@inproceedings{ruiz-etal-2014-phoneme,
title = "Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling",
author = "Ruiz, Pablo and
{\'A}lvarez, Aitor and
Arzelus, Haritz",
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/387_Paper.pdf",
pages = "437--442",
abstract = "Long audio alignment systems for Spanish and English are presented, within an automatic subtitling application. Language-specific phone decoders automatically recognize audio contents at phoneme level. At the same time, language-dependent grapheme-to-phoneme modules perform a transcription of the script for the audio. A dynamic programming algorithm (Hirschberg{'}s algorithm) finds matches between the phonemes automatically recognized by the phone decoder and the phonemes in the scripts transcription. Alignment accuracy is evaluated when scoring alignment operations with a baseline binary matrix, and when scoring alignment operations with several continuous-score matrices, based on phoneme similarity as assessed through comparing multivalued phonological features. Alignment accuracy results are reported at phoneme, word and subtitle level. Alignment accuracy when using the continuous scoring matrices based on phonological similarity was clearly higher than when using the baseline binary matrix.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruiz-etal-2014-phoneme">
<titleInfo>
<title>Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Álvarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haritz</namePart>
<namePart type="family">Arzelus</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>Long audio alignment systems for Spanish and English are presented, within an automatic subtitling application. Language-specific phone decoders automatically recognize audio contents at phoneme level. At the same time, language-dependent grapheme-to-phoneme modules perform a transcription of the script for the audio. A dynamic programming algorithm (Hirschberg’s algorithm) finds matches between the phonemes automatically recognized by the phone decoder and the phonemes in the scripts transcription. Alignment accuracy is evaluated when scoring alignment operations with a baseline binary matrix, and when scoring alignment operations with several continuous-score matrices, based on phoneme similarity as assessed through comparing multivalued phonological features. Alignment accuracy results are reported at phoneme, word and subtitle level. Alignment accuracy when using the continuous scoring matrices based on phonological similarity was clearly higher than when using the baseline binary matrix.</abstract>
<identifier type="citekey">ruiz-etal-2014-phoneme</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/387_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>437</start>
<end>442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling
%A Ruiz, Pablo
%A Álvarez, Aitor
%A Arzelus, Haritz
%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 ruiz-etal-2014-phoneme
%X Long audio alignment systems for Spanish and English are presented, within an automatic subtitling application. Language-specific phone decoders automatically recognize audio contents at phoneme level. At the same time, language-dependent grapheme-to-phoneme modules perform a transcription of the script for the audio. A dynamic programming algorithm (Hirschberg’s algorithm) finds matches between the phonemes automatically recognized by the phone decoder and the phonemes in the scripts transcription. Alignment accuracy is evaluated when scoring alignment operations with a baseline binary matrix, and when scoring alignment operations with several continuous-score matrices, based on phoneme similarity as assessed through comparing multivalued phonological features. Alignment accuracy results are reported at phoneme, word and subtitle level. Alignment accuracy when using the continuous scoring matrices based on phonological similarity was clearly higher than when using the baseline binary matrix.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/387_Paper.pdf
%P 437-442
Markdown (Informal)
[Phoneme Similarity Matrices to Improve Long Audio Alignment for Automatic Subtitling](http://www.lrec-conf.org/proceedings/lrec2014/pdf/387_Paper.pdf) (Ruiz et al., LREC 2014)
ACL