@inproceedings{breuer-etal-2006-set,
title = "Set-up of a Unit-Selection Synthesis with a Prominent Voice",
author = {Breuer, Stefan and
Bergmann, Sven and
Dragon, Ralf and
M{\"o}ller, Sebastian},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/307_pdf.pdf",
abstract = "In this paper, we describe the set-up process and an initial evaluation of a unit-selection speech synthesizer. The synthesizer is specific in that it is intended to speak with a prominent voice. As a consequence, only very limited resources were available for setting up the unit database. These resources have been extracted from an audio book, segmented with the help of an HMM-based wrapper, and then used with the non-uniform unit-selection approach implemented in the Bonn Open Synthesis System (BOSS). In order to adapt the database to the BOSS implementation, the label files were amended by phrase boundaries, converted to XML, amended by prosodic and spectral information, and then further converted to a MySQL relational database structure. The BOSS system selects units on the basis of this information, adding individual unit costs to the concatenation costs given by MFCC and F0 distances. The paper discusses the problems which occurred during the database set-up, the invested effort, as well as the quality level which can be reached by this approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="breuer-etal-2006-set">
<titleInfo>
<title>Set-up of a Unit-Selection Synthesis with a Prominent Voice</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Breuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Bergmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Dragon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe the set-up process and an initial evaluation of a unit-selection speech synthesizer. The synthesizer is specific in that it is intended to speak with a prominent voice. As a consequence, only very limited resources were available for setting up the unit database. These resources have been extracted from an audio book, segmented with the help of an HMM-based wrapper, and then used with the non-uniform unit-selection approach implemented in the Bonn Open Synthesis System (BOSS). In order to adapt the database to the BOSS implementation, the label files were amended by phrase boundaries, converted to XML, amended by prosodic and spectral information, and then further converted to a MySQL relational database structure. The BOSS system selects units on the basis of this information, adding individual unit costs to the concatenation costs given by MFCC and F0 distances. The paper discusses the problems which occurred during the database set-up, the invested effort, as well as the quality level which can be reached by this approach.</abstract>
<identifier type="citekey">breuer-etal-2006-set</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/307_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Set-up of a Unit-Selection Synthesis with a Prominent Voice
%A Breuer, Stefan
%A Bergmann, Sven
%A Dragon, Ralf
%A Möller, Sebastian
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F breuer-etal-2006-set
%X In this paper, we describe the set-up process and an initial evaluation of a unit-selection speech synthesizer. The synthesizer is specific in that it is intended to speak with a prominent voice. As a consequence, only very limited resources were available for setting up the unit database. These resources have been extracted from an audio book, segmented with the help of an HMM-based wrapper, and then used with the non-uniform unit-selection approach implemented in the Bonn Open Synthesis System (BOSS). In order to adapt the database to the BOSS implementation, the label files were amended by phrase boundaries, converted to XML, amended by prosodic and spectral information, and then further converted to a MySQL relational database structure. The BOSS system selects units on the basis of this information, adding individual unit costs to the concatenation costs given by MFCC and F0 distances. The paper discusses the problems which occurred during the database set-up, the invested effort, as well as the quality level which can be reached by this approach.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/307_pdf.pdf
Markdown (Informal)
[Set-up of a Unit-Selection Synthesis with a Prominent Voice](http://www.lrec-conf.org/proceedings/lrec2006/pdf/307_pdf.pdf) (Breuer et al., LREC 2006)
ACL