Cargando…

Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization

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 an...

Descripción completa

Detalles Bibliográficos
Autores principales: Fang, Chunying, Li, Haifeng, Ma, Lin, Zhang, Mancai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5282458/
https://www.ncbi.nlm.nih.gov/pubmed/28194222
http://dx.doi.org/10.1155/2017/2431573
_version_ 1782503325510402048
author Fang, Chunying
Li, Haifeng
Ma, Lin
Zhang, Mancai
author_facet Fang, Chunying
Li, Haifeng
Ma, Lin
Zhang, Mancai
author_sort Fang, Chunying
collection PubMed
description 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.
format Online
Article
Text
id pubmed-5282458
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-52824582017-02-13 Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization Fang, Chunying Li, Haifeng Ma, Lin Zhang, Mancai Comput Math Methods Med Research Article 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. Hindawi Publishing Corporation 2017 2017-01-17 /pmc/articles/PMC5282458/ /pubmed/28194222 http://dx.doi.org/10.1155/2017/2431573 Text en Copyright © 2017 Chunying Fang et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Fang, Chunying
Li, Haifeng
Ma, Lin
Zhang, Mancai
Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
title Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
title_full Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
title_fullStr Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
title_full_unstemmed Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
title_short Intelligibility Evaluation of Pathological Speech through Multigranularity Feature Extraction and Optimization
title_sort intelligibility evaluation of pathological speech through multigranularity feature extraction and optimization
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5282458/
https://www.ncbi.nlm.nih.gov/pubmed/28194222
http://dx.doi.org/10.1155/2017/2431573
work_keys_str_mv AT fangchunying intelligibilityevaluationofpathologicalspeechthroughmultigranularityfeatureextractionandoptimization
AT lihaifeng intelligibilityevaluationofpathologicalspeechthroughmultigranularityfeatureextractionandoptimization
AT malin intelligibilityevaluationofpathologicalspeechthroughmultigranularityfeatureextractionandoptimization
AT zhangmancai intelligibilityevaluationofpathologicalspeechthroughmultigranularityfeatureextractionandoptimization