Massively multilingual adversarial speech recognition

Oliver Adams; Matthew Wiesner; Shinji Watanabe; David Yarowsky

Massively multilingual adversarial speech recognition

Oliver Adams, Matthew Wiesner, Shinji Watanabe, David Yarowsky

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

Abstract

We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective.

Original language	English
Title of host publication	Long and Short Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	96-108
Number of pages	13
ISBN (Electronic)	9781950737130
Publication status	Published - 2019
Externally published	Yes
Event	2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 - Minneapolis, United States Duration: 2019 Jun 2 → 2019 Jun 7

Publication series

Name	NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume	1

Conference

Conference	2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Country/Territory	United States
City	Minneapolis
Period	19/6/2 → 19/6/7

ASJC Scopus subject areas

Language and Linguistics
Computer Science Applications
Linguistics and Language

Cite this

Adams, O., Wiesner, M., Watanabe, S., & Yarowsky, D. (2019). Massively multilingual adversarial speech recognition. In Long and Short Papers (pp. 96-108). (NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; Vol. 1). Association for Computational Linguistics (ACL).

Massively multilingual adversarial speech recognition. / Adams, Oliver; Wiesner, Matthew; Watanabe, Shinji et al.
Long and Short Papers. Association for Computational Linguistics (ACL), 2019. p. 96-108 (NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; Vol. 1).

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

Adams, O, Wiesner, M, Watanabe, S & Yarowsky, D 2019, Massively multilingual adversarial speech recognition. in Long and Short Papers. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 1, Association for Computational Linguistics (ACL), pp. 96-108, 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019, Minneapolis, United States, 19/6/2.

Adams, Oliver ; Wiesner, Matthew ; Watanabe, Shinji et al. / Massively multilingual adversarial speech recognition. Long and Short Papers. Association for Computational Linguistics (ACL), 2019. pp. 96-108 (NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference).

@inproceedings{ad5a79ea8ed44f0b8a56245ca56138fd,

title = "Massively multilingual adversarial speech recognition",

abstract = "We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective.",

author = "Oliver Adams and Matthew Wiesner and Shinji Watanabe and David Yarowsky",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 ; Conference date: 02-06-2019 Through 07-06-2019",

year = "2019",

language = "English",

series = "NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",

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

pages = "96--108",

booktitle = "Long and Short Papers",

}

TY - GEN

T1 - Massively multilingual adversarial speech recognition

AU - Adams, Oliver

AU - Wiesner, Matthew

AU - Watanabe, Shinji

AU - Yarowsky, David

PY - 2019

Y1 - 2019

N2 - We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective.

AB - We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical location, and orthography. In this context, experiments demonstrate the effectiveness of two additional pretraining objectives in encouraging language-independent encoder representations: a context-independent phoneme objective paired with a language-adversarial classification objective.

UR - http://www.scopus.com/inward/record.url?scp=85074710896&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074710896&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85074710896

T3 - NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

SP - 96

EP - 108

BT - Long and Short Papers

PB - Association for Computational Linguistics (ACL)

T2 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019

Y2 - 2 June 2019 through 7 June 2019

ER -

Massively multilingual adversarial speech recognition

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this