Voice activity detection with generalized gamma distribution

被引:2
作者
Almpanidis, George [1 ]
Kotropoulos, Constantine [1 ]
机构
[1] Aristotle Univ Thessaloniki, Dept Informat, GR-54124 Thessaloniki, Greece
来源
2006 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO - ICME 2006, VOLS 1-5, PROCEEDINGS | 2006年
关键词
D O I
10.1109/ICME.2006.262692
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we model speech samples with the generalized Gamma distribution and evaluate the efficiency of such modelling for voice activity detection. Using a computationally inexpensive maximum likelihood approach, we employ the Bayesian Information Criterion for identifying the phoneme boundaries in noisy speech.
引用
收藏
页码:961 / +
页数:2
相关论文
共 16 条
[1]  
CHANG J, 2003, P EUR C SPEECH COMM
[2]  
CHEN S, 1998, DARPA SPEECH REC WOR
[3]   DISTBIC: A speaker-based segmentation for audio data indexing [J].
Delacourt, P ;
Wellekens, CJ .
SPEECH COMMUNICATION, 2000, 32 (1-2) :111-126
[4]   Comparison of energy-based endpoint detectors for speech signal processing [J].
Ganapathiraju, A ;
Webster, L ;
Trimble, J ;
Bush, K ;
Kornman, P .
PROCEEDINGS OF THE IEEE SOUTHEASTCON '96: BRINGING TOGETHER EDUCATION, SCIENCE AND TECHNOLOGY, 1996, :500-503
[5]   A soft voice activity detector based on a Laplacian-Gaussian model [J].
Gazor, S ;
Zhang, W .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2003, 11 (05) :498-505
[6]   Speech probability distribution [J].
Gazor, S ;
Zhang, W .
IEEE SIGNAL PROCESSING LETTERS, 2003, 10 (07) :204-207
[7]  
MARTIN R, 2002, P IEEE INT C AC SPEE, V1, P253
[8]   Robust voice activity detection using higher-order statistics in the LPC residual domain [J].
Nemer, E ;
Goubran, R ;
Mahmoud, S .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001, 9 (03) :217-231
[9]  
Pigeon S, 1997, LECT NOTES COMPUT SC, V1206, P403, DOI 10.1007/BFb0016021
[10]   Statistical modeling of speech signals based on generalized gamma distribution [J].
Shin, JW ;
Chang, JH ;
Kim, NS .
IEEE SIGNAL PROCESSING LETTERS, 2005, 12 (03) :258-261