@inproceedings{tadimeti-etal-2022-evaluation,
title = "Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain",
author = "Tadimeti, Divya and
Georgila, Kallirroi and
Traum, David",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.645",
pages = "6001--6008",
abstract = "We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems on dialogue agent-directed English speech from speakers with General American vs. non-American accents. Our results show that the performance of the ASR systems for non-American accents is considerably worse than for General American accents. Depending on the recognizer, the absolute difference in performance between General American accents and all non-American accents combined can vary approximately from 2{\%} to 12{\%}, with relative differences varying approximately between 16{\%} and 49{\%}. This drop in performance becomes even larger when we consider specific categories of non-American accents indicating a need for more diligent collection of and training on non-native English speaker data in order to narrow this performance gap. There are performance differences across ASR systems, and while the same general pattern holds, with more errors for non-American accents, there are some accents for which the best recognizer is different than in the overall case. We expect these results to be useful for dialogue system designers in developing more robust inclusive dialogue systems, and for ASR providers in taking into account performance requirements for different accents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tadimeti-etal-2022-evaluation">
<titleInfo>
<title>Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divya</namePart>
<namePart type="family">Tadimeti</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">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems on dialogue agent-directed English speech from speakers with General American vs. non-American accents. Our results show that the performance of the ASR systems for non-American accents is considerably worse than for General American accents. Depending on the recognizer, the absolute difference in performance between General American accents and all non-American accents combined can vary approximately from 2% to 12%, with relative differences varying approximately between 16% and 49%. This drop in performance becomes even larger when we consider specific categories of non-American accents indicating a need for more diligent collection of and training on non-native English speaker data in order to narrow this performance gap. There are performance differences across ASR systems, and while the same general pattern holds, with more errors for non-American accents, there are some accents for which the best recognizer is different than in the overall case. We expect these results to be useful for dialogue system designers in developing more robust inclusive dialogue systems, and for ASR providers in taking into account performance requirements for different accents.</abstract>
<identifier type="citekey">tadimeti-etal-2022-evaluation</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.645</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6001</start>
<end>6008</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain
%A Tadimeti, Divya
%A Georgila, Kallirroi
%A Traum, David
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F tadimeti-etal-2022-evaluation
%X We evaluate several publicly available off-the-shelf (commercial and research) automatic speech recognition (ASR) systems on dialogue agent-directed English speech from speakers with General American vs. non-American accents. Our results show that the performance of the ASR systems for non-American accents is considerably worse than for General American accents. Depending on the recognizer, the absolute difference in performance between General American accents and all non-American accents combined can vary approximately from 2% to 12%, with relative differences varying approximately between 16% and 49%. This drop in performance becomes even larger when we consider specific categories of non-American accents indicating a need for more diligent collection of and training on non-native English speaker data in order to narrow this performance gap. There are performance differences across ASR systems, and while the same general pattern holds, with more errors for non-American accents, there are some accents for which the best recognizer is different than in the overall case. We expect these results to be useful for dialogue system designers in developing more robust inclusive dialogue systems, and for ASR providers in taking into account performance requirements for different accents.
%U https://aclanthology.org/2022.lrec-1.645
%P 6001-6008
Markdown (Informal)
[Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain](https://aclanthology.org/2022.lrec-1.645) (Tadimeti et al., LREC 2022)
ACL