@inproceedings{pine-etal-2022-requirements,
title = "Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization",
author = "Pine, Aidan and
Wells, Dan and
Brinklow, Nathan and
Littell, Patrick and
Richmond, Korin",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.507/",
doi = "10.18653/v1/2022.acl-long.507",
pages = "7346--7359",
abstract = "This paper describes the motivation and development of speech synthesis systems for the purposes of language revitalization. By building speech synthesis systems for three Indigenous languages spoken in Canada, Kanien`k{\'e}ha, Gitksan {\&} SEN{\'C}O{\={T}}EN, we re-evaluate the question of how much data is required to build low-resource speech synthesis systems featuring state-of-the-art neural models. For example, preliminary results with English data show that a FastSpeech2 model trained with 1 hour of training data can produce speech with comparable naturalness to a Tacotron2 model trained with 10 hours of data. Finally, we motivate future research in evaluation and classroom integration in the field of speech synthesis for language revitalization."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pine-etal-2022-requirements">
<titleInfo>
<title>Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aidan</namePart>
<namePart type="family">Pine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Wells</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Brinklow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Littell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Korin</namePart>
<namePart type="family">Richmond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the motivation and development of speech synthesis systems for the purposes of language revitalization. By building speech synthesis systems for three Indigenous languages spoken in Canada, Kanien‘kéha, Gitksan & SENĆO\=TEN, we re-evaluate the question of how much data is required to build low-resource speech synthesis systems featuring state-of-the-art neural models. For example, preliminary results with English data show that a FastSpeech2 model trained with 1 hour of training data can produce speech with comparable naturalness to a Tacotron2 model trained with 10 hours of data. Finally, we motivate future research in evaluation and classroom integration in the field of speech synthesis for language revitalization.</abstract>
<identifier type="citekey">pine-etal-2022-requirements</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.507</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.507/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>7346</start>
<end>7359</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization
%A Pine, Aidan
%A Wells, Dan
%A Brinklow, Nathan
%A Littell, Patrick
%A Richmond, Korin
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F pine-etal-2022-requirements
%X This paper describes the motivation and development of speech synthesis systems for the purposes of language revitalization. By building speech synthesis systems for three Indigenous languages spoken in Canada, Kanien‘kéha, Gitksan & SENĆO\=TEN, we re-evaluate the question of how much data is required to build low-resource speech synthesis systems featuring state-of-the-art neural models. For example, preliminary results with English data show that a FastSpeech2 model trained with 1 hour of training data can produce speech with comparable naturalness to a Tacotron2 model trained with 10 hours of data. Finally, we motivate future research in evaluation and classroom integration in the field of speech synthesis for language revitalization.
%R 10.18653/v1/2022.acl-long.507
%U https://aclanthology.org/2022.acl-long.507/
%U https://doi.org/10.18653/v1/2022.acl-long.507
%P 7346-7359
Markdown (Informal)
[Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization](https://aclanthology.org/2022.acl-long.507/) (Pine et al., ACL 2022)
ACL