@inproceedings{boeffard-etal-2012-towards,
title = "Towards Fully Automatic Annotation of Audio Books for {TTS}",
author = "Boeffard, Olivier and
Charonnat, Laure and
Maguer, S{\'e}bastien Le and
Lolive, Damien",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/632_Paper.pdf",
pages = "975--980",
abstract = "Building speech corpora is a first and crucial step for every text-to-speech synthesis system. Nowadays, the use of statistical models implies the use of huge sized corpora that need to be recorded, transcribed, annotated and segmented to be usable. The variety of corpora necessary for recent applications (content, style, etc.) makes the use of existing digital audio resources very attractive. Among all available resources, audiobooks, considering their quality, are interesting. Considering this framework, we propose a complete acquisition, segmentation and annotation chain for audiobooks that tends to be fully automatic. The proposed process relies on a data structure, Roots, that establishes the relations between the different annotation levels represented as sequences of items. This methodology has been applied successfully on 11 hours of speech extracted from an audiobook. A manual check, on a part of the corpus, shows the efficiency of the process.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boeffard-etal-2012-towards">
<titleInfo>
<title>Towards Fully Automatic Annotation of Audio Books for TTS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Boeffard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Sébastien</namePart>
<namePart type="given">Le</namePart>
<namePart type="family">Maguer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Lolive</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building speech corpora is a first and crucial step for every text-to-speech synthesis system. Nowadays, the use of statistical models implies the use of huge sized corpora that need to be recorded, transcribed, annotated and segmented to be usable. The variety of corpora necessary for recent applications (content, style, etc.) makes the use of existing digital audio resources very attractive. Among all available resources, audiobooks, considering their quality, are interesting. Considering this framework, we propose a complete acquisition, segmentation and annotation chain for audiobooks that tends to be fully automatic. The proposed process relies on a data structure, Roots, that establishes the relations between the different annotation levels represented as sequences of items. This methodology has been applied successfully on 11 hours of speech extracted from an audiobook. A manual check, on a part of the corpus, shows the efficiency of the process.</abstract>
<identifier type="citekey">boeffard-etal-2012-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/632_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>975</start>
<end>980</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Fully Automatic Annotation of Audio Books for TTS
%A Boeffard, Olivier
%A Charonnat, Laure
%A Maguer, Sébastien Le
%A Lolive, Damien
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F boeffard-etal-2012-towards
%X Building speech corpora is a first and crucial step for every text-to-speech synthesis system. Nowadays, the use of statistical models implies the use of huge sized corpora that need to be recorded, transcribed, annotated and segmented to be usable. The variety of corpora necessary for recent applications (content, style, etc.) makes the use of existing digital audio resources very attractive. Among all available resources, audiobooks, considering their quality, are interesting. Considering this framework, we propose a complete acquisition, segmentation and annotation chain for audiobooks that tends to be fully automatic. The proposed process relies on a data structure, Roots, that establishes the relations between the different annotation levels represented as sequences of items. This methodology has been applied successfully on 11 hours of speech extracted from an audiobook. A manual check, on a part of the corpus, shows the efficiency of the process.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/632_Paper.pdf
%P 975-980
Markdown (Informal)
[Towards Fully Automatic Annotation of Audio Books for TTS](http://www.lrec-conf.org/proceedings/lrec2012/pdf/632_Paper.pdf) (Boeffard et al., LREC 2012)
ACL
- Olivier Boeffard, Laure Charonnat, Sébastien Le Maguer, and Damien Lolive. 2012. Towards Fully Automatic Annotation of Audio Books for TTS. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 975–980, Istanbul, Turkey. European Language Resources Association (ELRA).