Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders

Nina R. Benway; Yashish M. Siriwardena; Jonathan L. Preston; Elaine Hitchcock; Tara McAllister; Carol Espy-Wilson

doi:10.21437/Interspeech.2023-1924

Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders

Nina R. Benway, Yashish M. Siriwardena, Jonathan L. Preston, Elaine Hitchcock, Tara McAllister, Carol Espy-Wilson

Department of Communication Sciences & Disorders

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

Abstract

Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the extent to which a speech inversion system trained on adult speech performs in the context of (1) child and (2) clinical speech. In the absence of an articulatory dataset in children with rhotic speech sound disorders, we show that classifiers trained on tract variables from acoustic-to-articulatory speech inversion meet or exceed the performance of state-of-the-art features when predicting clinician judgment of rhoticity.

Original language	English (US)
Pages (from-to)	4568-4572
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.2023-1924
State	Published - 2023
Event	24th International Speech Communication Association, Interspeech 2023 - Dublin, Ireland Duration: Aug 20 2023 → Aug 24 2023

Keywords

mispronunciation detection
rhotic
speech sound disorder

ASJC Scopus subject areas

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

Access to Document

10.21437/Interspeech.2023-1924

Cite this

Benway, N. R., Siriwardena, Y. M., Preston, J. L., Hitchcock, E., McAllister, T., & Espy-Wilson, C. (2023). Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2023-August, 4568-4572. https://doi.org/10.21437/Interspeech.2023-1924

Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders. / Benway, Nina R.; Siriwardena, Yashish M.; Preston, Jonathan L. et al.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2023-August, 2023, p. 4568-4572.

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

Benway, NR, Siriwardena, YM, Preston, JL, Hitchcock, E, McAllister, T & Espy-Wilson, C 2023, 'Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2023-August, pp. 4568-4572. https://doi.org/10.21437/Interspeech.2023-1924

Benway NR, Siriwardena YM, Preston JL, Hitchcock E, McAllister T, Espy-Wilson C. Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2023;2023-August:4568-4572. doi: 10.21437/Interspeech.2023-1924

@article{74b226f786184cf4a96bae93ef76cdb1,

title = "Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders",

abstract = "Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the extent to which a speech inversion system trained on adult speech performs in the context of (1) child and (2) clinical speech. In the absence of an articulatory dataset in children with rhotic speech sound disorders, we show that classifiers trained on tract variables from acoustic-to-articulatory speech inversion meet or exceed the performance of state-of-the-art features when predicting clinician judgment of rhoticity.",

keywords = "mispronunciation detection, rhotic, speech sound disorder",

author = "Benway, {Nina R.} and Siriwardena, {Yashish M.} and Preston, {Jonathan L.} and Elaine Hitchcock and Tara McAllister and Carol Espy-Wilson",

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.2023-1924",

language = "English (US)",

volume = "2023-August",

pages = "4568--4572",

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

issn = "2308-457X",

}

TY - JOUR

T1 - Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders

AU - Benway, Nina R.

AU - Siriwardena, Yashish M.

AU - Preston, Jonathan L.

AU - Hitchcock, Elaine

AU - McAllister, Tara

AU - Espy-Wilson, Carol

PY - 2023

Y1 - 2023

N2 - Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the extent to which a speech inversion system trained on adult speech performs in the context of (1) child and (2) clinical speech. In the absence of an articulatory dataset in children with rhotic speech sound disorders, we show that classifiers trained on tract variables from acoustic-to-articulatory speech inversion meet or exceed the performance of state-of-the-art features when predicting clinician judgment of rhoticity.

AB - Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the extent to which a speech inversion system trained on adult speech performs in the context of (1) child and (2) clinical speech. In the absence of an articulatory dataset in children with rhotic speech sound disorders, we show that classifiers trained on tract variables from acoustic-to-articulatory speech inversion meet or exceed the performance of state-of-the-art features when predicting clinician judgment of rhoticity.

KW - mispronunciation detection

KW - rhotic

KW - speech sound disorder

UR - http://www.scopus.com/inward/record.url?scp=85171557523&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85171557523&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2023-1924

DO - 10.21437/Interspeech.2023-1924

M3 - Conference Article

AN - SCOPUS:85171557523

SN - 2308-457X

VL - 2023-August

SP - 4568

EP - 4572

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 -

Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of/ɹ/in Child Speech Sound Disorders

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this