@inproceedings{gishri-etal-2010-lexicon,
title = "Lexicon Design for Transcription of Spontaneous Voice Messages",
author = "Gishri, Michal and
Silber-Varod, Vered and
Moyal, Ami",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/953_Paper.pdf",
abstract = "Building a comprehensive pronunciation lexicon is a crucial element in the success of any speech recognition engine. The first stage of lexicon design involves the compilation of a comprehensive word list that keeps the Out-Of-Vocabulary (OOV) word rate to a minimum. The second stage involves providing optimized phonemic representations for all lexical items on the list. The research presented here focuses on the first stage of lexicon design ― word list compilation, and describes the methodologies employed in the collection of a pronunciation lexicon designed for the purpose of American English voice message transcription using speech recognition. The lexicon design used is based on a topic domain structure with a target of 90{\%} word coverage for each domain. This differs somewhat from standard approaches where probable words from textual corpora are extracted. This paper raises four issues involved in lexicon design for the transcription of spontaneous voice messages: the inclusion of interjections and other characteristics common to spontaneous speech; the identification of unique messaging terminology; the relative ratio of proper nouns to common words; and the overall size of the lexicon.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gishri-etal-2010-lexicon">
<titleInfo>
<title>Lexicon Design for Transcription of Spontaneous Voice Messages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Gishri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Silber-Varod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ami</namePart>
<namePart type="family">Moyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building a comprehensive pronunciation lexicon is a crucial element in the success of any speech recognition engine. The first stage of lexicon design involves the compilation of a comprehensive word list that keeps the Out-Of-Vocabulary (OOV) word rate to a minimum. The second stage involves providing optimized phonemic representations for all lexical items on the list. The research presented here focuses on the first stage of lexicon design ― word list compilation, and describes the methodologies employed in the collection of a pronunciation lexicon designed for the purpose of American English voice message transcription using speech recognition. The lexicon design used is based on a topic domain structure with a target of 90% word coverage for each domain. This differs somewhat from standard approaches where probable words from textual corpora are extracted. This paper raises four issues involved in lexicon design for the transcription of spontaneous voice messages: the inclusion of interjections and other characteristics common to spontaneous speech; the identification of unique messaging terminology; the relative ratio of proper nouns to common words; and the overall size of the lexicon.</abstract>
<identifier type="citekey">gishri-etal-2010-lexicon</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/953_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicon Design for Transcription of Spontaneous Voice Messages
%A Gishri, Michal
%A Silber-Varod, Vered
%A Moyal, Ami
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F gishri-etal-2010-lexicon
%X Building a comprehensive pronunciation lexicon is a crucial element in the success of any speech recognition engine. The first stage of lexicon design involves the compilation of a comprehensive word list that keeps the Out-Of-Vocabulary (OOV) word rate to a minimum. The second stage involves providing optimized phonemic representations for all lexical items on the list. The research presented here focuses on the first stage of lexicon design ― word list compilation, and describes the methodologies employed in the collection of a pronunciation lexicon designed for the purpose of American English voice message transcription using speech recognition. The lexicon design used is based on a topic domain structure with a target of 90% word coverage for each domain. This differs somewhat from standard approaches where probable words from textual corpora are extracted. This paper raises four issues involved in lexicon design for the transcription of spontaneous voice messages: the inclusion of interjections and other characteristics common to spontaneous speech; the identification of unique messaging terminology; the relative ratio of proper nouns to common words; and the overall size of the lexicon.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/953_Paper.pdf
Markdown (Informal)
[Lexicon Design for Transcription of Spontaneous Voice Messages](http://www.lrec-conf.org/proceedings/lrec2010/pdf/953_Paper.pdf) (Gishri et al., LREC 2010)
ACL