Modeling Inhalation in Voice Activity Detection

被引：0

作者：

Aguiar Pontes, Josafa de Jesus ^{[1
]}

机构：

[1] Escuela Politec Nacl, Fac Ingn Sistemas, Quito, Ecuador

来源：

2019 INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND SOFTWARE TECHNOLOGIES (ICI2ST) | 2019年

关键词：

Breath; Inhalation; Pause; Silence; Speech; Support Vector Machine; Voice Activity Detection; VAD; Voiceless fricative consonants; ALGORITHM;

D O I：

10.1109/ICI2ST.2019.00011

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The present work investigates the detection of voice activity in acoustic signals of human speech that occur in low noise environments. It proposes a method capable of differentiating between speech and pause events in an acoustic signal that includes inhalations. For this purpose, it uses components, which are based on Support Vector Machine (SVM) classifiers, specialized in detection of both silence and inhalation. In this sense, it shows that the detection of inhalations allows for improving the accurate prediction rate of speech and pause events in a VAD system, reaching a result of 71.8%.

引用

页码：24 / 31

页数：8

共 29 条

[1]

[Anonymous], 2007, Robust Speech Recognition and Understanding, DOI [10.5772/4740, DOI 10.5772/4740]

[2]

Bigi B., 2014, 2 AS PAC CORP LING C

[3] LIBSVM: A Library for Support Vector Machines [J].

Chang, Chih-Chung ;

Lin, Chih-Jen .

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)

[4] Improved voice activity detection algorithm using wavelet and support vector machine [J].

Chen, Shi-Huang ;

Guido, Rodrigo Capobianco ;

Truong, Trieu-Kien ;

Chang, Yaotsu .

COMPUTER SPEECH AND LANGUAGE, 2010, 24 (03) :531-543

[5] Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine [J].

Elton, R. Johny ;

Vasuki, P. ;

Mohanalin, J. .

ENTROPY, 2016, 18 (08)

[6]

Eyben F., 2013, P 21 ACM INT C MULT, P835

[7]

Freeman D. K., 1989, ICASSP-89: 1989 International Conference on Acoustics, Speech and Signal Processing (IEEE Cat. No.89CH2673-2), P369, DOI 10.1109/ICASSP.1989.266442

[8] Features for voice activity detection: a comparative analysis [J].

Graf, Simon ;

Herbig, Tobias ;

Buck, Markus ;

Schmidt, Gerhard .

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2015,

[9]

Hou PX, 2017, IEEE INT CONF FUZZY

[10] Statistical model-based voice activity detection using support vector machine [J].

Jo, Q-H. ;

Chang, J. -H. ;

Shin, J. W. ;

Kim, N. S. .

IET SIGNAL PROCESSING, 2009, 3 (03) :205-210

← 1 2 3 →