Independent component analysis applied to feature extraction for robust automatic speech recognition

Electronics Letters

Volumn 36, Issue 23, 2000, Pages 1977-1978

  Potamitis, L ^a   Fakotakis, N ^a   Kokkinakis, G ^a  

^a UNIVERSITY OF PATRAS   (Greece)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COSINE TRANSFORMS; FEATURE EXTRACTION; SPECTRUM ANALYSIS; SPEECH RECOGNITION; VECTORS;

AUTOMATIC SPEECH RECOGNITION (ASR); HIDDEN MARKOV MODEL (HMM) CLASSIFIERS; LINEAR DISCRIMINATION ANALYSIS (LDA); LOG SPECTRUM; PRINCIPLE COMPONENT ANALYSIS (PCA);

WAVEGUIDE COMPONENTS;

EID: 0034319559     PISSN: 00135194     EISSN: None     Source Type: Journal    
DOI: 10.1049/el:20001365     Document Type: Article

References (5)

1. EISELE, T., HAEB-UMBACH., and LANGMANN, D.: 'A comparative study of linear feature transformation techniques for automatic speech recognition'. ICSLP, 1996, pp. 252-255
2. HERMASNKY, H., and NABYATH, N.: 'Spectral basis functions from discrimination analysis'. ICSLP, 1988, pp. 616-620
3. SIOHAN, O.: On the robustness of linear discrimination analysis as a preprocessing step for noisy speech recognition'. ICASSP, 1998, pp. 125-128
4. LEE, T.W., GIROLAMI, M., and SEJNOWSKI, T.J.: 'Independent component analysis using an extended Infomax algorithm for mixed sub-Gaussian and super-Gaussian sources', Neural Comput., 1999, 11, (2), pp. 409-433
5. JANG, G.-J., YUN, S.-J., and OH, Y.-H.: 'Feature vector transformation using ICA and its application to speaker verification', Eurospeech, 1999, pp. 767-770