Speech-in-speech recognition is modulated by familiarity to dialect

Jessica L.L. Chin; Elena Talevska; Mark Antoniou

doi:10.21437/Interspeech.2023-1196

Speech-in-speech recognition is modulated by familiarity to dialect

Jessica L.L. Chin, Elena Talevska, Mark Antoniou

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

1 Citation (Scopus)

Abstract

Listening to speech in competing background speech can be difficult due to elements such as the linguistic content of the signal. Linguistic release from masking occurs when altering the masker language results in less interference in speech recognition. The greater the linguistic differences between the target and masker, the higher the speech recognition accuracy. However, for dialectal variations of the same language, these patterns are less consistent. This study examined speech-in-speech recognition in Australian English monolinguals when the target speech was in either Australian (AU) or American English, and when the masker speech was in either of the dialects or a foreign language (Swedish). Speech recognition performance was greatest when AU was the target and poorest when AU was the masker. There were fewer differences in performance between the Swedish and dialect maskers. Results indicate that speech recognition is modulated by a listener's familiarity to a dialect.

Original language	English
Title of host publication	Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023
Subtitle of host publication	Inclusive Spoken Language Science and Technology - Breaking Down Barriers
Editors	Naomi Harte, Julie Carson-Berndsen, Gareth Jones
Place of Publication	Dublin, Ireland
Pages	3113-3116
Number of pages	4
DOIs	https://doi.org/10.21437/Interspeech.2023-1196
Publication status	Published - 2023
Event	24th International Speech Communication Association, Interspeech 2023 - Dublin, Ireland Duration: 20 Aug 2023 → 24 Aug 2023

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISSN (Print)	2308-457X

Conference

Conference	24th International Speech Communication Association, Interspeech 2023
Country/Territory	Ireland
City	Dublin
Period	20/08/23 → 24/08/23

Bibliographical note

Publisher Copyright:
© 2023 International Speech Communication Association. All rights reserved.

Keywords

dialect variation
familiarity to dialect
foreign language
speech-in-speech recognition
target-masker similarity

Access to Document

10.21437/Interspeech.2023-1196

full textFinal published version, 238 KB

Cite this

Chin, J. L. L., Talevska, E., & Antoniou, M. (2023). Speech-in-speech recognition is modulated by familiarity to dialect. In N. Harte, J. Carson-Berndsen, & G. Jones (Eds.), Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023: Inclusive Spoken Language Science and Technology - Breaking Down Barriers (pp. 3113-3116). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).. https://doi.org/10.21437/Interspeech.2023-1196

Chin, Jessica L.L. ; Talevska, Elena ; Antoniou, Mark. / Speech-in-speech recognition is modulated by familiarity to dialect. Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023: Inclusive Spoken Language Science and Technology - Breaking Down Barriers. editor / Naomi Harte ; Julie Carson-Berndsen ; Gareth Jones. Dublin, Ireland, 2023. pp. 3113-3116 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{9f265151a04149ceacb5a71ce6e4c302,

title = "Speech-in-speech recognition is modulated by familiarity to dialect",

abstract = "Listening to speech in competing background speech can be difficult due to elements such as the linguistic content of the signal. Linguistic release from masking occurs when altering the masker language results in less interference in speech recognition. The greater the linguistic differences between the target and masker, the higher the speech recognition accuracy. However, for dialectal variations of the same language, these patterns are less consistent. This study examined speech-in-speech recognition in Australian English monolinguals when the target speech was in either Australian (AU) or American English, and when the masker speech was in either of the dialects or a foreign language (Swedish). Speech recognition performance was greatest when AU was the target and poorest when AU was the masker. There were fewer differences in performance between the Swedish and dialect maskers. Results indicate that speech recognition is modulated by a listener's familiarity to a dialect.",

keywords = "dialect variation, familiarity to dialect, foreign language, speech-in-speech recognition, target-masker similarity",

