PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/

Nina R. Benway; Jonathan L. Preston; Elaine Hitchcock; Asif Salekin; Harshit Sharma; Tara McAllister

doi:10.21437/Interspeech.2022-10785

PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/

Nina R. Benway, Jonathan L. Preston, Elaine Hitchcock, Asif Salekin, Harshit Sharma, Tara McAllister

Communication Sciences and Disorders

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

5 Scopus citations

Abstract

We present the PERCEPT-R corpus, a labeled corpus of child speakers of American English with typical speech and residual speech sound disorders affecting rhotics. We demonstrate the utility of age-and-gender normalized formants extracted from PERCEPT-R in training support vector classifiers to predict ground-truth perceptual judgments of “rhotic” (i.e., dialect-typical) and clinical “derhotic”/ɹ/for novel speakers (mean of participant-specific f-metrics=.83; SD =.18, N = 281).

Original language	English
Pages (from-to)	3648-3652
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2022-September
DOIs	https://doi.org/10.21437/Interspeech.2022-10785
State	Published - 2022
Event	23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022 - Incheon, Korea, Republic of Duration: 18 Sep 2022 → 22 Sep 2022

Keywords

/ɹ/
child speech
clinical speech
mispronunciation detection
open access dataset

Access to Document

10.21437/Interspeech.2022-10785

Cite this

Benway, N. R., Preston, J. L., Hitchcock, E., Salekin, A., Sharma, H., & McAllister, T. (2022). PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2022-September, 3648-3652. https://doi.org/10.21437/Interspeech.2022-10785

@article{a2ede7648f83427ab9f3813ca6c800c4,

title = "PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/",

abstract = "We present the PERCEPT-R corpus, a labeled corpus of child speakers of American English with typical speech and residual speech sound disorders affecting rhotics. We demonstrate the utility of age-and-gender normalized formants extracted from PERCEPT-R in training support vector classifiers to predict ground-truth perceptual judgments of “rhotic” (i.e., dialect-typical) and clinical “derhotic”/ɹ/for novel speakers (mean of participant-specific f-metrics=.83; SD =.18, N = 281).",

keywords = "/ɹ/, child speech, clinical speech, mispronunciation detection, open access dataset",

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

note = "Publisher Copyright: Copyright {\textcopyright} 2022 ISCA.; 23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022 ; Conference date: 18-09-2022 Through 22-09-2022",

year = "2022",

doi = "10.21437/Interspeech.2022-10785",

language = "English",

volume = "2022-September",

pages = "3648--3652",

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

issn = "2308-457X",

publisher = "International Speech Communication Association",

}

Benway, NR, Preston, JL, Hitchcock, E, Salekin, A, Sharma, H & McAllister, T 2022, 'PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2022-September, pp. 3648-3652. https://doi.org/10.21437/Interspeech.2022-10785

PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/. / Benway, Nina R.; Preston, Jonathan L.; Hitchcock, Elaine et al.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2022-September, 2022, p. 3648-3652.

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

TY - JOUR

T1 - PERCEPT-R

T2 - 23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022

AU - Benway, Nina R.

AU - Preston, Jonathan L.

AU - Hitchcock, Elaine

AU - Salekin, Asif

AU - Sharma, Harshit

AU - McAllister, Tara

PY - 2022

Y1 - 2022

N2 - We present the PERCEPT-R corpus, a labeled corpus of child speakers of American English with typical speech and residual speech sound disorders affecting rhotics. We demonstrate the utility of age-and-gender normalized formants extracted from PERCEPT-R in training support vector classifiers to predict ground-truth perceptual judgments of “rhotic” (i.e., dialect-typical) and clinical “derhotic”/ɹ/for novel speakers (mean of participant-specific f-metrics=.83; SD =.18, N = 281).

AB - We present the PERCEPT-R corpus, a labeled corpus of child speakers of American English with typical speech and residual speech sound disorders affecting rhotics. We demonstrate the utility of age-and-gender normalized formants extracted from PERCEPT-R in training support vector classifiers to predict ground-truth perceptual judgments of “rhotic” (i.e., dialect-typical) and clinical “derhotic”/ɹ/for novel speakers (mean of participant-specific f-metrics=.83; SD =.18, N = 281).

KW - /ɹ/

KW - child speech

KW - clinical speech

KW - mispronunciation detection

KW - open access dataset

UR - https://www.scopus.com/pages/publications/85140063828

U2 - 10.21437/Interspeech.2022-10785

DO - 10.21437/Interspeech.2022-10785

M3 - Conference article

AN - SCOPUS:85140063828

SN - 2308-457X

VL - 2022-September

SP - 3648

EP - 3652

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

Y2 - 18 September 2022 through 22 September 2022

ER -

PERCEPT-R: An Open-Access American English Child/Clinical Speech Corpus Specialized for the Audio Classification of/ɹ/

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this