Designing a Reduced Feature-Vector Set for Speech Recognition by Using KL/GPD Competitive Training

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 2107-2110

  Nitta, Tsuneo ^a   Kawamura, Akinori ^a  

^a TOSHIBA CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNITION;

% REDUCTIONS; COMPUTATION TIME; FEATURE EXTRACTOR; FEATURES VECTOR; HYBRID ALGORITHMS; MATRIX QUANTIZATION; MEMORY SIZE; PERFORMANCE; QUANTIZERS; SPEAKER-INDEPENDENT SPEECH RECOGNITION;

SPEECH COMMUNICATION;

EID: 85086796470     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. H.Matsu'ura, Y.Masai, J.Iwasaki, S.Tanaka, H. Kamio, and T.Nitta, “Multimodal, Keyword-based Spoken Dialogue System - MultiksDial”, IEEE Proc. ICASSP94, pp.33-36 (1994).
2. K. Maeda, Japanese Patent No. Showa-63-31831 (application date: March, 1980).
3. M.Kuusela and E.Oja, “The Averaged Learning Subspace Method for Spectral Pattern Recognition”, IEEE IJCPR'82, pp.134-137 (1982).
4. S.Amari, “A Theory of Adaptive Pattern Classifiers”, IEEE Trans. on Elec. Computers, vol.EC-16, No.3, pp.299-307 (June 1967).
5. S.Katagiri, C.-H.Lee, and B.-H.Juang, “New Discriminative Training Algorithms Based on the Generalized Probabilistic Descent Method”, IEEE Neural Networks for Signal Processing, pp.299-308 (1991).
6. H.Watanabe, T.Yamaguchi, and S.Katagiri, “Discriminative Metric Design for Pattern Recognition”, IEEE Proc. ICASSP95, pp.3439-3442 (1995).
7. E.Oja, “Subspace Method of Pattern Recognition”, Research Studies Press (1983).