@inproceedings{shubha-etal-2019-customizing,
title = "Customizing Grapheme-to-Phoneme System for Non-Trivial Transcription Problems in {B}angla Language",
author = "Shubha, Sudipta Saha and
Sadeq, Nafis and
Ahmed, Shafayat and
Islam, Md. Nahidul and
Adnan, Muhammad Abdullah and
Khan, Md. Yasin Ali and
Islam, Mohammad Zuberul",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1322/",
doi = "10.18653/v1/N19-1322",
pages = "3191--3200",
abstract = "Grapheme to phoneme (G2P) conversion is an integral part in various text and speech processing systems, such as: Text to Speech system, Speech Recognition system, etc. The existing methodologies for G2P conversion in Bangla language are mostly rule-based. However, data-driven approaches have proved their superiority over rule-based approaches for large-scale G2P conversion in other languages, such as: English, German, etc. As the performance of data-driven approaches for G2P conversion depend largely on pronunciation lexicon on which the system is trained, in this paper, we investigate on developing an improved training lexicon by identifying and categorizing the critical cases in Bangla language and include those critical cases in training lexicon for developing a robust G2P conversion system in Bangla language. Additionally, we have incorporated nasal vowels in our proposed phoneme list. Our methodology outperforms other state-of-the-art approaches for G2P conversion in Bangla language."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shubha-etal-2019-customizing">
<titleInfo>
<title>Customizing Grapheme-to-Phoneme System for Non-Trivial Transcription Problems in Bangla Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="given">Saha</namePart>
<namePart type="family">Shubha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafis</namePart>
<namePart type="family">Sadeq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafayat</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Nahidul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Abdullah</namePart>
<namePart type="family">Adnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Yasin</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Zuberul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grapheme to phoneme (G2P) conversion is an integral part in various text and speech processing systems, such as: Text to Speech system, Speech Recognition system, etc. The existing methodologies for G2P conversion in Bangla language are mostly rule-based. However, data-driven approaches have proved their superiority over rule-based approaches for large-scale G2P conversion in other languages, such as: English, German, etc. As the performance of data-driven approaches for G2P conversion depend largely on pronunciation lexicon on which the system is trained, in this paper, we investigate on developing an improved training lexicon by identifying and categorizing the critical cases in Bangla language and include those critical cases in training lexicon for developing a robust G2P conversion system in Bangla language. Additionally, we have incorporated nasal vowels in our proposed phoneme list. Our methodology outperforms other state-of-the-art approaches for G2P conversion in Bangla language.</abstract>
<identifier type="citekey">shubha-etal-2019-customizing</identifier>
<identifier type="doi">10.18653/v1/N19-1322</identifier>
<location>
<url>https://aclanthology.org/N19-1322/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>3191</start>
<end>3200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Customizing Grapheme-to-Phoneme System for Non-Trivial Transcription Problems in Bangla Language
%A Shubha, Sudipta Saha
%A Sadeq, Nafis
%A Ahmed, Shafayat
%A Islam, Md. Nahidul
%A Adnan, Muhammad Abdullah
%A Khan, Md. Yasin Ali
%A Islam, Mohammad Zuberul
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F shubha-etal-2019-customizing
%X Grapheme to phoneme (G2P) conversion is an integral part in various text and speech processing systems, such as: Text to Speech system, Speech Recognition system, etc. The existing methodologies for G2P conversion in Bangla language are mostly rule-based. However, data-driven approaches have proved their superiority over rule-based approaches for large-scale G2P conversion in other languages, such as: English, German, etc. As the performance of data-driven approaches for G2P conversion depend largely on pronunciation lexicon on which the system is trained, in this paper, we investigate on developing an improved training lexicon by identifying and categorizing the critical cases in Bangla language and include those critical cases in training lexicon for developing a robust G2P conversion system in Bangla language. Additionally, we have incorporated nasal vowels in our proposed phoneme list. Our methodology outperforms other state-of-the-art approaches for G2P conversion in Bangla language.
%R 10.18653/v1/N19-1322
%U https://aclanthology.org/N19-1322/
%U https://doi.org/10.18653/v1/N19-1322
%P 3191-3200
Markdown (Informal)
[Customizing Grapheme-to-Phoneme System for Non-Trivial Transcription Problems in Bangla Language](https://aclanthology.org/N19-1322/) (Shubha et al., NAACL 2019)
ACL
- Sudipta Saha Shubha, Nafis Sadeq, Shafayat Ahmed, Md. Nahidul Islam, Muhammad Abdullah Adnan, Md. Yasin Ali Khan, and Mohammad Zuberul Islam. 2019. Customizing Grapheme-to-Phoneme System for Non-Trivial Transcription Problems in Bangla Language. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3191–3200, Minneapolis, Minnesota. Association for Computational Linguistics.