Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
Joint Authors
Ma, Lin
Li, Haifeng
Fang, Chunying
Zhang, Mancai
Source
Computational and Mathematical Methods in Medicine
Issue
Vol. 2017, Issue 2017 (31 Dec. 2017), pp.1-8, 8 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2017-01-17
Country of Publication
Egypt
No. of Pages
8
Main Subjects
Abstract EN
Pathological speech usually refers to speech distortion resulting from illness or other biological insults.
The assessment of pathological speech plays an important role in assisting the experts, while automatic evaluation of speech intelligibility is difficult because it is usually nonstationary and mutational.
In this paper, we carry out an independent innovation of feature extraction and reduction, and we describe a multigranularity combined feature scheme which is optimized by the hierarchical visual method.
A novel method of generating feature set based on S-transform and chaotic analysis is proposed.
There are BAFS (430, basic acoustics feature), local spectral characteristics MSCC (84, Mel S-transform cepstrum coefficients), and chaotic features (12).
Finally, radar chart and F-score are proposed to optimize the features by the hierarchical visual fusion.
The feature set could be optimized from 526 to 96 dimensions based on NKI-CCRT corpus and 104 dimensions based on SVD corpus.
The experimental results denote that new features by support vector machine (SVM) have the best performance, with a recognition rate of 84.4% on NKI-CCRT corpus and 78.7% on SVD corpus.
The proposed method is thus approved to be effective and reliable for pathological speech intelligibility evaluation.
American Psychological Association (APA)
Fang, Chunying& Li, Haifeng& Ma, Lin& Zhang, Mancai. 2017. Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization. Computational and Mathematical Methods in Medicine،Vol. 2017, no. 2017, pp.1-8.
https://search.emarefa.net/detail/BIM-1142012
Modern Language Association (MLA)
Fang, Chunying…[et al.]. Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization. Computational and Mathematical Methods in Medicine No. 2017 (2017), pp.1-8.
https://search.emarefa.net/detail/BIM-1142012
American Medical Association (AMA)
Fang, Chunying& Li, Haifeng& Ma, Lin& Zhang, Mancai. Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization. Computational and Mathematical Methods in Medicine. 2017. Vol. 2017, no. 2017, pp.1-8.
https://search.emarefa.net/detail/BIM-1142012
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1142012