@inproceedings{jongtaveesataporn-etal-2008-thai,
title = "{T}hai Broadcast News Corpus Construction and Evaluation",
author = "Jongtaveesataporn, Markpong and
Wutiwiwatchai, Chai and
Iwano, Koji and
Furui, Sadaoki",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/319_paper.pdf",
abstract = "Large speech and text corpora are crucial to the development of a state-of-the-art speech recognition system. This paper reports on the construction and evaluation of the first Thai broadcast news speech and text corpora. Specifications and conventions used in the transcription process are described in the paper. The speech corpus contains about 17 hours of speech data while the text corpus was transcribed from around 35 hours of television broadcast news. The characteristics of the corpus were analyzed and shown in the paper. The speech corpus was split according to the evaluation focus condition used in the DARPA Hub-4 evaluation. An 18K-word Thai speech recognition system was setup to test with this speech corpus as a preliminary experiment. Acoustic model adaptations were performed to improve the system performance. The best system yielded a word error rate of about 20{\%} for clean and planned speech, and below 30{\%} for the overall condition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jongtaveesataporn-etal-2008-thai">
<titleInfo>
<title>Thai Broadcast News Corpus Construction and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markpong</namePart>
<namePart type="family">Jongtaveesataporn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chai</namePart>
<namePart type="family">Wutiwiwatchai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Iwano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadaoki</namePart>
<namePart type="family">Furui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">Khalid</namePart>
<namePart type="family">Choukri</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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large speech and text corpora are crucial to the development of a state-of-the-art speech recognition system. This paper reports on the construction and evaluation of the first Thai broadcast news speech and text corpora. Specifications and conventions used in the transcription process are described in the paper. The speech corpus contains about 17 hours of speech data while the text corpus was transcribed from around 35 hours of television broadcast news. The characteristics of the corpus were analyzed and shown in the paper. The speech corpus was split according to the evaluation focus condition used in the DARPA Hub-4 evaluation. An 18K-word Thai speech recognition system was setup to test with this speech corpus as a preliminary experiment. Acoustic model adaptations were performed to improve the system performance. The best system yielded a word error rate of about 20% for clean and planned speech, and below 30% for the overall condition.</abstract>
<identifier type="citekey">jongtaveesataporn-etal-2008-thai</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/319_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thai Broadcast News Corpus Construction and Evaluation
%A Jongtaveesataporn, Markpong
%A Wutiwiwatchai, Chai
%A Iwano, Koji
%A Furui, Sadaoki
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F jongtaveesataporn-etal-2008-thai
%X Large speech and text corpora are crucial to the development of a state-of-the-art speech recognition system. This paper reports on the construction and evaluation of the first Thai broadcast news speech and text corpora. Specifications and conventions used in the transcription process are described in the paper. The speech corpus contains about 17 hours of speech data while the text corpus was transcribed from around 35 hours of television broadcast news. The characteristics of the corpus were analyzed and shown in the paper. The speech corpus was split according to the evaluation focus condition used in the DARPA Hub-4 evaluation. An 18K-word Thai speech recognition system was setup to test with this speech corpus as a preliminary experiment. Acoustic model adaptations were performed to improve the system performance. The best system yielded a word error rate of about 20% for clean and planned speech, and below 30% for the overall condition.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/319_paper.pdf
Markdown (Informal)
[Thai Broadcast News Corpus Construction and Evaluation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/319_paper.pdf) (Jongtaveesataporn et al., LREC 2008)
ACL
- Markpong Jongtaveesataporn, Chai Wutiwiwatchai, Koji Iwano, and Sadaoki Furui. 2008. Thai Broadcast News Corpus Construction and Evaluation. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).