@inproceedings{shamsi-2020-tts,
title = "{TTS} voice corpus reduction for audio-book generation",
author = "Shamsi, Meysam",
editor = "Benzitoun, Christophe and
Braud, Chlo{\'e} and
Huber, Laurine and
Langlois, David and
Ouni, Slim and
Pogodalla, Sylvain and
Schneider, St{\'e}phane",
booktitle = "Actes de la 6e conf{\'e}rence conjointe Journ{\'e}es d'{\'E}tudes sur la Parole (JEP, 33e {\'e}dition), Traitement Automatique des Langues Naturelles (TALN, 27e {\'e}dition), Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (R{\'E}CITAL, 22e {\'e}dition). Volume 3 : Rencontre des {\'E}tudiants Chercheurs en Informatique pour le TAL",
month = "6",
year = "2020",
address = "Nancy, France",
publisher = "ATALA et AFCP",
url = "https://aclanthology.org/2020.jeptalnrecital-recital.15",
pages = "193--204",
abstract = "Nowadays, with emerging new voice corpora, voice corpus reduction in expressive TTS becomes more important. In this study a spitting greedy approach is investigated to remove utterances. In the first step by comparing five objective measures, the TTS global cost has been found as the best available metric for approximation of perceptual quality. The greedy algorithm employs this measure to evaluate the candidates in each step and the synthetic quality resulted by its solution. It turned out that reducing voice corpus size until a certain length (1 hour in our experiment) could not degrade the synthetic quality. By modifying the original greedy algorithm, its computation time is reduced to a reasonable duration. Two perceptual tests have been run to compare this greedy method and the random strategy for voice corpus reduction. They revealed that there is no superiority of using the proposed greedy approach for corpus reduction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shamsi-2020-tts">
<titleInfo>
<title>TTS voice corpus reduction for audio-book generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meysam</namePart>
<namePart type="family">Shamsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Benzitoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurine</namePart>
<namePart type="family">Huber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Langlois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slim</namePart>
<namePart type="family">Ouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Pogodalla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stéphane</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA et AFCP</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Nowadays, with emerging new voice corpora, voice corpus reduction in expressive TTS becomes more important. In this study a spitting greedy approach is investigated to remove utterances. In the first step by comparing five objective measures, the TTS global cost has been found as the best available metric for approximation of perceptual quality. The greedy algorithm employs this measure to evaluate the candidates in each step and the synthetic quality resulted by its solution. It turned out that reducing voice corpus size until a certain length (1 hour in our experiment) could not degrade the synthetic quality. By modifying the original greedy algorithm, its computation time is reduced to a reasonable duration. Two perceptual tests have been run to compare this greedy method and the random strategy for voice corpus reduction. They revealed that there is no superiority of using the proposed greedy approach for corpus reduction.</abstract>
<identifier type="citekey">shamsi-2020-tts</identifier>
<location>
<url>https://aclanthology.org/2020.jeptalnrecital-recital.15</url>
</location>
<part>
<date>2020-6</date>
<extent unit="page">
<start>193</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TTS voice corpus reduction for audio-book generation
%A Shamsi, Meysam
%Y Benzitoun, Christophe
%Y Braud, Chloé
%Y Huber, Laurine
%Y Langlois, David
%Y Ouni, Slim
%Y Pogodalla, Sylvain
%Y Schneider, Stéphane
%S Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL
%D 2020
%8 June
%I ATALA et AFCP
%C Nancy, France
%F shamsi-2020-tts
%X Nowadays, with emerging new voice corpora, voice corpus reduction in expressive TTS becomes more important. In this study a spitting greedy approach is investigated to remove utterances. In the first step by comparing five objective measures, the TTS global cost has been found as the best available metric for approximation of perceptual quality. The greedy algorithm employs this measure to evaluate the candidates in each step and the synthetic quality resulted by its solution. It turned out that reducing voice corpus size until a certain length (1 hour in our experiment) could not degrade the synthetic quality. By modifying the original greedy algorithm, its computation time is reduced to a reasonable duration. Two perceptual tests have been run to compare this greedy method and the random strategy for voice corpus reduction. They revealed that there is no superiority of using the proposed greedy approach for corpus reduction.
%U https://aclanthology.org/2020.jeptalnrecital-recital.15
%P 193-204
Markdown (Informal)
[TTS voice corpus reduction for audio-book generation](https://aclanthology.org/2020.jeptalnrecital-recital.15) (Shamsi, JEP/TALN/RECITAL 2020)
ACL
- Meysam Shamsi. 2020. TTS voice corpus reduction for audio-book generation. In Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 3 : Rencontre des Étudiants Chercheurs en Informatique pour le TAL, pages 193–204, Nancy, France. ATALA et AFCP.