@inproceedings{huang-etal-2020-construction,
title = "On Construction of the {ASR}-oriented {I}ndian {E}nglish Pronunciation Dictionary",
author = "Huang, Xian and
Jin, Xin and
Li, Qike and
Zhang, Keliang",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.812",
pages = "6593--6598",
abstract = "As a World English, a New English and a regional variety of English, Indian English (IE) has developed its own distinctive characteristics, especially phonologically, from other varieties of English. An Automatic Speech Recognition (ASR) system simply trained on British English (BE) /American English (AE) speech data and using the BE/AE pronunciation dictionary performs much worse when applied to IE. An applicable IEASR system needs spontaneous IE speech as training materials and a comprehensive, linguistically-guided IE pronunciation dictionary (IEPD) so as to achieve the effective mapping between the acoustic model and language model. This research builds a small IE spontaneous speech corpus, analyzes and summarizes the phonological variation features of IE, comes up with an IE phoneme set and complies the IEPD (including a common-English-word list, an Indian-word list, an acronym list and an affix list). Finally, two ASR systems are trained with 120 hours IE spontaneous speech data, using the IEPD we construct in this study and CMUdict separately. The two systems are tested with 50 audio clips of IE spontaneous speech. The result shows the system trained with IEPD performs better than the one trained with CMUdict with WER being 15.63{\%} lower on the test data.",
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="huang-etal-2020-construction">
<titleInfo>
<title>On Construction of the ASR-oriented Indian English Pronunciation Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qike</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keliang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</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 Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>As a World English, a New English and a regional variety of English, Indian English (IE) has developed its own distinctive characteristics, especially phonologically, from other varieties of English. An Automatic Speech Recognition (ASR) system simply trained on British English (BE) /American English (AE) speech data and using the BE/AE pronunciation dictionary performs much worse when applied to IE. An applicable IEASR system needs spontaneous IE speech as training materials and a comprehensive, linguistically-guided IE pronunciation dictionary (IEPD) so as to achieve the effective mapping between the acoustic model and language model. This research builds a small IE spontaneous speech corpus, analyzes and summarizes the phonological variation features of IE, comes up with an IE phoneme set and complies the IEPD (including a common-English-word list, an Indian-word list, an acronym list and an affix list). Finally, two ASR systems are trained with 120 hours IE spontaneous speech data, using the IEPD we construct in this study and CMUdict separately. The two systems are tested with 50 audio clips of IE spontaneous speech. The result shows the system trained with IEPD performs better than the one trained with CMUdict with WER being 15.63% lower on the test data.</abstract>
<identifier type="citekey">huang-etal-2020-construction</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.812</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6593</start>
<end>6598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Construction of the ASR-oriented Indian English Pronunciation Dictionary
%A Huang, Xian
%A Jin, Xin
%A Li, Qike
%A Zhang, Keliang
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth 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 huang-etal-2020-construction
%X As a World English, a New English and a regional variety of English, Indian English (IE) has developed its own distinctive characteristics, especially phonologically, from other varieties of English. An Automatic Speech Recognition (ASR) system simply trained on British English (BE) /American English (AE) speech data and using the BE/AE pronunciation dictionary performs much worse when applied to IE. An applicable IEASR system needs spontaneous IE speech as training materials and a comprehensive, linguistically-guided IE pronunciation dictionary (IEPD) so as to achieve the effective mapping between the acoustic model and language model. This research builds a small IE spontaneous speech corpus, analyzes and summarizes the phonological variation features of IE, comes up with an IE phoneme set and complies the IEPD (including a common-English-word list, an Indian-word list, an acronym list and an affix list). Finally, two ASR systems are trained with 120 hours IE spontaneous speech data, using the IEPD we construct in this study and CMUdict separately. The two systems are tested with 50 audio clips of IE spontaneous speech. The result shows the system trained with IEPD performs better than the one trained with CMUdict with WER being 15.63% lower on the test data.
%U https://aclanthology.org/2020.lrec-1.812
%P 6593-6598
Markdown (Informal)
[On Construction of the ASR-oriented Indian English Pronunciation Dictionary](https://aclanthology.org/2020.lrec-1.812) (Huang et al., LREC 2020)
ACL