On the efficient speech feature extraction based on independent component analysis

Neural Processing Letters

Volumn 15, Issue 3, 2002, Pages 235-245

  Lee, Jong Hwan ^a   Lee, Te Won ^b   Jung, Ho Young ^a   Lee, Soo Young ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

^b UNIVERSITY OF CALIFORNIA SAN DIEGO   (United States)

Author keywords

Auditory system; Critical band; Feature extraction; Independent component analysis; Sparse code; Speech signal processing

Indexed keywords

BANDWIDTH; FREQUENCY DOMAIN ANALYSIS; INDEPENDENT COMPONENT ANALYSIS; SIGNAL ENCODING; SPEECH ANALYSIS; SPEECH PROCESSING; TIME DOMAIN ANALYSIS;

CRITICAL BAND;

FEATURE EXTRACTION;

EID: 0036609363     PISSN: 13704621     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1015777200976     Document Type: Article

References (15)

1. Possible principles underlying the transformation of sensory messages
2. Emergence of simple-cell receptive field properties by learning a sparse code for natural images
3. The 'independent components' of natural scenes are edge filters
4. Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture
5. Independent component analysis a new concept?
6. An information-maximization approach to blind separation and blind deconvolution
7. Probabilistic framework for the adaptation and comparison of image codes
8. Analytical expressions for critical-band rate and critical bandwidth as a function of frequency
9. Functional connectivity in auditory cortex using chronic, multichannel unit recordings
10. Natural gradient works efficiently in learning
11. Quantum-mechanical distribution functions revisited
12. The wavelet transform, time-frequency localization and signal analysis
13. Time-frequency and multiple-resolution representations in auditory modeling