@inproceedings{sini-etal-2022-investigating,
title = "Investigating Inter- and Intra-speaker Voice Conversion using Audiobooks",
author = "Sini, Aghilas and
Lolive, Damien and
Barbot, Nelly and
Alain, Pierre",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.794/",
pages = "7305--7313",
abstract = "Audiobook readers play with their voices to emphasize some text passages, highlight discourse changes or significant events, or in order to make listening easier and entertaining. A dialog is a central passage in audiobooks where the reader applies significant voice transformation, mainly prosodic modifications, to realize character properties and changes. However, these intra-speaker modifications are hard to reproduce with simple text-to-speech synthesis. The manner of vocalizing characters involved in a given story depends on the text style and differs from one speaker to another. In this work, this problem is investigated through the prism of voice conversion. We propose to explore modifying the narrator`s voice to fit the context of the story, such as the character who is speaking, using voice conversion. To this end, two complementary experiments are designed: the first one aims to assess the quality of our Phonetic PosteriorGrams (PPG)-based voice conversion system using parallel data. Subjective evaluations with naive raters are conducted to estimate the quality of the signal generated and the speaker similarity. The second experiment applies an intra-speaker voice conversion, considering narration passages and direct speech passages as two distinct speakers. Data are then nonparallel and the dissimilarity between character and narrator is subjectively measured."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sini-etal-2022-investigating">
<titleInfo>
<title>Investigating Inter- and Intra-speaker Voice Conversion using Audiobooks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aghilas</namePart>
<namePart type="family">Sini</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>
<name type="personal">
<namePart type="given">Nelly</namePart>
<namePart type="family">Barbot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Alain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Audiobook readers play with their voices to emphasize some text passages, highlight discourse changes or significant events, or in order to make listening easier and entertaining. A dialog is a central passage in audiobooks where the reader applies significant voice transformation, mainly prosodic modifications, to realize character properties and changes. However, these intra-speaker modifications are hard to reproduce with simple text-to-speech synthesis. The manner of vocalizing characters involved in a given story depends on the text style and differs from one speaker to another. In this work, this problem is investigated through the prism of voice conversion. We propose to explore modifying the narrator‘s voice to fit the context of the story, such as the character who is speaking, using voice conversion. To this end, two complementary experiments are designed: the first one aims to assess the quality of our Phonetic PosteriorGrams (PPG)-based voice conversion system using parallel data. Subjective evaluations with naive raters are conducted to estimate the quality of the signal generated and the speaker similarity. The second experiment applies an intra-speaker voice conversion, considering narration passages and direct speech passages as two distinct speakers. Data are then nonparallel and the dissimilarity between character and narrator is subjectively measured.</abstract>
<identifier type="citekey">sini-etal-2022-investigating</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.794/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7305</start>
<end>7313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Inter- and Intra-speaker Voice Conversion using Audiobooks
%A Sini, Aghilas
%A Lolive, Damien
%A Barbot, Nelly
%A Alain, Pierre
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F sini-etal-2022-investigating
%X Audiobook readers play with their voices to emphasize some text passages, highlight discourse changes or significant events, or in order to make listening easier and entertaining. A dialog is a central passage in audiobooks where the reader applies significant voice transformation, mainly prosodic modifications, to realize character properties and changes. However, these intra-speaker modifications are hard to reproduce with simple text-to-speech synthesis. The manner of vocalizing characters involved in a given story depends on the text style and differs from one speaker to another. In this work, this problem is investigated through the prism of voice conversion. We propose to explore modifying the narrator‘s voice to fit the context of the story, such as the character who is speaking, using voice conversion. To this end, two complementary experiments are designed: the first one aims to assess the quality of our Phonetic PosteriorGrams (PPG)-based voice conversion system using parallel data. Subjective evaluations with naive raters are conducted to estimate the quality of the signal generated and the speaker similarity. The second experiment applies an intra-speaker voice conversion, considering narration passages and direct speech passages as two distinct speakers. Data are then nonparallel and the dissimilarity between character and narrator is subjectively measured.
%U https://aclanthology.org/2022.lrec-1.794/
%P 7305-7313
Markdown (Informal)
[Investigating Inter- and Intra-speaker Voice Conversion using Audiobooks](https://aclanthology.org/2022.lrec-1.794/) (Sini et al., LREC 2022)
ACL