A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction

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

Volumn 1, Issue , 1998, Pages 9-12

  Rigoll, G ^a   Willett, D ^a  

^a UNIVERSITY OF DUISBURG ESSEN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

COMPLEX NETWORKS; CONTINUOUS SPEECH RECOGNITION; FEATURE EXTRACTION; HYBRID SYSTEMS; LINEAR TRANSFORMATIONS; SIGNAL PROCESSING;

COMPUTATIONAL COSTS; DISCRIMINATIVE FEATURES; DISCRIMINATIVE TRAINING; FEATURE TRANSFORMATIONS; NONLINEAR FEATURE EXTRACTION; RECOGNITION ACCURACY; RECOGNITION SYSTEMS; RESOURCE MANAGEMENT;

MATHEMATICAL TRANSFORMATIONS;

EID: 0031630638     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1998.674354     Document Type: Conference Paper

References (11)

1. X. Aubert, R. Haeb-Umbach, H. Ney, "Continuous mixture densities and linear discriminant analysis for improved context-dependent acoustic models", Proc. ICASSP, 1993, pp. 648-651.
2. H. Bourlard, N. Morgan, "Connectionist Speech Recognition-A Hybrid Approach", Kluwer Academic Press, 1994.
3. M. M. Hochberg, G. D. Cook, S. J. Renals, A. J. Robinson, A. S. Schechtman, "The 1994 ABBOT Hybrid Connectionist-HMM Large-Vocabulary Recognition System", Proc. ARPA Spoken Language Systems Technology Workshop, 1995.
4. H. Ney, "Speech Recognition in a Neural Network Framework: Discriminative Training of Gaussian Models and Mixture Densities as Radial Basis Functions", Proc. ICASSP, 1991, pp. 573-576.
5. Y. Normandin, R. Lacouture, R. Cardin: "MMIE Training for Large Vocabulary Continuous Speech Recognition" Proc. IC-SLP, 1994, pp. 1367-1370.
6. G. Rigoll, "Maximum Mutual Information Neural Networks for Hybrid Connectionist-HMM Speech Recognition", IEEE-Trans. Speech Audio Processing, Vol. 2, No. 1, Jan. 1994, pp. 175-184.
7. G. Rigoll, C. Neukirchen, "A new approach to hybrid HMM/ANN speech recognition using mutual information neural networks", Advances in Neural Information Processing Systems (NJPS-96), Denver, 1996, pp. 772-778.
8. V. Valtehev, J.J. Odell, P.C. Woodland, S.J. Young "Lattice-Based Discriminative Training for Large Vocabulary Speech Recognition" Proc. ICASSP, 1996, pp. 605-608.
9. D. Willett, C. Neukirchen, R. Rottland, "Dictionary-Based Discriminative HMM Parameter Estimation for Continuous Speech Recognition Systems", Proc. ICASSP, 1997, pp. 1515-1518.
10. D. Willett, G. Rigoll, "Hybrid HMM/NN Speech Recognition with a discriminant neural feature extraction" Advances in Neural Information Processing Systems (NTPS-97), Denver, 1997.
11. D. Willett, G. Rigoll, "A New Approach to Generalized Mix ture Tying for Continuous HMM-Based Speech Recognition", Proc. EUROSPEECH, 1997, pp. 1175-1178.