Optimizing an automatic creaky voice detection method for Australian English-speaking females

Hannah White; Joshua Penney; Andy Gibson; Anita Szakay; Felicity Cox

doi:10.21437/Interspeech.2021-711

Optimizing an automatic creaky voice detection method for Australian English-speaking females

Hannah White, Joshua Penney, Andy Gibson, Anita Szakay, Felicity Cox

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

3 Citations (Scopus)

Abstract

Creaky voice is a nonmodal phonation type that has various linguistic and sociolinguistic functions. Manually annotating creaky voice for phonetic analysis is time-consuming and labor-intensive. In recent years, automatic tools for detecting creaky voice have been proposed, which present the possibility for easier, faster and more consistent creak identification. One of these proposed tools is a Creak Detector algorithm that uses an automatic neural network taking its input from several acoustic cues to identify creaky voice. Previous work has suggested that the creak probability threshold at which this tool determines an instance to be creaky may vary depending on the speaker population. The present study investigates the optimal creak detection threshold for female Australian English speakers.

Results show further support for the practice of first finding the optimal threshold when using the Creak Detection algorithm on new data sets. Additionally, results show that accuracy of creaky voice detection using the Creak Detection algorithm can be significantly improved by excluding non-sonorant data.

Original language	English
Title of host publication	INTERSPEECH 2021
Subtitle of host publication	Proceedings of the 22nd Annual Conference of the International Speech Communication Association
Place of Publication	Baixas, France
Publisher	International Speech Communication Association (ISCA)
Pages	1384-1388
Number of pages	5
ISBN (Electronic)	9781713836902
DOIs	https://doi.org/10.21437/Interspeech.2021-711
Publication status	Published - 2021
Event	INTERSPEECH (22nd : 2021) - Brno, Czech Republic Duration: 30 Aug 2021 → 3 Sept 2021

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	6
ISSN (Print)	2308-457X
ISSN (Electronic)	1990-9772

Conference

Conference	INTERSPEECH (22nd : 2021)
Country/Territory	Czech Republic
City	Brno
Period	30/08/21 → 3/09/21

Keywords

creaky voice
creak detection
automatic methods
Australian English

Access to Document

10.21437/Interspeech.2021-711Licence: Unspecified

Cite this

White, H., Penney, J., Gibson, A., Szakay, A., & Cox, F. (2021). Optimizing an automatic creaky voice detection method for Australian English-speaking females. In INTERSPEECH 2021: Proceedings of the 22nd Annual Conference of the International Speech Communication Association (pp. 1384-1388). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 6). International Speech Communication Association (ISCA). https://doi.org/10.21437/Interspeech.2021-711

White, Hannah ; Penney, Joshua ; Gibson, Andy et al. / Optimizing an automatic creaky voice detection method for Australian English-speaking females. INTERSPEECH 2021: Proceedings of the 22nd Annual Conference of the International Speech Communication Association. Baixas, France : International Speech Communication Association (ISCA), 2021. pp. 1384-1388 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{d6e15b5c400d497bacef7082220fe468,

title = "Optimizing an automatic creaky voice detection method for Australian English-speaking females",

abstract = "Creaky voice is a nonmodal phonation type that has various linguistic and sociolinguistic functions. Manually annotating creaky voice for phonetic analysis is time-consuming and labor-intensive. In recent years, automatic tools for detecting creaky voice have been proposed, which present the possibility for easier, faster and more consistent creak identification. One of these proposed tools is a Creak Detector algorithm that uses an automatic neural network taking its input from several acoustic cues to identify creaky voice. Previous work has suggested that the creak probability threshold at which this tool determines an instance to be creaky may vary depending on the speaker population. The present study investigates the optimal creak detection threshold for female Australian English speakers.Results show further support for the practice of first finding the optimal threshold when using the Creak Detection algorithm on new data sets. Additionally, results show that accuracy of creaky voice detection using the Creak Detection algorithm can be significantly improved by excluding non-sonorant data.",

keywords = "creaky voice, creak detection, automatic methods, Australian English",

author = "Hannah White and Joshua Penney and Andy Gibson and Anita Szakay and Felicity Cox",

year = "2021",

doi = "10.21437/Interspeech.2021-711",

language = "English",

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

publisher = "International Speech Communication Association (ISCA)",

pages = "1384--1388",

booktitle = "INTERSPEECH 2021",

note = "INTERSPEECH (22nd : 2021) ; Conference date: 30-08-2021 Through 03-09-2021",

