant findings that demonstrate differences in the contributions of specific ASR error types toward speech translation quality and suggest further error types that may contribute to translation difficulty.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruiz-federico-2014-assessing">
<titleInfo>
<title>Assessing the impact of speech recognition errors on machine translation quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-oct 22-26</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Simard</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">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In spoken language translation, it is crucial that an automatic speech recognition (ASR) system produces outputs that can be adequately translated by a statistical machine translation (SMT) system. While word error rate (WER) is the standard metric of ASR quality, the assumption that each ASR error type is weighted equally is violated in a SMT system that relies on structured input. In this paper, we outline a statistical framework for analyzing the impact of specific ASR error types on translation quality in a speech translation pipeline. Our approach is based on linear mixed-effects models, which allow the analysis of ASR errors on a translation quality metric. The mixed-effects models take into account the variability of ASR systems and the difficulty of each speech utterance being translated in a specific experimental setting. We use mixed-effects models to verify that the ASR errors that compose the WER metric do not contribute equally to translation quality and that interactions exist between ASR errors that cumulatively affect a SMT system’s ability to translate an utterance. Our experiments are carried out on the English to French language pair using eight ASR systems and seven post-edited machine translation references from the IWSLT 2013 evaluation campaign. We report significant findings that demonstrate differences in the contributions of specific ASR error types toward speech translation quality and suggest further error types that may contribute to translation difficulty.</abstract>
<identifier type="citekey">ruiz-federico-2014-assessing</identifier>
<location>
<url>https://aclanthology.org/2014.amta-researchers.20</url>
</location>
<part>
<date>2014-oct 22-26</date>
<extent unit="page">
<start>261</start>
<end>274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing the impact of speech recognition errors on machine translation quality
%A Ruiz, Nicholas
%A Federico, Marcello
%Y Al-Onaizan, Yaser
%Y Simard, Michel
%S Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track
%D 2014
%8 oct 22 26
%I Association for Machine Translation in the Americas
%C Vancouver, Canada
%F ruiz-federico-2014-assessing
%X In spoken language translation, it is crucial that an automatic speech recognition (ASR) system produces outputs that can be adequately translated by a statistical machine translation (SMT) system. While word error rate (WER) is the standard metric of ASR quality, the assumption that each ASR error type is weighted equally is violated in a SMT system that relies on structured input. In this paper, we outline a statistical framework for analyzing the impact of specific ASR error types on translation quality in a speech translation pipeline. Our approach is based on linear mixed-effects models, which allow the analysis of ASR errors on a translation quality metric. The mixed-effects models take into account the variability of ASR systems and the difficulty of each speech utterance being translated in a specific experimental setting. We use mixed-effects models to verify that the ASR errors that compose the WER metric do not contribute equally to translation quality and that interactions exist between ASR errors that cumulatively affect a SMT system’s ability to translate an utterance. Our experiments are carried out on the English to French language pair using eight ASR systems and seven post-edited machine translation references from the IWSLT 2013 evaluation campaign. We report significant findings that demonstrate differences in the contributions of specific ASR error types toward speech translation quality and suggest further error types that may contribute to translation difficulty.
%U https://aclanthology.org/2014.amta-researchers.20
%P 261-274
Markdown (Informal)
[Assessing the impact of speech recognition errors on machine translation quality](https://aclanthology.org/2014.amta-researchers.20) (Ruiz & Federico, AMTA 2014)
ACL