@inproceedings{georgila-etal-2020-evaluation,
title = "Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains",
author = "Georgila, Kallirroi and
Leuski, Anton and
Yanov, Volodymyr and
Traum, David",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.797",
pages = "6469--6476",
abstract = "We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems across diverse dialogue domains (in US-English). Our evaluation is aimed at non-experts with limited experience in speech recognition. Our goal is not only to compare a variety of ASR systems on several diverse data sets but also to measure how much ASR technology has advanced since our previous large-scale evaluations on the same data sets. Our results show that the performance of each speech recognizer can vary significantly depending on the domain. Furthermore, despite major recent progress in ASR technology, current state-of-the-art speech recognizers perform poorly in domains that require special vocabulary and language models, and under noisy conditions. We expect that our evaluation will prove useful to ASR consumers and dialogue system designers.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="georgila-etal-2020-evaluation">
<titleInfo>
<title>Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains</title>
</titleInfo>
<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">Anton</namePart>
<namePart type="family">Leuski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Volodymyr</namePart>
<namePart type="family">Yanov</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>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems across diverse dialogue domains (in US-English). Our evaluation is aimed at non-experts with limited experience in speech recognition. Our goal is not only to compare a variety of ASR systems on several diverse data sets but also to measure how much ASR technology has advanced since our previous large-scale evaluations on the same data sets. Our results show that the performance of each speech recognizer can vary significantly depending on the domain. Furthermore, despite major recent progress in ASR technology, current state-of-the-art speech recognizers perform poorly in domains that require special vocabulary and language models, and under noisy conditions. We expect that our evaluation will prove useful to ASR consumers and dialogue system designers.</abstract>
<identifier type="citekey">georgila-etal-2020-evaluation</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.797</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>6469</start>
<end>6476</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains
%A Georgila, Kallirroi
%A Leuski, Anton
%A Yanov, Volodymyr
%A Traum, David
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F georgila-etal-2020-evaluation
%X We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems across diverse dialogue domains (in US-English). Our evaluation is aimed at non-experts with limited experience in speech recognition. Our goal is not only to compare a variety of ASR systems on several diverse data sets but also to measure how much ASR technology has advanced since our previous large-scale evaluations on the same data sets. Our results show that the performance of each speech recognizer can vary significantly depending on the domain. Furthermore, despite major recent progress in ASR technology, current state-of-the-art speech recognizers perform poorly in domains that require special vocabulary and language models, and under noisy conditions. We expect that our evaluation will prove useful to ASR consumers and dialogue system designers.
%U https://aclanthology.org/2020.lrec-1.797
%P 6469-6476
Markdown (Informal)
[Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains](https://aclanthology.org/2020.lrec-1.797) (Georgila et al., LREC 2020)
ACL