An FPN-based classification method for speech intelligibility detection of children with speech impairments

Fadhilah Rosdi, Siti Salwah Salim, Mumtaz Begum Mustafa

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The inability to speak fluently degrades the quality of life of many individuals. Early intervention from childhood can reduce the disfluency of speech among adults. Traditionally, disfluency of speech among children is diagnosed based on the speech intelligibility assessment by speech and language pathologists, which can be expensive and time-consuming. Hence, numerous attempts were made to automate the speech intelligibility detection. Current detectors can discriminate unintelligible speech by calculating the posterior probability scores for each articulatory feature class. However, their major drawback is producing results that are most likely based on training and input data, leading to inconsistencies in discriminating speech sounds. As such, the performance of detectors is still far below humans. To overcome this limitation, a new classification method based on Fuzzy Petri Nets (FPN) is proposed to improve the classification accuracy. FPN was proposed as it has greater knowledge representation ability to reason using uncertain or ambiguous information. In this research, the speech features of Malay impaired children’s speeches are analyzed for the identification of the significant speech features in the impaired speech which are related to the intelligibility deficits. The results showed that FPN is more reliable in discriminating speech sounds than the baseline classifiers with improvements in the classification accuracy and precision.

Original languageEnglish
Pages (from-to)1-18
Number of pages18
JournalSoft Computing
DOIs
Publication statusAccepted/In press - 21 Nov 2017

Fingerprint

Fuzzy Petri Net
Speech Intelligibility
Speech intelligibility
Petri nets
Detector
Speech
Children
Acoustic waves
Detectors
Quality of Life
Posterior Probability
Knowledge representation
Knowledge Representation
Ambiguous
Inconsistency
Baseline
Classifiers
Likely
Classifier

Keywords

  • Classification
  • Fuzzy Petri Nets
  • Intelligibility detection
  • Speech impairments

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Geometry and Topology

Cite this

An FPN-based classification method for speech intelligibility detection of children with speech impairments. / Rosdi, Fadhilah; Salim, Siti Salwah; Mustafa, Mumtaz Begum.

In: Soft Computing, 21.11.2017, p. 1-18.

Research output: Contribution to journalArticle

@article{3c99673169c04ecb944f3a36f4dbf2bf,
title = "An FPN-based classification method for speech intelligibility detection of children with speech impairments",
abstract = "The inability to speak fluently degrades the quality of life of many individuals. Early intervention from childhood can reduce the disfluency of speech among adults. Traditionally, disfluency of speech among children is diagnosed based on the speech intelligibility assessment by speech and language pathologists, which can be expensive and time-consuming. Hence, numerous attempts were made to automate the speech intelligibility detection. Current detectors can discriminate unintelligible speech by calculating the posterior probability scores for each articulatory feature class. However, their major drawback is producing results that are most likely based on training and input data, leading to inconsistencies in discriminating speech sounds. As such, the performance of detectors is still far below humans. To overcome this limitation, a new classification method based on Fuzzy Petri Nets (FPN) is proposed to improve the classification accuracy. FPN was proposed as it has greater knowledge representation ability to reason using uncertain or ambiguous information. In this research, the speech features of Malay impaired children’s speeches are analyzed for the identification of the significant speech features in the impaired speech which are related to the intelligibility deficits. The results showed that FPN is more reliable in discriminating speech sounds than the baseline classifiers with improvements in the classification accuracy and precision.",
keywords = "Classification, Fuzzy Petri Nets, Intelligibility detection, Speech impairments",
author = "Fadhilah Rosdi and Salim, {Siti Salwah} and Mustafa, {Mumtaz Begum}",
year = "2017",
month = "11",
day = "21",
doi = "10.1007/s00500-017-2932-9",
language = "English",
pages = "1--18",
journal = "Soft Computing",
issn = "1432-7643",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - An FPN-based classification method for speech intelligibility detection of children with speech impairments

AU - Rosdi, Fadhilah

AU - Salim, Siti Salwah

AU - Mustafa, Mumtaz Begum

PY - 2017/11/21

Y1 - 2017/11/21

N2 - The inability to speak fluently degrades the quality of life of many individuals. Early intervention from childhood can reduce the disfluency of speech among adults. Traditionally, disfluency of speech among children is diagnosed based on the speech intelligibility assessment by speech and language pathologists, which can be expensive and time-consuming. Hence, numerous attempts were made to automate the speech intelligibility detection. Current detectors can discriminate unintelligible speech by calculating the posterior probability scores for each articulatory feature class. However, their major drawback is producing results that are most likely based on training and input data, leading to inconsistencies in discriminating speech sounds. As such, the performance of detectors is still far below humans. To overcome this limitation, a new classification method based on Fuzzy Petri Nets (FPN) is proposed to improve the classification accuracy. FPN was proposed as it has greater knowledge representation ability to reason using uncertain or ambiguous information. In this research, the speech features of Malay impaired children’s speeches are analyzed for the identification of the significant speech features in the impaired speech which are related to the intelligibility deficits. The results showed that FPN is more reliable in discriminating speech sounds than the baseline classifiers with improvements in the classification accuracy and precision.

AB - The inability to speak fluently degrades the quality of life of many individuals. Early intervention from childhood can reduce the disfluency of speech among adults. Traditionally, disfluency of speech among children is diagnosed based on the speech intelligibility assessment by speech and language pathologists, which can be expensive and time-consuming. Hence, numerous attempts were made to automate the speech intelligibility detection. Current detectors can discriminate unintelligible speech by calculating the posterior probability scores for each articulatory feature class. However, their major drawback is producing results that are most likely based on training and input data, leading to inconsistencies in discriminating speech sounds. As such, the performance of detectors is still far below humans. To overcome this limitation, a new classification method based on Fuzzy Petri Nets (FPN) is proposed to improve the classification accuracy. FPN was proposed as it has greater knowledge representation ability to reason using uncertain or ambiguous information. In this research, the speech features of Malay impaired children’s speeches are analyzed for the identification of the significant speech features in the impaired speech which are related to the intelligibility deficits. The results showed that FPN is more reliable in discriminating speech sounds than the baseline classifiers with improvements in the classification accuracy and precision.

KW - Classification

KW - Fuzzy Petri Nets

KW - Intelligibility detection

KW - Speech impairments

UR - http://www.scopus.com/inward/record.url?scp=85034663865&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034663865&partnerID=8YFLogxK

U2 - 10.1007/s00500-017-2932-9

DO - 10.1007/s00500-017-2932-9

M3 - Article

AN - SCOPUS:85034663865

SP - 1

EP - 18

JO - Soft Computing

JF - Soft Computing

SN - 1432-7643

ER -