Geodesic
Voice Activity Detection Method Based on Multi-valued Coarse-graining Lempel-Ziv Complexity
Computer Science and Information Systems, Tome 8 (2011) no. 3.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

One of the key issues in practical speech processing is to locate precisely endpoints of the input utterance to be free of non-speech regions. Although lots of studies have been performed to solve this problem, the operation of existing voice activity detection (VAD) algorithms is still far away from ideal. This paper proposes a novel robust feature for VAD method that is based on multi-valued coarse-graining Lempel-Ziv Complexity (MLZC), which is an improved algorithm of the binary coarse-graining Lempel-Ziv Complexity (BLZC). In addition, we use fuzzy c-Means clustering algorithm and the Bayesian information criterion algorithm to estimate the thresholds of the MLZC characteristic, and adopt the dual-thresholds method for VAD. Experimental results on the TIMIT continuous speech database show that at low SNR environments, the detection performance of the proposed MLZC method is superior to the VAD in GSM ARM, G.729 and BLZC method.
Keywords: speech processing, voice activity detection, Lempel-Ziv complexity, multi-valued coarse-graining, fuzzy c-Means clustering algorithm, Bayesian information criterion algorithm 
@article{CSIS_2011_8_3_a17,
     author = {Huan Zhao and Gangjin Wang and Cheng Xu and Fei Yu},
     title = {Voice {Activity} {Detection} {Method} {Based} on {Multi-valued} {Coarse-graining} {Lempel-Ziv} {Complexity}},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {8},
     number = {3},
     year = {2011},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2011_8_3_a17/}
}
TY  - JOUR
AU  - Huan Zhao
AU  - Gangjin Wang
AU  - Cheng Xu
AU  - Fei Yu
TI  - Voice Activity Detection Method Based on Multi-valued Coarse-graining Lempel-Ziv Complexity
JO  - Computer Science and Information Systems
PY  - 2011
VL  - 8
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2011_8_3_a17/
ID  - CSIS_2011_8_3_a17
ER  - 
%0 Journal Article
%A Huan Zhao
%A Gangjin Wang
%A Cheng Xu
%A Fei Yu
%T Voice Activity Detection Method Based on Multi-valued Coarse-graining Lempel-Ziv Complexity
%J Computer Science and Information Systems
%D 2011
%V 8
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2011_8_3_a17/
%F CSIS_2011_8_3_a17
Huan Zhao; Gangjin Wang; Cheng Xu; Fei Yu. Voice Activity Detection Method Based on Multi-valued Coarse-graining Lempel-Ziv Complexity. Computer Science and Information Systems, Tome 8 (2011) no. 3. http://geodesic.mathdoc.fr/item/CSIS_2011_8_3_a17/