textless-lib: a Library for Textless Spoken Language Processing

Eugene Kharitonov; Jade Copet; Kushal Lakhotia; Tu Anh Nguyen; Paden Tomasello; Ann Lee; Ali Elkahky; Wei Ning Hsu; Abdelrahman Mohamed; Emmanuel Dupoux; Yossi Adi

textless-lib: a Library for Textless Spoken Language Processing

Eugene Kharitonov, Jade Copet, Kushal Lakhotia, Tu Anh Nguyen, Paden Tomasello, Ann Lee, Ali Elkahky, Wei Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux, Yossi Adi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research 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. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/.

Original language	English
Title of host publication	NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, Proceedings of the Demonstrations Session
Publisher	Association for Computational Linguistics (ACL)
Pages	1-9
Number of pages	9
ISBN (Electronic)	9781955917742
State	Published - 2022
Externally published	Yes
Event	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - Seattle, United States Duration: 10 Jul 2022 → 15 Jul 2022

Publication series

Name	NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session

Conference

Conference	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022
Country/Territory	United States
City	Seattle
Period	10/07/22 → 15/07/22

Bibliographical note

Publisher Copyright:
© 2022 Association for Computational Linguistics.

Cite this

Kharitonov, E., Copet, J., Lakhotia, K., Nguyen, T. A., Tomasello, P., Lee, A., Elkahky, A., Hsu, W. N., Mohamed, A., Dupoux, E., & Adi, Y. (2022). textless-lib: a Library for Textless Spoken Language Processing. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session (pp. 1-9). (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session). Association for Computational Linguistics (ACL).

Kharitonov, Eugene ; Copet, Jade ; Lakhotia, Kushal et al. / textless-lib : a Library for Textless Spoken Language Processing. NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session. Association for Computational Linguistics (ACL), 2022. pp. 1-9 (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session).

@inproceedings{050fe862f9614614896c2f1265f1d0d4,

title = "textless-lib: a Library for Textless Spoken Language Processing",

abstract = "Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research 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. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/.",

author = "Eugene Kharitonov and Jade Copet and Kushal Lakhotia and Nguyen, {Tu Anh} and Paden Tomasello and Ann Lee and Ali Elkahky and Hsu, {Wei Ning} and Abdelrahman Mohamed and Emmanuel Dupoux and Yossi Adi",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 ; Conference date: 10-07-2022 Through 15-07-2022",

year = "2022",

language = "אנגלית",

series = "NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1--9",

booktitle = "NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics",

address = "ארצות הברית",

}

Kharitonov, E, Copet, J, Lakhotia, K, Nguyen, TA, Tomasello, P, Lee, A, Elkahky, A, Hsu, WN, Mohamed, A, Dupoux, E & Adi, Y 2022, textless-lib: a Library for Textless Spoken Language Processing. in NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session. NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session, Association for Computational Linguistics (ACL), pp. 1-9, 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, United States, 10/07/22.

textless-lib: a Library for Textless Spoken Language Processing. / Kharitonov, Eugene; Copet, Jade; Lakhotia, Kushal et al.
NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session. Association for Computational Linguistics (ACL), 2022. p. 1-9 (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - textless-lib

T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022

AU - Kharitonov, Eugene

AU - Copet, Jade

AU - Lakhotia, Kushal

AU - Nguyen, Tu Anh

AU - Tomasello, Paden

AU - Lee, Ann

AU - Elkahky, Ali

AU - Hsu, Wei Ning

AU - Mohamed, Abdelrahman

AU - Dupoux, Emmanuel

AU - Adi, Yossi

PY - 2022

Y1 - 2022

N2 - Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research 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. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/.

AB - Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research 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. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/.

UR - http://www.scopus.com/inward/record.url?scp=85137579750&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85137579750

T3 - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session

SP - 1

EP - 9

BT - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

Y2 - 10 July 2022 through 15 July 2022

ER -

Kharitonov E, Copet J, Lakhotia K, Nguyen TA, Tomasello P, Lee A et al. textless-lib: a Library for Textless Spoken Language Processing. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session. Association for Computational Linguistics (ACL). 2022. p. 1-9. (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session).

textless-lib: a Library for Textless Spoken Language Processing

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this