Automated vocal analysis of children with hearing loss and their typical and atypical peers

Mark Vandam, D. Kimbrough Oller, Sophie E Ambrose, Sharmistha Gray, Jeffrey A. Richards, Dongxin Xu, Jill Gilkerson, Noah H. Silbert, Mary Pat Moeller

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This study investigated automatic assessment of vocal development in children with hearing loss compared with children who are typically developing, have language delays, and have autism spectrum disorder. Statistical models are examined for performance in a classification model and to predict age within the four groups of children. Design: The vocal analysis system analyzed 1913 whole-day, naturalistic acoustic recordings from 273 toddlers and preschoolers comprising children who were typically developing, hard of hearing, language delayed, or autistic. Results: Samples from children who were hard of hearing patterned more similarly to those of typically developing children than to the language delayed or autistic samples. The statistical models were able to classify children from the four groups examined and estimate developmental age based on automated vocal analysis. Conclusions: This work shows a broad similarity between children with hearing loss and typically developing children, although children with hearing loss show some delay in their production of speech. Automatic acoustic analysis can now be used to quantitatively compare vocal development in children with and without speech-related disorders. The work may serve to better distinguish among various developmental disorders and ultimately contribute to improved intervention.

Original languageEnglish (US)
Pages (from-to)e146-e152
JournalEar and hearing
Volume36
Issue number4
DOIs
StatePublished - Jul 11 2015

Fingerprint

Hearing Loss
Statistical Models
Child Development
Acoustics
Hearing
Language Development Disorders
Speech Disorders
Child Language
Language

Keywords

  • Autism
  • Automatic speech processing
  • Automatic speech recognition
  • Hard of hearing
  • Language delay
  • Speech production
  • Vocal development

ASJC Scopus subject areas

  • Otorhinolaryngology
  • Speech and Hearing

Cite this

Automated vocal analysis of children with hearing loss and their typical and atypical peers. / Vandam, Mark; Oller, D. Kimbrough; Ambrose, Sophie E; Gray, Sharmistha; Richards, Jeffrey A.; Xu, Dongxin; Gilkerson, Jill; Silbert, Noah H.; Moeller, Mary Pat.

In: Ear and hearing, Vol. 36, No. 4, 11.07.2015, p. e146-e152.

Research output: Contribution to journalArticle

Vandam, M, Oller, DK, Ambrose, SE, Gray, S, Richards, JA, Xu, D, Gilkerson, J, Silbert, NH & Moeller, MP 2015, 'Automated vocal analysis of children with hearing loss and their typical and atypical peers', Ear and hearing, vol. 36, no. 4, pp. e146-e152. https://doi.org/10.1097/AUD.0000000000000138
Vandam, Mark ; Oller, D. Kimbrough ; Ambrose, Sophie E ; Gray, Sharmistha ; Richards, Jeffrey A. ; Xu, Dongxin ; Gilkerson, Jill ; Silbert, Noah H. ; Moeller, Mary Pat. / Automated vocal analysis of children with hearing loss and their typical and atypical peers. In: Ear and hearing. 2015 ; Vol. 36, No. 4. pp. e146-e152.
@article{f3a25d31d65847ebaf4924eb90873a18,
title = "Automated vocal analysis of children with hearing loss and their typical and atypical peers",
abstract = "This study investigated automatic assessment of vocal development in children with hearing loss compared with children who are typically developing, have language delays, and have autism spectrum disorder. Statistical models are examined for performance in a classification model and to predict age within the four groups of children. Design: The vocal analysis system analyzed 1913 whole-day, naturalistic acoustic recordings from 273 toddlers and preschoolers comprising children who were typically developing, hard of hearing, language delayed, or autistic. Results: Samples from children who were hard of hearing patterned more similarly to those of typically developing children than to the language delayed or autistic samples. The statistical models were able to classify children from the four groups examined and estimate developmental age based on automated vocal analysis. Conclusions: This work shows a broad similarity between children with hearing loss and typically developing children, although children with hearing loss show some delay in their production of speech. Automatic acoustic analysis can now be used to quantitatively compare vocal development in children with and without speech-related disorders. The work may serve to better distinguish among various developmental disorders and ultimately contribute to improved intervention.",
keywords = "Autism, Automatic speech processing, Automatic speech recognition, Hard of hearing, Language delay, Speech production, Vocal development",
author = "Mark Vandam and Oller, {D. Kimbrough} and Ambrose, {Sophie E} and Sharmistha Gray and Richards, {Jeffrey A.} and Dongxin Xu and Jill Gilkerson and Silbert, {Noah H.} and Moeller, {Mary Pat}",
year = "2015",
month = "7",
day = "11",
doi = "10.1097/AUD.0000000000000138",
language = "English (US)",
volume = "36",
pages = "e146--e152",
journal = "Ear and Hearing",
issn = "0196-0202",
publisher = "Lippincott Williams and Wilkins",
number = "4",

