@inproceedings{seng-etal-2008-first,
title = "First Broadcast News Transcription System for {K}hmer Language",
author = "Seng, Sopheap and
Sam, Sethserey and
Besacier, Laurent and
Bigi, Brigitte and
Castelli, Eric",
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/661_paper.pdf",
abstract = "In this paper we present an overview on the development of a large vocabulary continuous speech recognition (LVCSR) system for Khmer, the official language of Cambodia, spoken by more than 15 million people. As an under-resourced language, develop a LVCSR system for Khmer is a challenging task. We describe our methodologies for quick language data collection and processing for language modeling and acoustic modeling. For language modeling, we investigate the use of word and sub-word as basic modeling unit in order to see the potential of sub-word units in the case of unsegmented language like Khmer. Grapheme-based acoustic modeling is used to quickly build our Khmer language acoustic model. Furthermore, the approaches and tools used for the development of our system are documented and made publicly available on the web. We hope this will contribute to accelerate the development of LVCSR system for a new language, especially for under-resource languages of developing countries where resources and expertise are limited.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seng-etal-2008-first">
<titleInfo>
<title>First Broadcast News Transcription System for Khmer Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sopheap</namePart>
<namePart type="family">Seng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sethserey</namePart>
<namePart type="family">Sam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brigitte</namePart>
<namePart type="family">Bigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Castelli</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>In this paper we present an overview on the development of a large vocabulary continuous speech recognition (LVCSR) system for Khmer, the official language of Cambodia, spoken by more than 15 million people. As an under-resourced language, develop a LVCSR system for Khmer is a challenging task. We describe our methodologies for quick language data collection and processing for language modeling and acoustic modeling. For language modeling, we investigate the use of word and sub-word as basic modeling unit in order to see the potential of sub-word units in the case of unsegmented language like Khmer. Grapheme-based acoustic modeling is used to quickly build our Khmer language acoustic model. Furthermore, the approaches and tools used for the development of our system are documented and made publicly available on the web. We hope this will contribute to accelerate the development of LVCSR system for a new language, especially for under-resource languages of developing countries where resources and expertise are limited.</abstract>
<identifier type="citekey">seng-etal-2008-first</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/661_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T First Broadcast News Transcription System for Khmer Language
%A Seng, Sopheap
%A Sam, Sethserey
%A Besacier, Laurent
%A Bigi, Brigitte
%A Castelli, Eric
%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 seng-etal-2008-first
%X In this paper we present an overview on the development of a large vocabulary continuous speech recognition (LVCSR) system for Khmer, the official language of Cambodia, spoken by more than 15 million people. As an under-resourced language, develop a LVCSR system for Khmer is a challenging task. We describe our methodologies for quick language data collection and processing for language modeling and acoustic modeling. For language modeling, we investigate the use of word and sub-word as basic modeling unit in order to see the potential of sub-word units in the case of unsegmented language like Khmer. Grapheme-based acoustic modeling is used to quickly build our Khmer language acoustic model. Furthermore, the approaches and tools used for the development of our system are documented and made publicly available on the web. We hope this will contribute to accelerate the development of LVCSR system for a new language, especially for under-resource languages of developing countries where resources and expertise are limited.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/661_paper.pdf
Markdown (Informal)
[First Broadcast News Transcription System for Khmer Language](http://www.lrec-conf.org/proceedings/lrec2008/pdf/661_paper.pdf) (Seng et al., LREC 2008)
ACL
- Sopheap Seng, Sethserey Sam, Laurent Besacier, Brigitte Bigi, and Eric Castelli. 2008. First Broadcast News Transcription System for Khmer Language. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).