}

White, H, Penney, J, Gibson, A, Szakay, A & Cox, F 2021, Optimizing an automatic creaky voice detection method for Australian English-speaking females. in INTERSPEECH 2021: Proceedings of the 22nd Annual Conference of the International Speech Communication Association. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 6, International Speech Communication Association (ISCA), Baixas, France, pp. 1384-1388, INTERSPEECH (22nd : 2021), Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-711

Optimizing an automatic creaky voice detection method for Australian English-speaking females. / White, Hannah; Penney, Joshua; Gibson, Andy et al.
INTERSPEECH 2021: Proceedings of the 22nd Annual Conference of the International Speech Communication Association. Baixas, France: International Speech Communication Association (ISCA), 2021. p. 1384-1388 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 6).

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

TY - GEN

T1 - Optimizing an automatic creaky voice detection method for Australian English-speaking females

AU - White, Hannah

AU - Penney, Joshua

AU - Gibson, Andy

AU - Szakay, Anita

AU - Cox, Felicity

PY - 2021

Y1 - 2021

N2 - Creaky voice is a nonmodal phonation type that has various linguistic and sociolinguistic functions. Manually annotating creaky voice for phonetic analysis is time-consuming and labor-intensive. In recent years, automatic tools for detecting creaky voice have been proposed, which present the possibility for easier, faster and more consistent creak identification. One of these proposed tools is a Creak Detector algorithm that uses an automatic neural network taking its input from several acoustic cues to identify creaky voice. Previous work has suggested that the creak probability threshold at which this tool determines an instance to be creaky may vary depending on the speaker population. The present study investigates the optimal creak detection threshold for female Australian English speakers.Results show further support for the practice of first finding the optimal threshold when using the Creak Detection algorithm on new data sets. Additionally, results show that accuracy of creaky voice detection using the Creak Detection algorithm can be significantly improved by excluding non-sonorant data.

AB - Creaky voice is a nonmodal phonation type that has various linguistic and sociolinguistic functions. Manually annotating creaky voice for phonetic analysis is time-consuming and labor-intensive. In recent years, automatic tools for detecting creaky voice have been proposed, which present the possibility for easier, faster and more consistent creak identification. One of these proposed tools is a Creak Detector algorithm that uses an automatic neural network taking its input from several acoustic cues to identify creaky voice. Previous work has suggested that the creak probability threshold at which this tool determines an instance to be creaky may vary depending on the speaker population. The present study investigates the optimal creak detection threshold for female Australian English speakers.Results show further support for the practice of first finding the optimal threshold when using the Creak Detection algorithm on new data sets. Additionally, results show that accuracy of creaky voice detection using the Creak Detection algorithm can be significantly improved by excluding non-sonorant data.

KW - creaky voice

KW - creak detection

KW - automatic methods

KW - Australian English

UR - http://purl.org/au-research/grants/arc/DP190102164

UR - http://purl.org/au-research/grants/arc/FT180100462

UR - http://www.scopus.com/inward/record.url?scp=85119291407&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2021-711

DO - 10.21437/Interspeech.2021-711

M3 - Conference proceeding contribution

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

SP - 1384

EP - 1388

BT - INTERSPEECH 2021

PB - International Speech Communication Association (ISCA)

CY - Baixas, France

T2 - INTERSPEECH (22nd : 2021)

Y2 - 30 August 2021 through 3 September 2021

ER -

White H, Penney J, Gibson A, Szakay A , Cox F. Optimizing an automatic creaky voice detection method for Australian English-speaking females. In INTERSPEECH 2021: Proceedings of the 22nd Annual Conference of the International Speech Communication Association. Baixas, France: International Speech Communication Association (ISCA). 2021. p. 1384-1388. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2021-711

Optimizing an automatic creaky voice detection method for Australian English-speaking females

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

ARC - Future Fellowships: Multicultural Australian English: The new voice of Sydney

Children's speech, community diversity and the emergence of sound change

Cite this

Optimizing an automatic creaky voice detection method for Australian English-speaking females

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

ARC - Future Fellowships: Multicultural Australian English: The new voice of Sydney

Children's speech, community diversity and the emergence of sound change

Cite this