@inproceedings{masmoudi-etal-2014-corpus,
title = "A Corpus and Phonetic Dictionary for {T}unisian {A}rabic Speech Recognition",
author = "Masmoudi, Abir and
Khmekhem, Mariem Ellouze and
Est{\`e}ve, Yannick and
Belguith, Lamia Hadrich and
Habash, Nizar",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/454_Paper.pdf",
pages = "306--310",
abstract = "In this paper we describe an effort to create a corpus and phonetic dictionary for Tunisian Arabic Automatic Speech Recognition (ASR). The corpus, named TARIC (Tunisian Arabic Railway Interaction Corpus) has a collection of audio recordings and transcriptions from dialogues in the Tunisian Railway Transport Network. The phonetic (or pronunciation) dictionary is an important ASR component that serves as an intermediary between acoustic models and language models in ASR systems. The method proposed in this paper, to automatically generate a phonetic dictionary, is rule based. For that reason, we define a set of pronunciation rules and a lexicon of exceptions. To determine the performance of our phonetic rules, we chose to evaluate our pronunciation dictionary on two types of corpora. The word error rate of word grapheme-to-phoneme mapping is around 9{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="masmoudi-etal-2014-corpus">
<titleInfo>
<title>A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abir</namePart>
<namePart type="family">Masmoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariem</namePart>
<namePart type="given">Ellouze</namePart>
<namePart type="family">Khmekhem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannick</namePart>
<namePart type="family">Estève</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe an effort to create a corpus and phonetic dictionary for Tunisian Arabic Automatic Speech Recognition (ASR). The corpus, named TARIC (Tunisian Arabic Railway Interaction Corpus) has a collection of audio recordings and transcriptions from dialogues in the Tunisian Railway Transport Network. The phonetic (or pronunciation) dictionary is an important ASR component that serves as an intermediary between acoustic models and language models in ASR systems. The method proposed in this paper, to automatically generate a phonetic dictionary, is rule based. For that reason, we define a set of pronunciation rules and a lexicon of exceptions. To determine the performance of our phonetic rules, we chose to evaluate our pronunciation dictionary on two types of corpora. The word error rate of word grapheme-to-phoneme mapping is around 9%.</abstract>
<identifier type="citekey">masmoudi-etal-2014-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/454_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>306</start>
<end>310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition
%A Masmoudi, Abir
%A Khmekhem, Mariem Ellouze
%A Estève, Yannick
%A Belguith, Lamia Hadrich
%A Habash, Nizar
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F masmoudi-etal-2014-corpus
%X In this paper we describe an effort to create a corpus and phonetic dictionary for Tunisian Arabic Automatic Speech Recognition (ASR). The corpus, named TARIC (Tunisian Arabic Railway Interaction Corpus) has a collection of audio recordings and transcriptions from dialogues in the Tunisian Railway Transport Network. The phonetic (or pronunciation) dictionary is an important ASR component that serves as an intermediary between acoustic models and language models in ASR systems. The method proposed in this paper, to automatically generate a phonetic dictionary, is rule based. For that reason, we define a set of pronunciation rules and a lexicon of exceptions. To determine the performance of our phonetic rules, we chose to evaluate our pronunciation dictionary on two types of corpora. The word error rate of word grapheme-to-phoneme mapping is around 9%.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/454_Paper.pdf
%P 306-310
Markdown (Informal)
[A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition](http://www.lrec-conf.org/proceedings/lrec2014/pdf/454_Paper.pdf) (Masmoudi et al., LREC 2014)
ACL
- Abir Masmoudi, Mariem Ellouze Khmekhem, Yannick Estève, Lamia Hadrich Belguith, and Nizar Habash. 2014. A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 306–310, Reykjavik, Iceland. European Language Resources Association (ELRA).