@inproceedings{ruggiero-etal-2024-enhancing,
title = "Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion",
author = "Ruggiero, Giuseppe and
Testa, Matteo and
Walle, Jurgen Van De and
Di Caro, Luigi",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.122/",
doi = "10.18653/v1/2024.findings-emnlp.122",
pages = "2237--2246",
abstract = "The creation of artificial polyglot voices remains a challenging task, despite considerable progress in recent years. This paper investigates self-supervised learning for voice conversion to create native-sounding polyglot voices. We introduce a novel cross-lingual any-to-one voice conversion system that is able to preserve the source accent without the need for multilingual data from the target speaker. In addition, we show a novel cross-lingual fine-tuning strategy that further improves the accent and reduces the training data requirements. Objective and subjective evaluations with English, Spanish, French and Mandarin Chinese confirm that our approach improves on state-of-the-art methods, enhancing the speech intelligibility and overall quality of the converted speech, especially in cross-lingual scenarios. Audio samples are available at: https://giuseppe-ruggiero.github.io/a2o-vc-demo/"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruggiero-etal-2024-enhancing">
<titleInfo>
<title>Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Ruggiero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Testa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jurgen</namePart>
<namePart type="given">Van</namePart>
<namePart type="given">De</namePart>
<namePart type="family">Walle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luigi</namePart>
<namePart type="family">Di Caro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The creation of artificial polyglot voices remains a challenging task, despite considerable progress in recent years. This paper investigates self-supervised learning for voice conversion to create native-sounding polyglot voices. We introduce a novel cross-lingual any-to-one voice conversion system that is able to preserve the source accent without the need for multilingual data from the target speaker. In addition, we show a novel cross-lingual fine-tuning strategy that further improves the accent and reduces the training data requirements. Objective and subjective evaluations with English, Spanish, French and Mandarin Chinese confirm that our approach improves on state-of-the-art methods, enhancing the speech intelligibility and overall quality of the converted speech, especially in cross-lingual scenarios. Audio samples are available at: https://giuseppe-ruggiero.github.io/a2o-vc-demo/</abstract>
<identifier type="citekey">ruggiero-etal-2024-enhancing</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.122</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.122/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2237</start>
<end>2246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion
%A Ruggiero, Giuseppe
%A Testa, Matteo
%A Walle, Jurgen Van De
%A Di Caro, Luigi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F ruggiero-etal-2024-enhancing
%X The creation of artificial polyglot voices remains a challenging task, despite considerable progress in recent years. This paper investigates self-supervised learning for voice conversion to create native-sounding polyglot voices. We introduce a novel cross-lingual any-to-one voice conversion system that is able to preserve the source accent without the need for multilingual data from the target speaker. In addition, we show a novel cross-lingual fine-tuning strategy that further improves the accent and reduces the training data requirements. Objective and subjective evaluations with English, Spanish, French and Mandarin Chinese confirm that our approach improves on state-of-the-art methods, enhancing the speech intelligibility and overall quality of the converted speech, especially in cross-lingual scenarios. Audio samples are available at: https://giuseppe-ruggiero.github.io/a2o-vc-demo/
%R 10.18653/v1/2024.findings-emnlp.122
%U https://aclanthology.org/2024.findings-emnlp.122/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.122
%P 2237-2246
Markdown (Informal)
[Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion](https://aclanthology.org/2024.findings-emnlp.122/) (Ruggiero et al., Findings 2024)
ACL