Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders

Nina R. Benway; Jonathan L. Preston

doi:10.21437/Interspeech.2023-1882

Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders

Nina R. Benway, Jonathan L. Preston

Department of Communication Sciences & Disorders

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

3 Scopus citations

Abstract

Because lab accuracy of clinical speech technology systems may be overoptimistic, clinical validation is vital to demonstrate system reproducibility-in this case, the ability of the PERCEPT-R Classifier to predict clinician judgment of American English/ɹ/during ChainingAI motor-based speech sound disorder intervention. All five participants experienced statistically-significant improvement in untreated words following 10 sessions of combined human-ChainingAI treatment. These gains, despite a wide range of PERCEPT-human and human-human (F1-score) agreement, raise questions about best measuring classification performance for clinical speech that may be perceptually ambiguous.

Original language	English (US)
Pages (from-to)	4558-4562
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.2023-1882
State	Published - 2023
Event	24th International Speech Communication Association, Interspeech 2023 - Dublin, Ireland Duration: Aug 20 2023 → Aug 24 2023

Keywords

rhotics
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.2023-1882

Cite this

Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders. / Benway, Nina R.; Preston, Jonathan L.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2023-August, 2023, p. 4558-4562.

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

@article{b1b02e71e75d4323ad0e41b30690e221,

title = "Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders",

abstract = "Because lab accuracy of clinical speech technology systems may be overoptimistic, clinical validation is vital to demonstrate system reproducibility-in this case, the ability of the PERCEPT-R Classifier to predict clinician judgment of American English/ɹ/during ChainingAI motor-based speech sound disorder intervention. All five participants experienced statistically-significant improvement in untreated words following 10 sessions of combined human-ChainingAI treatment. These gains, despite a wide range of PERCEPT-human and human-human (F1-score) agreement, raise questions about best measuring classification performance for clinical speech that may be perceptually ambiguous.",

keywords = "rhotics, speech sound disorder",

author = "Benway, {Nina R.} and Preston, {Jonathan L.}",

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.2023-1882",

language = "English (US)",

volume = "2023-August",

pages = "4558--4562",

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

issn = "2308-457X",

}

TY - JOUR

T1 - Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders

AU - Benway, Nina R.

AU - Preston, Jonathan L.

PY - 2023

Y1 - 2023

N2 - Because lab accuracy of clinical speech technology systems may be overoptimistic, clinical validation is vital to demonstrate system reproducibility-in this case, the ability of the PERCEPT-R Classifier to predict clinician judgment of American English/ɹ/during ChainingAI motor-based speech sound disorder intervention. All five participants experienced statistically-significant improvement in untreated words following 10 sessions of combined human-ChainingAI treatment. These gains, despite a wide range of PERCEPT-human and human-human (F1-score) agreement, raise questions about best measuring classification performance for clinical speech that may be perceptually ambiguous.

AB - Because lab accuracy of clinical speech technology systems may be overoptimistic, clinical validation is vital to demonstrate system reproducibility-in this case, the ability of the PERCEPT-R Classifier to predict clinician judgment of American English/ɹ/during ChainingAI motor-based speech sound disorder intervention. All five participants experienced statistically-significant improvement in untreated words following 10 sessions of combined human-ChainingAI treatment. These gains, despite a wide range of PERCEPT-human and human-human (F1-score) agreement, raise questions about best measuring classification performance for clinical speech that may be perceptually ambiguous.

KW - rhotics

KW - speech sound disorder

UR - http://www.scopus.com/inward/record.url?scp=85171569002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85171569002&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2023-1882

DO - 10.21437/Interspeech.2023-1882

M3 - Conference Article

AN - SCOPUS:85171569002

SN - 2308-457X

VL - 2023-August

SP - 4558

EP - 4562

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 -

Prospective Validation of Motor-Based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this