Classifying Rhoticity of/ɹ/in Speech Sound Disorder using Age-and-Sex Normalized Formants

Nina R. Benway; Jonathan L. Preston; Asif Salekin; Yi Xiao; Harshit Sharma; Tara McAllister

doi:10.21437/Interspeech.2023-312

Classifying Rhoticity of/ɹ/in Speech Sound Disorder using Age-and-Sex Normalized Formants

Nina R. Benway, Jonathan L. Preston, Asif Salekin, Yi Xiao, Harshit Sharma, Tara McAllister

Research output: Contribution to journal › Conference Article › peer-review

6 Scopus citations

Abstract

Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g.,/ɹ/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic/ɹ/in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score = .81 (σ_x = .10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.

Original language	English (US)
Pages (from-to)	4563-4567
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2023-August
DOIs	https://doi.org/10.21437/Interspeech.2023-312
State	Published - 2023
Event	24th International Speech Communication Association, Interspeech 2023 - Dublin, Ireland Duration: Aug 20 2023 → Aug 24 2023

Keywords

clinical
mispronunciation detection
rhotics

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modeling and Simulation

Access to Document

10.21437/Interspeech.2023-312

Cite this

Classifying Rhoticity of/ɹ/in Speech Sound Disorder using Age-and-Sex Normalized Formants. / Benway, Nina R.; Preston, Jonathan L.; Salekin, Asif et al.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2023-August, 2023, p. 4563-4567.

Research output: Contribution to journal › Conference Article › peer-review

@article{65e475d855fd43a4b54fba406e99aa51,

title = "Classifying Rhoticity of/ɹ/in Speech Sound Disorder using Age-and-Sex Normalized Formants",

abstract = "Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g.,/ɹ/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic/ɹ/in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score = .81 (σx = .10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.",

keywords = "clinical, mispronunciation detection, rhotics",

author = "Benway, {Nina R.} and Preston, {Jonathan L.} and Asif Salekin and Yi Xiao and Harshit Sharma and Tara McAllister",

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.2023-312",

language = "English (US)",

volume = "2023-August",

pages = "4563--4567",

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

issn = "2308-457X",

}

TY - JOUR

T1 - Classifying Rhoticity of/ɹ/in Speech Sound Disorder using Age-and-Sex Normalized Formants

AU - Benway, Nina R.

AU - Preston, Jonathan L.

AU - Salekin, Asif

AU - Xiao, Yi

AU - Sharma, Harshit

AU - McAllister, Tara

PY - 2023

Y1 - 2023

N2 - Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g.,/ɹ/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic/ɹ/in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score = .81 (σx = .10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.

AB - Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g.,/ɹ/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs. derhotic/ɹ/in the PERCEPT-R Corpus. Gated recurrent neural networks trained on this feature set achieve a mean test participant-specific F1-score = .81 (σx = .10, med = .83, n = 48), with post hoc modeling showing no significant effect of child age or sex.

KW - clinical

KW - mispronunciation detection

KW - rhotics

UR - http://www.scopus.com/inward/record.url?scp=85171553384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85171553384&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2023-312

DO - 10.21437/Interspeech.2023-312

M3 - Conference Article

AN - SCOPUS:85171553384

SN - 2308-457X

VL - 2023-August

SP - 4563

EP - 4567

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

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

T2 - 24th International Speech Communication Association, Interspeech 2023

Y2 - 20 August 2023 through 24 August 2023

ER -

Classifying Rhoticity of/ɹ/in Speech Sound Disorder using Age-and-Sex Normalized Formants

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this