@inproceedings{lanchantin-etal-2008-automatic,
title = "Automatic Phoneme Segmentation with Relaxed Textual Constraints",
author = "Lanchantin, Pierre and
Morris, Andrew C. and
Rodet, Xavier and
Veaux, Christophe",
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/606_paper.pdf",
abstract = "Speech synthesis by unit selection requires the segmentation of a large single speaker high quality recording. Automatic speech recognition techniques, e.g. Hidden Markov Models (HMM), can be optimised for maximum segmentation accuracy. This paper presents the results of tuning such a phoneme segmentation system. Firstly, using no text transcription, the design of an HMM phoneme recogniser is optimised subject to a phoneme bigram language model. Optimal performance is obtained with triphone models, 7 states per phoneme and 5 Gaussians per state, reaching 94.4{\%} phoneme recognition accuracy with 95.2{\%} of phoneme boundaries within 70 ms of hand labelled boundaries. Secondly, using the textual information modeled by a multi-pronunciation phonetic graph built according to errors found in the first step, the reported phoneme recognition accuracy increases to 96.8{\%} with 96.1{\%} of phoneme boundaries within 70 ms of hand labelled boundaries. Finally, the results from these two segmentation methods based on different phonetic graphs, the evaluation set, the hand labelling and the test procedures are discussed and possible improvements are proposed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lanchantin-etal-2008-automatic">
<titleInfo>
<title>Automatic Phoneme Segmentation with Relaxed Textual Constraints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Lanchantin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Morris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Rodet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Veaux</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>Speech synthesis by unit selection requires the segmentation of a large single speaker high quality recording. Automatic speech recognition techniques, e.g. Hidden Markov Models (HMM), can be optimised for maximum segmentation accuracy. This paper presents the results of tuning such a phoneme segmentation system. Firstly, using no text transcription, the design of an HMM phoneme recogniser is optimised subject to a phoneme bigram language model. Optimal performance is obtained with triphone models, 7 states per phoneme and 5 Gaussians per state, reaching 94.4% phoneme recognition accuracy with 95.2% of phoneme boundaries within 70 ms of hand labelled boundaries. Secondly, using the textual information modeled by a multi-pronunciation phonetic graph built according to errors found in the first step, the reported phoneme recognition accuracy increases to 96.8% with 96.1% of phoneme boundaries within 70 ms of hand labelled boundaries. Finally, the results from these two segmentation methods based on different phonetic graphs, the evaluation set, the hand labelling and the test procedures are discussed and possible improvements are proposed.</abstract>
<identifier type="citekey">lanchantin-etal-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/606_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Phoneme Segmentation with Relaxed Textual Constraints
%A Lanchantin, Pierre
%A Morris, Andrew C.
%A Rodet, Xavier
%A Veaux, Christophe
%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 lanchantin-etal-2008-automatic
%X Speech synthesis by unit selection requires the segmentation of a large single speaker high quality recording. Automatic speech recognition techniques, e.g. Hidden Markov Models (HMM), can be optimised for maximum segmentation accuracy. This paper presents the results of tuning such a phoneme segmentation system. Firstly, using no text transcription, the design of an HMM phoneme recogniser is optimised subject to a phoneme bigram language model. Optimal performance is obtained with triphone models, 7 states per phoneme and 5 Gaussians per state, reaching 94.4% phoneme recognition accuracy with 95.2% of phoneme boundaries within 70 ms of hand labelled boundaries. Secondly, using the textual information modeled by a multi-pronunciation phonetic graph built according to errors found in the first step, the reported phoneme recognition accuracy increases to 96.8% with 96.1% of phoneme boundaries within 70 ms of hand labelled boundaries. Finally, the results from these two segmentation methods based on different phonetic graphs, the evaluation set, the hand labelling and the test procedures are discussed and possible improvements are proposed.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/606_paper.pdf
Markdown (Informal)
[Automatic Phoneme Segmentation with Relaxed Textual Constraints](http://www.lrec-conf.org/proceedings/lrec2008/pdf/606_paper.pdf) (Lanchantin et al., LREC 2008)
ACL