Machine Learning Approach to Dysphonia Detection

被引：30

作者：

Dankovicova, Zuzana ^{[1
]}

Sovak, David ^{[1
]}

Drotar, Peter ^{[1
]}

Vokorokos, Liberios ^{[1
]}

机构：

[1] Tech Univ Kosice, Fac Elect Engn & Informat, Dept Comp & Informat, Kosice 04001, Slovakia

来源：

APPLIED SCIENCES-BASEL | 2018年 / 8卷 / 10期

关键词：

decision support systems; biomedical signal processing; speech analysis; supervised learning; support vector machines; SUPPORT; TECHNOLOGY; SELECTION; DISEASE;

D O I：

10.3390/app8101927

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

This paper addresses the processing of speech data and their utilization in a decision support system. The main aim of this work is to utilize machine learning methods to recognize pathological speech, particularly dysphonia. We extracted 1560 speech features and used these to train the classification model. As classifiers, three state-of-the-art methods were used: K-nearest neighbors, random forests, and support vector machine. We analyzed the performance of classifiers with and without gender taken into account. The experimental results showed that it is possible to recognize pathological speech with as high as a 91.3% classification accuracy.

引用

页数：12

共 29 条

[1] A Random Forest approach using imprecise probabilities [J].

Abellan, Joaquin ;

Mantas, Carlos J. ;

Castellano, Javier G. .

KNOWLEDGE-BASED SYSTEMS, 2017, 134 :72-84

[2] NS-k-NN: Neutrosophic Set-Based k-Nearest Neighbors Classifier [J].

Akbulut, Yaman ;

Sengur, Abdulkadir ;

Guo, Yanhui ;

Smarandache, Florentin .

SYMMETRY-BASEL, 2017, 9 (09)

[3] Voice Pathology Detection and Classification Using Auto-Correlation and Entropy Features in Different Frequency Regions [J].

Al-Nasheri, Ahmed ;

Muhammad, Ghulam ;

Alsulaiman, Mansour ;

Ali, Zulfiqar ;

Malki, Khalid H. ;

Mesallam, Tamer A. ;

Ibrahim, Mohamed Farahat .

IEEE ACCESS, 2018, 6 :6961-6974

[4]

Baken R. J., 2000, Clinical Measurement of Speech and Voice

[5]

Barry B., SAARBRUECKEN VOICE D

[6]

Bone D, 2016, CONF REC ASILOMAR C, P831, DOI 10.1109/ACSSC.2016.7869164

[7] Use of machine learning to improve autism screening and diagnostic instruments: effectiveness, efficiency, and multi-instrument fusion [J].

Bone, Daniel ;

Bishop, Somer L. ;

Black, Matthew P. ;

Goodwin, Matthew S. ;

Lord, Catherine ;

Narayanan, Shrikanth S. .

JOURNAL OF CHILD PSYCHOLOGY AND PSYCHIATRY, 2016, 57 (08) :927-937

[8] Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics [J].

Boulesteix, Anne-Laure ;

Janitza, Silke ;

Kruppa, Jochen ;

Koenig, Inke R. .

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2012, 2 (06) :493-507

[9] Feature selection in machine learning: A new perspective [J].

Cai, Jie ;

Luo, Jiawei ;

Wang, Shulin ;

Yang, Sheng .

NEUROCOMPUTING, 2018, 300 :70-79

[10] Advanced Information Technology - Support of Improved Personalized Therapy of Speech Disorders [J].

Danubianu, M. ;

Pentiuc, S. G. ;

Tobolcea, I. ;

Schipor, O. A. .

INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2010, 5 (05) :684-692

← 1 2 3 →