Pronunciation analysis for children with speech sound disorders

Shiran Dudy, Meysam Asgari, Alexander Kain

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Phonological disorders affect 10% of preschool and school-age children, adversely affecting their communication, academic performance, and interaction level. Effective pronunciation training requires prolonged supervised practice and interaction. Unfortunately, many children do not have access or only limited access to a speech-language pathologist. Computer-assisted pronunciation training has the potential for being a highly effective teaching aid; however, to-date such systems remain incapable of identifying pronunciation errors with sufficient accuracy. In this paper, we propose to improve accuracy by (1) learning acoustic models from a large children's speech database, (2) using an explicit model of typical pronunciation errors of children in the target age range, and (3) explicit modeling of the acoustics of distorted phonemes.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5573-5576
Number of pages4
Volume2015-November
ISBN (Print)9781424492718
DOIs
StatePublished - Nov 4 2015
Event37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 - Milan, Italy
Duration: Aug 25 2015Aug 29 2015

Other

Other37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015
CountryItaly
CityMilan
Period8/25/158/29/15

Fingerprint

Acoustics
Acoustic waves
Teaching
Communication
Language
Learning
Databases
Speech Sound Disorder

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Dudy, S., Asgari, M., & Kain, A. (2015). Pronunciation analysis for children with speech sound disorders. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (Vol. 2015-November, pp. 5573-5576). [7319655] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2015.7319655

Pronunciation analysis for children with speech sound disorders. / Dudy, Shiran; Asgari, Meysam; Kain, Alexander.

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. p. 5573-5576 7319655.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dudy, S, Asgari, M & Kain, A 2015, Pronunciation analysis for children with speech sound disorders. in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. vol. 2015-November, 7319655, Institute of Electrical and Electronics Engineers Inc., pp. 5573-5576, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Milan, Italy, 8/25/15. https://doi.org/10.1109/EMBC.2015.7319655
Dudy S, Asgari M, Kain A. Pronunciation analysis for children with speech sound disorders. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Vol. 2015-November. Institute of Electrical and Electronics Engineers Inc. 2015. p. 5573-5576. 7319655 https://doi.org/10.1109/EMBC.2015.7319655
Dudy, Shiran ; Asgari, Meysam ; Kain, Alexander. / Pronunciation analysis for children with speech sound disorders. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. pp. 5573-5576
@inproceedings{6ebc87efafcb49acaa5728e012aa6d78,
title = "Pronunciation analysis for children with speech sound disorders",
abstract = "Phonological disorders affect 10{\%} of preschool and school-age children, adversely affecting their communication, academic performance, and interaction level. Effective pronunciation training requires prolonged supervised practice and interaction. Unfortunately, many children do not have access or only limited access to a speech-language pathologist. Computer-assisted pronunciation training has the potential for being a highly effective teaching aid; however, to-date such systems remain incapable of identifying pronunciation errors with sufficient accuracy. In this paper, we propose to improve accuracy by (1) learning acoustic models from a large children's speech database, (2) using an explicit model of typical pronunciation errors of children in the target age range, and (3) explicit modeling of the acoustics of distorted phonemes.",
author = "Shiran Dudy and Meysam Asgari and Alexander Kain",
year = "2015",
month = "11",
day = "4",
doi = "10.1109/EMBC.2015.7319655",
language = "English (US)",
isbn = "9781424492718",
volume = "2015-November",
pages = "5573--5576",
booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Pronunciation analysis for children with speech sound disorders

AU - Dudy, Shiran

AU - Asgari, Meysam

AU - Kain, Alexander

PY - 2015/11/4

Y1 - 2015/11/4

N2 - Phonological disorders affect 10% of preschool and school-age children, adversely affecting their communication, academic performance, and interaction level. Effective pronunciation training requires prolonged supervised practice and interaction. Unfortunately, many children do not have access or only limited access to a speech-language pathologist. Computer-assisted pronunciation training has the potential for being a highly effective teaching aid; however, to-date such systems remain incapable of identifying pronunciation errors with sufficient accuracy. In this paper, we propose to improve accuracy by (1) learning acoustic models from a large children's speech database, (2) using an explicit model of typical pronunciation errors of children in the target age range, and (3) explicit modeling of the acoustics of distorted phonemes.

AB - Phonological disorders affect 10% of preschool and school-age children, adversely affecting their communication, academic performance, and interaction level. Effective pronunciation training requires prolonged supervised practice and interaction. Unfortunately, many children do not have access or only limited access to a speech-language pathologist. Computer-assisted pronunciation training has the potential for being a highly effective teaching aid; however, to-date such systems remain incapable of identifying pronunciation errors with sufficient accuracy. In this paper, we propose to improve accuracy by (1) learning acoustic models from a large children's speech database, (2) using an explicit model of typical pronunciation errors of children in the target age range, and (3) explicit modeling of the acoustics of distorted phonemes.

UR - http://www.scopus.com/inward/record.url?scp=84953300352&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953300352&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2015.7319655

DO - 10.1109/EMBC.2015.7319655

M3 - Conference contribution

SN - 9781424492718

VL - 2015-November

SP - 5573

EP - 5576

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

PB - Institute of Electrical and Electronics Engineers Inc.

ER -