@inproceedings{yao-etal-2010-practical,
title = "Practical Evaluation of Speech Recognizers for Virtual Human Dialogue Systems",
author = "Yao, Xuchen and
Bhutada, Pravin and
Georgila, Kallirroi and
Sagae, Kenji and
Artstein, Ron and
Traum, David",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/675_Paper.pdf",
abstract = "We perform a large-scale evaluation of multiple off-the-shelf speech recognizers across diverse domains for virtual human dialogue systems. Our evaluation is aimed at speech recognition consumers and potential consumers with limited experience with readily available recognizers. We focus on practical factors to determine what levels of performance can be expected from different available recognizers in various projects featuring different types of conversational utterances. Our results show that there is no single recognizer that outperforms all other recognizers in all domains. The performance of each recognizer may vary significantly depending on the domain, the size and perplexity of the corpus, the out-of-vocabulary rate, and whether acoustic and language model adaptation has been used or not. We expect that our evaluation will prove useful to other speech recognition consumers, especially in the dialogue community, and will shed some light on the key problem in spoken dialogue systems of selecting the most suitable available speech recognition system for a particular application, and what impact training will have.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yao-etal-2010-practical">
<titleInfo>
<title>Practical Evaluation of Speech Recognizers for Virtual Human Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuchen</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pravin</namePart>
<namePart type="family">Bhutada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kallirroi</namePart>
<namePart type="family">Georgila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Sagae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ron</namePart>
<namePart type="family">Artstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We perform a large-scale evaluation of multiple off-the-shelf speech recognizers across diverse domains for virtual human dialogue systems. Our evaluation is aimed at speech recognition consumers and potential consumers with limited experience with readily available recognizers. We focus on practical factors to determine what levels of performance can be expected from different available recognizers in various projects featuring different types of conversational utterances. Our results show that there is no single recognizer that outperforms all other recognizers in all domains. The performance of each recognizer may vary significantly depending on the domain, the size and perplexity of the corpus, the out-of-vocabulary rate, and whether acoustic and language model adaptation has been used or not. We expect that our evaluation will prove useful to other speech recognition consumers, especially in the dialogue community, and will shed some light on the key problem in spoken dialogue systems of selecting the most suitable available speech recognition system for a particular application, and what impact training will have.</abstract>
<identifier type="citekey">yao-etal-2010-practical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/675_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Practical Evaluation of Speech Recognizers for Virtual Human Dialogue Systems
%A Yao, Xuchen
%A Bhutada, Pravin
%A Georgila, Kallirroi
%A Sagae, Kenji
%A Artstein, Ron
%A Traum, David
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F yao-etal-2010-practical
%X We perform a large-scale evaluation of multiple off-the-shelf speech recognizers across diverse domains for virtual human dialogue systems. Our evaluation is aimed at speech recognition consumers and potential consumers with limited experience with readily available recognizers. We focus on practical factors to determine what levels of performance can be expected from different available recognizers in various projects featuring different types of conversational utterances. Our results show that there is no single recognizer that outperforms all other recognizers in all domains. The performance of each recognizer may vary significantly depending on the domain, the size and perplexity of the corpus, the out-of-vocabulary rate, and whether acoustic and language model adaptation has been used or not. We expect that our evaluation will prove useful to other speech recognition consumers, especially in the dialogue community, and will shed some light on the key problem in spoken dialogue systems of selecting the most suitable available speech recognition system for a particular application, and what impact training will have.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/675_Paper.pdf
Markdown (Informal)
[Practical Evaluation of Speech Recognizers for Virtual Human Dialogue Systems](http://www.lrec-conf.org/proceedings/lrec2010/pdf/675_Paper.pdf) (Yao et al., LREC 2010)
ACL