@inproceedings{wang-etal-2021-exploring-integration,
title = "Exploring the Integration of {E}2{E} {ASR} and Pronunciation Modeling for {E}nglish Mispronunciation Detection",
author = "Wang, Hsin-Wei and
Yan, Bi-Cheng and
Hsu, Yung-Chang and
Chen, Berlin",
editor = "Lee, Lung-Hao and
Chang, Chia-Hui and
Chen, Kuan-Yu",
booktitle = "Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)",
month = oct,
year = "2021",
address = "Taoyuan, Taiwan",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
url = "https://aclanthology.org/2021.rocling-1.17",
pages = "124--131",
abstract = "There has been increasing demand to develop effective computer-assisted language training (CAPT) systems, which can provide feedback on mispronunciations and facilitate second-language (L2) learners to improve their speaking proficiency through repeated practice. Due to the shortage of non-native speech for training the automatic speech recognition (ASR) module of a CAPT system, the corresponding mispronunciation detection performance is often affected by imperfect ASR. Recognizing this importance, we in this paper put forward a two-stage mispronunciation detection method. In the first stage, the speech uttered by an L2 learner is processed by an end-to-end ASR module to produce N-best phone sequence hypotheses. In the second stage, these hypotheses are fed into a pronunciation model which seeks to faithfully predict the phone sequence hypothesis that is most likely pronounced by the learner, so as to improve the performance of mispronunciation detection. Empirical experiments conducted a English benchmark dataset seem to confirm the utility of our method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-exploring-integration">
<titleInfo>
<title>Exploring the Integration of E2E ASR and Pronunciation Modeling for English Mispronunciation Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hsin-Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bi-Cheng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yung-Chang</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berlin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lung-Hao</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-Yu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
<place>
<placeTerm type="text">Taoyuan, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There has been increasing demand to develop effective computer-assisted language training (CAPT) systems, which can provide feedback on mispronunciations and facilitate second-language (L2) learners to improve their speaking proficiency through repeated practice. Due to the shortage of non-native speech for training the automatic speech recognition (ASR) module of a CAPT system, the corresponding mispronunciation detection performance is often affected by imperfect ASR. Recognizing this importance, we in this paper put forward a two-stage mispronunciation detection method. In the first stage, the speech uttered by an L2 learner is processed by an end-to-end ASR module to produce N-best phone sequence hypotheses. In the second stage, these hypotheses are fed into a pronunciation model which seeks to faithfully predict the phone sequence hypothesis that is most likely pronounced by the learner, so as to improve the performance of mispronunciation detection. Empirical experiments conducted a English benchmark dataset seem to confirm the utility of our method.</abstract>
<identifier type="citekey">wang-etal-2021-exploring-integration</identifier>
<location>
<url>https://aclanthology.org/2021.rocling-1.17</url>
</location>
<part>
<date>2021-10</date>
<extent unit="page">
<start>124</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Integration of E2E ASR and Pronunciation Modeling for English Mispronunciation Detection
%A Wang, Hsin-Wei
%A Yan, Bi-Cheng
%A Hsu, Yung-Chang
%A Chen, Berlin
%Y Lee, Lung-Hao
%Y Chang, Chia-Hui
%Y Chen, Kuan-Yu
%S Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)
%D 2021
%8 October
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taoyuan, Taiwan
%F wang-etal-2021-exploring-integration
%X There has been increasing demand to develop effective computer-assisted language training (CAPT) systems, which can provide feedback on mispronunciations and facilitate second-language (L2) learners to improve their speaking proficiency through repeated practice. Due to the shortage of non-native speech for training the automatic speech recognition (ASR) module of a CAPT system, the corresponding mispronunciation detection performance is often affected by imperfect ASR. Recognizing this importance, we in this paper put forward a two-stage mispronunciation detection method. In the first stage, the speech uttered by an L2 learner is processed by an end-to-end ASR module to produce N-best phone sequence hypotheses. In the second stage, these hypotheses are fed into a pronunciation model which seeks to faithfully predict the phone sequence hypothesis that is most likely pronounced by the learner, so as to improve the performance of mispronunciation detection. Empirical experiments conducted a English benchmark dataset seem to confirm the utility of our method.
%U https://aclanthology.org/2021.rocling-1.17
%P 124-131
Markdown (Informal)
[Exploring the Integration of E2E ASR and Pronunciation Modeling for English Mispronunciation Detection](https://aclanthology.org/2021.rocling-1.17) (Wang et al., ROCLING 2021)
ACL