@inproceedings{charonnat-etal-2008-automatic,
title = "Automatic Phone Segmentation of Expressive Speech",
author = {Charonnat, Laure and
Vidal, Ga{\"e}lle and
Boeffard, Olivier},
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/596_paper.pdf",
abstract = "In order to improve the flexibility and the precision of an automatic phone segmentation system for a type of expressive speech, the dubbing into French of fiction movies, we developed both the phonetic labeling process and the alignment process. The automatic labelling system relies on an automatic grapheme-to-phoneme conversion including all the variants of the phonetic chain and on HMM modeling. In this article, we will distinguish three sets of phone models: a set of context independent models, a set of left and right context dependant models and finally a mixing of the two that combines phone and triphone models according to the precision of alignment obtained for each phonetic broad-class. The three models are evaluated on a test corpus. On the one hand we notice a little decrease in the score of phonetic labelling mainly due to pauses insertions, but on the other hand the mixed set of models gives the best results for the score of precision of the alignment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="charonnat-etal-2008-automatic">
<titleInfo>
<title>Automatic Phone Segmentation of Expressive Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laure</namePart>
<namePart type="family">Charonnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaëlle</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Boeffard</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 order to improve the flexibility and the precision of an automatic phone segmentation system for a type of expressive speech, the dubbing into French of fiction movies, we developed both the phonetic labeling process and the alignment process. The automatic labelling system relies on an automatic grapheme-to-phoneme conversion including all the variants of the phonetic chain and on HMM modeling. In this article, we will distinguish three sets of phone models: a set of context independent models, a set of left and right context dependant models and finally a mixing of the two that combines phone and triphone models according to the precision of alignment obtained for each phonetic broad-class. The three models are evaluated on a test corpus. On the one hand we notice a little decrease in the score of phonetic labelling mainly due to pauses insertions, but on the other hand the mixed set of models gives the best results for the score of precision of the alignment.</abstract>
<identifier type="citekey">charonnat-etal-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/596_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Phone Segmentation of Expressive Speech
%A Charonnat, Laure
%A Vidal, Gaëlle
%A Boeffard, Olivier
%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 charonnat-etal-2008-automatic
%X In order to improve the flexibility and the precision of an automatic phone segmentation system for a type of expressive speech, the dubbing into French of fiction movies, we developed both the phonetic labeling process and the alignment process. The automatic labelling system relies on an automatic grapheme-to-phoneme conversion including all the variants of the phonetic chain and on HMM modeling. In this article, we will distinguish three sets of phone models: a set of context independent models, a set of left and right context dependant models and finally a mixing of the two that combines phone and triphone models according to the precision of alignment obtained for each phonetic broad-class. The three models are evaluated on a test corpus. On the one hand we notice a little decrease in the score of phonetic labelling mainly due to pauses insertions, but on the other hand the mixed set of models gives the best results for the score of precision of the alignment.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/596_paper.pdf
Markdown (Informal)
[Automatic Phone Segmentation of Expressive Speech](http://www.lrec-conf.org/proceedings/lrec2008/pdf/596_paper.pdf) (Charonnat et al., LREC 2008)
ACL
- Laure Charonnat, Gaëlle Vidal, and Olivier Boeffard. 2008. Automatic Phone Segmentation of Expressive Speech. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).