}

TY - JOUR

T1 - Automated vocal analysis of children with hearing loss and their typical and atypical peers

AU - Vandam, Mark

AU - Oller, D. Kimbrough

AU - Ambrose, Sophie E

AU - Gray, Sharmistha

AU - Richards, Jeffrey A.

AU - Xu, Dongxin

AU - Gilkerson, Jill

AU - Silbert, Noah H.

AU - Moeller, Mary Pat

PY - 2015/7/11

Y1 - 2015/7/11

N2 - This study investigated automatic assessment of vocal development in children with hearing loss compared with children who are typically developing, have language delays, and have autism spectrum disorder. Statistical models are examined for performance in a classification model and to predict age within the four groups of children. Design: The vocal analysis system analyzed 1913 whole-day, naturalistic acoustic recordings from 273 toddlers and preschoolers comprising children who were typically developing, hard of hearing, language delayed, or autistic. Results: Samples from children who were hard of hearing patterned more similarly to those of typically developing children than to the language delayed or autistic samples. The statistical models were able to classify children from the four groups examined and estimate developmental age based on automated vocal analysis. Conclusions: This work shows a broad similarity between children with hearing loss and typically developing children, although children with hearing loss show some delay in their production of speech. Automatic acoustic analysis can now be used to quantitatively compare vocal development in children with and without speech-related disorders. The work may serve to better distinguish among various developmental disorders and ultimately contribute to improved intervention.

AB - This study investigated automatic assessment of vocal development in children with hearing loss compared with children who are typically developing, have language delays, and have autism spectrum disorder. Statistical models are examined for performance in a classification model and to predict age within the four groups of children. Design: The vocal analysis system analyzed 1913 whole-day, naturalistic acoustic recordings from 273 toddlers and preschoolers comprising children who were typically developing, hard of hearing, language delayed, or autistic. Results: Samples from children who were hard of hearing patterned more similarly to those of typically developing children than to the language delayed or autistic samples. The statistical models were able to classify children from the four groups examined and estimate developmental age based on automated vocal analysis. Conclusions: This work shows a broad similarity between children with hearing loss and typically developing children, although children with hearing loss show some delay in their production of speech. Automatic acoustic analysis can now be used to quantitatively compare vocal development in children with and without speech-related disorders. The work may serve to better distinguish among various developmental disorders and ultimately contribute to improved intervention.

KW - Autism

KW - Automatic speech processing

KW - Automatic speech recognition

KW - Hard of hearing

KW - Language delay

KW - Speech production

KW - Vocal development

UR - http://www.scopus.com/inward/record.url?scp=84936985924&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936985924&partnerID=8YFLogxK

U2 - 10.1097/AUD.0000000000000138

DO - 10.1097/AUD.0000000000000138

M3 - Article

C2 - 25587667

AN - SCOPUS:84936985924

VL - 36

SP - e146-e152

JO - Ear and Hearing

JF - Ear and Hearing

SN - 0196-0202

IS - 4

ER -