@inproceedings{kharitonov-etal-2022-textless,
title = "textless-lib: a Library for Textless Spoken Language Processing",
author = "Kharitonov, Eugene and
Copet, Jade and
Lakhotia, Kushal and
Nguyen, Tu Anh and
Tomasello, Paden and
Lee, Ann and
Elkahky, Ali and
Hsu, Wei-Ning and
Mohamed, Abdelrahman and
Dupoux, Emmanuel and
Adi, Yossi",
editor = "Hajishirzi, Hannaneh and
Ning, Qiang and
Sil, Avi",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-demo.1/",
doi = "10.18653/v1/2022.naacl-demo.1",
pages = "1--9",
abstract = "Textless spoken language processing is an exciting area of research that promises to extend applicability of the standard NLP toolset onto spoken language and languages with few or no textual resources. Here, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in the area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kharitonov-etal-2022-textless">
<titleInfo>
<title>textless-lib: a Library for Textless Spoken Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Kharitonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Copet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Lakhotia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tu</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paden</namePart>
<namePart type="family">Tomasello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Elkahky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Ning</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Dupoux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yossi</namePart>
<namePart type="family">Adi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Textless spoken language processing is an exciting area of research that promises to extend applicability of the standard NLP toolset onto spoken language and languages with few or no textual resources. Here, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in the area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large.</abstract>
<identifier type="citekey">kharitonov-etal-2022-textless</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-demo.1</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-demo.1/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T textless-lib: a Library for Textless Spoken Language Processing
%A Kharitonov, Eugene
%A Copet, Jade
%A Lakhotia, Kushal
%A Nguyen, Tu Anh
%A Tomasello, Paden
%A Lee, Ann
%A Elkahky, Ali
%A Hsu, Wei-Ning
%A Mohamed, Abdelrahman
%A Dupoux, Emmanuel
%A Adi, Yossi
%Y Hajishirzi, Hannaneh
%Y Ning, Qiang
%Y Sil, Avi
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F kharitonov-etal-2022-textless
%X Textless spoken language processing is an exciting area of research that promises to extend applicability of the standard NLP toolset onto spoken language and languages with few or no textual resources. Here, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in the area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large.
%R 10.18653/v1/2022.naacl-demo.1
%U https://aclanthology.org/2022.naacl-demo.1/
%U https://doi.org/10.18653/v1/2022.naacl-demo.1
%P 1-9
Markdown (Informal)
[textless-lib: a Library for Textless Spoken Language Processing](https://aclanthology.org/2022.naacl-demo.1/) (Kharitonov et al., NAACL 2022)
ACL
- Eugene Kharitonov, Jade Copet, Kushal Lakhotia, Tu Anh Nguyen, Paden Tomasello, Ann Lee, Ali Elkahky, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux, and Yossi Adi. 2022. textless-lib: a Library for Textless Spoken Language Processing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations, pages 1–9, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.