Automatic detection of consonant omission in cleft palate speech

He, L, Wang, X, Zhang, J, Liu, Q, Yin, H and Lech, M 2018, 'Automatic detection of consonant omission in cleft palate speech', International Journal of Speech Technology, vol. 22, no. 1, pp. 59-65.

Document type: Journal Article
Collection: Journal Articles

Title Automatic detection of consonant omission in cleft palate speech
Author(s) He, L
Wang, X
Zhang, J
Liu, Q
Yin, H
Lech, M
Year 2018
Journal name International Journal of Speech Technology
Volume number 22
Issue number 1
Start page 59
End page 65
Total pages 7
Publisher Springer New York LLC
Abstract Consonant omission is one of the most typical and common articulation disorders in cleft palate (CP) speech. The automatic evaluation of consonant omission provides an objective and aided diagnosis to speech-language pathologists and CP patients. This work proposes an automatic consonant omission method. The collection of pathologic speech data is far more difficult than that of normal speech. The speech samples applied in this work are collected from 80 CP patients, with annotation on the phonemic level by professional speech-language pathologists. The proposed method requires no pre-training or modeling, by taking advantages of priori knowledge of CP speech and Chinese phonetics. The classification between voiced initials and finals is a difficulty in Mandarin speech processing researches, this work proposes a time-domain waveform difference analysis method to address this difficulty. The proposed method achieves the accuracy of 88.9% for consonant omission detection in CP speech, and the sensitivity and specificity of the proposed method are 70.89% and 91.86% respectively.
Subject Signal Processing
Keyword(s) Articulation disorder
Cleft palate speech
Consonant omission
Resonance disorder
DOI - identifier 10.1007/s10772-018-09570-w
Copyright notice © Springer Science+Business Media, LLC, part of Springer Nature 2018
ISSN 1381-2416
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 33 Abstract Views  -  Detailed Statistics
Created: Tue, 26 Mar 2019, 09:36:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us