Automatic assessment of articulation disorders using confident unit-based model adaptation

This paper presents an approach to automatic assessment on articulation disorders using unsupervised acoustic model adaptation. Prior knowledge is obtained via the phonological analysis of the speech data from 453 articulation disordered children. A confusion matrix of the recognition units for a sp...

Full description

Saved in:
Bibliographic Details
Published in2008 IEEE International Conference on Acoustics, Speech and Signal Processing pp. 4513 - 4516
Main Authors Hung-Yu Su, Chun-Hsien Wu, Pei-Jen Tsai
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2008
Subjects
Acoustic distortion
Adaptation model
articulation assessment
Articulation disorder
Automatic speech recognition
Computer science
Hospitals
Information analysis
Loudspeakers
Maximum likelihood linear regression
speaker adaptation
Speech analysis
Speech recognition
Online AccessGet full text

Cover

More Information
Summary:This paper presents an approach to automatic assessment on articulation disorders using unsupervised acoustic model adaptation. Prior knowledge is obtained via the phonological analysis of the speech data from 453 articulation disordered children. A confusion matrix of the recognition units for a specific subject is re-estimated based on the prior knowledge and the recognition results to choose the confident units for adaptation. The adapted acoustic models can effectively improve the recognition performance of the disordered speech and thus used for articulation assessment. In the experiments, the proposed unsupervised adaptation method achieved a significant performance improvement of 9.1% for disordered speech on syllable recognition rate. Automatic assessment also shows encouraging consistency to the assessment from the therapist.
ISBN:9781424414833
1424414830
ISSN:1520-6149
DOI:10.1109/ICASSP.2008.4518659