author = "Chin, {Jessica L.L.} and Elena Talevska and Mark Antoniou",

note = "Publisher Copyright: {\textcopyright} 2023 International Speech Communication Association. All rights reserved.; 24th International Speech Communication Association, Interspeech 2023 ; Conference date: 20-08-2023 Through 24-08-2023",

year = "2023",

doi = "10.21437/Interspeech.2023-1196",

language = "English",

series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

pages = "3113--3116",

editor = "Naomi Harte and Julie Carson-Berndsen and Gareth Jones",

booktitle = "Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023",

}

Chin, JLL, Talevska, E & Antoniou, M 2023, Speech-in-speech recognition is modulated by familiarity to dialect. in N Harte, J Carson-Berndsen & G Jones (eds), Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023: Inclusive Spoken Language Science and Technology - Breaking Down Barriers. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Dublin, Ireland, pp. 3113-3116, 24th International Speech Communication Association, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1196

Speech-in-speech recognition is modulated by familiarity to dialect. / Chin, Jessica L.L.; Talevska, Elena; Antoniou, Mark.
Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023: Inclusive Spoken Language Science and Technology - Breaking Down Barriers. ed. / Naomi Harte; Julie Carson-Berndsen; Gareth Jones. Dublin, Ireland, 2023. p. 3113-3116 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Speech-in-speech recognition is modulated by familiarity to dialect

AU - Chin, Jessica L.L.

AU - Talevska, Elena

AU - Antoniou, Mark

PY - 2023

Y1 - 2023

N2 - Listening to speech in competing background speech can be difficult due to elements such as the linguistic content of the signal. Linguistic release from masking occurs when altering the masker language results in less interference in speech recognition. The greater the linguistic differences between the target and masker, the higher the speech recognition accuracy. However, for dialectal variations of the same language, these patterns are less consistent. This study examined speech-in-speech recognition in Australian English monolinguals when the target speech was in either Australian (AU) or American English, and when the masker speech was in either of the dialects or a foreign language (Swedish). Speech recognition performance was greatest when AU was the target and poorest when AU was the masker. There were fewer differences in performance between the Swedish and dialect maskers. Results indicate that speech recognition is modulated by a listener's familiarity to a dialect.

AB - Listening to speech in competing background speech can be difficult due to elements such as the linguistic content of the signal. Linguistic release from masking occurs when altering the masker language results in less interference in speech recognition. The greater the linguistic differences between the target and masker, the higher the speech recognition accuracy. However, for dialectal variations of the same language, these patterns are less consistent. This study examined speech-in-speech recognition in Australian English monolinguals when the target speech was in either Australian (AU) or American English, and when the masker speech was in either of the dialects or a foreign language (Swedish). Speech recognition performance was greatest when AU was the target and poorest when AU was the masker. There were fewer differences in performance between the Swedish and dialect maskers. Results indicate that speech recognition is modulated by a listener's familiarity to a dialect.

KW - dialect variation

KW - familiarity to dialect

KW - foreign language

KW - speech-in-speech recognition

KW - target-masker similarity

UR - http://www.scopus.com/inward/record.url?scp=85171586581&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2023-1196

DO - 10.21437/Interspeech.2023-1196

M3 - Conference Paper

AN - SCOPUS:85171586581

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 3113

EP - 3116

BT - Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023

A2 - Harte, Naomi

A2 - Carson-Berndsen, Julie

A2 - Jones, Gareth

CY - Dublin, Ireland

T2 - 24th International Speech Communication Association, Interspeech 2023

Y2 - 20 August 2023 through 24 August 2023

ER -

Chin JLL, Talevska E, Antoniou M. Speech-in-speech recognition is modulated by familiarity to dialect. In Harte N, Carson-Berndsen J, Jones G, editors, Proceedings of INTERSPEECH 2023, Dublin, Ireland, 20-24 August 2023: Inclusive Spoken Language Science and Technology - Breaking Down Barriers. Dublin, Ireland. 2023. p. 3113-3116. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2023-1196

Speech-in-speech recognition is modulated by familiarity to dialect

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this