@inproceedings{pellegrini-lamel-2006-experimental,
title = "Experimental detection of vowel pronunciation variants in {A}mharic",
author = "Pellegrini, Thomas and
Lamel, Lori",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/701_pdf.pdf",
abstract = "The pronunciation lexicon is a fundamental element in an automatic speech transcription system. It associates each lexical entry (usually a grapheme), with one or more phonemic or phone-like forms, the pronunciation variants. Thorough knowledge of the target language is a priori necessary to establish the pronunciation baseforms and variants. The reliance on human expertise can pose difficulties in developing a system for a language where such knowledge may not be readily available. In this article a speech recognizer is used to help select pronunciation variants in Amharic, the official language of Ethiopia, focusing on alternate choices for vowels. This study is carried out using an audio corpus composed of 37 hours of speech from radio broadcasts which were orthographically transcribed by native speakers. Since the corpus is relatively small for estimating pronunciation variants, a first set of studies were carried out at a syllabic level. Word lexica were then constructed based on the observed syllable occurences. Automatic alignments were compared for lexica containing different vowel variants, with both context-independent and context-dependent acoustic models sets. The variant2+ measure proposed in (Adda-Decker and Lamel, 1999) is used to assess the potential need for pronunciation variants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pellegrini-lamel-2006-experimental">
<titleInfo>
<title>Experimental detection of vowel pronunciation variants in Amharic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Pellegrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lori</namePart>
<namePart type="family">Lamel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The pronunciation lexicon is a fundamental element in an automatic speech transcription system. It associates each lexical entry (usually a grapheme), with one or more phonemic or phone-like forms, the pronunciation variants. Thorough knowledge of the target language is a priori necessary to establish the pronunciation baseforms and variants. The reliance on human expertise can pose difficulties in developing a system for a language where such knowledge may not be readily available. In this article a speech recognizer is used to help select pronunciation variants in Amharic, the official language of Ethiopia, focusing on alternate choices for vowels. This study is carried out using an audio corpus composed of 37 hours of speech from radio broadcasts which were orthographically transcribed by native speakers. Since the corpus is relatively small for estimating pronunciation variants, a first set of studies were carried out at a syllabic level. Word lexica were then constructed based on the observed syllable occurences. Automatic alignments were compared for lexica containing different vowel variants, with both context-independent and context-dependent acoustic models sets. The variant2+ measure proposed in (Adda-Decker and Lamel, 1999) is used to assess the potential need for pronunciation variants.</abstract>
<identifier type="citekey">pellegrini-lamel-2006-experimental</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/701_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experimental detection of vowel pronunciation variants in Amharic
%A Pellegrini, Thomas
%A Lamel, Lori
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F pellegrini-lamel-2006-experimental
%X The pronunciation lexicon is a fundamental element in an automatic speech transcription system. It associates each lexical entry (usually a grapheme), with one or more phonemic or phone-like forms, the pronunciation variants. Thorough knowledge of the target language is a priori necessary to establish the pronunciation baseforms and variants. The reliance on human expertise can pose difficulties in developing a system for a language where such knowledge may not be readily available. In this article a speech recognizer is used to help select pronunciation variants in Amharic, the official language of Ethiopia, focusing on alternate choices for vowels. This study is carried out using an audio corpus composed of 37 hours of speech from radio broadcasts which were orthographically transcribed by native speakers. Since the corpus is relatively small for estimating pronunciation variants, a first set of studies were carried out at a syllabic level. Word lexica were then constructed based on the observed syllable occurences. Automatic alignments were compared for lexica containing different vowel variants, with both context-independent and context-dependent acoustic models sets. The variant2+ measure proposed in (Adda-Decker and Lamel, 1999) is used to assess the potential need for pronunciation variants.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/701_pdf.pdf
Markdown (Informal)
[Experimental detection of vowel pronunciation variants in Amharic](http://www.lrec-conf.org/proceedings/lrec2006/pdf/701_pdf.pdf) (Pellegrini & Lamel, LREC 2006)
ACL