Use of local kurtosis measure for spotting usable speech segments in co-channel speech

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2001, Pages 649-652

  Krishnamachari, Kasturi Rangan ^a   Yantorno, Robert E ^a   Lovekin, Jereme M ^a   Benincasa, Daniel S ^b   Wenndt, Stanley J ^b  

^a Temple University   (United States)

^b AIR FORCE RESEARCH LABORATORY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CO CHANNEL SPEECH; GAUSSIANITY; KUTOSIS; SPEECH SEGMENT; USABILITY;

ACOUSTIC VARIABLES MEASUREMENT; COMMUNICATION CHANNELS (INFORMATION THEORY); INTERFERENCE SUPPRESSION; SIGNAL INTERFERENCE; SPEECH INTELLIGIBILITY; SPEECH PROCESSING; STATISTICAL METHODS;

SPEECH COMMUNICATION;

EID: 0034843120     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940915     Document Type: Article

References (15)

1. Spectral autocorrelation ratio as a usability measure of speech segments under co-channel conditions
2. Iterative technique for blind source separation using only fourth order cumulants
3. Source separation using higher order moments
4. Source identification: A solution based on cumulants
5. New self-adaptive algorithm for source separation based on contrast functions
6. A new approach to multipath correction of constant modulus signals
7. Multichannel speech separation by Eigen decomposition and its application to co-talker interference removal
8. On minimum entropy deconvolution
9. Speech separation by kurtosis maximization
10. An experimental study of speech wave probability distributions
11. Minimum mean squared quantization in speech
12. Probability, random variables and stochastic processes
13. Description of spherically invariant random processes by means of G-functions
14. Description and generation of spherically invariant speech-model signals
15. Experimental studies on one and two-dimensional amplitude probability densities of speech signals