AN RNN BASED SPEECH RECOGNITION SYSTEM WITH DISCRIMINATIVE TRAINING

4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Volumn , Issue , 1995, Pages 1667-1670

  Lee, Tan ^a   Ching, P C ^a   Chan, L W ^a  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION; SPEECH RECOGNITION;

CANTONESE; DISCRIMINATIVE TRAINING; FULLY-CONNECTED RECURRENT NEURAL NETWORKS; NETWORK-BASED; NOVEL METHODS; RECOGNITION SYSTEMS; RECURRENT NEURAL NETWORK MODEL; SPEECH MODELS; SPEECH RECOGNITION SYSTEMS; TRAINING PROCEDURES;

RECURRENT NEURAL NETWORKS;

EID: 85033917718     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Tan Lee, P.C. Ching and L.W. Chan (1995), flecuTient Neural Networks for Speech Modeling and SpeechRecognition, Proceedings ofICASSP-95, Vol.5, pp.3319 - 3322.
2. J.L. Elman (1990), Finding Structure in Time, Cognitive Science 14, pp.179 - 211.
3. Pao-Chung Chang and Biing-Hwang Juang (1993), Discriminative Training ofDynamic Programing Based Speech Recognizers, IEEE Trans, on Speech Audio Processing, Vol.1, No.2, pp.135 - 143.
4. V.Gupta, M.Lennig, P.Mermelstein, P.Kenny, P.F.Seitz and D.O'Shaughnessy (1992), Use of Minimum Duration and Energy Contour for Phonemes to Improve Large Vocabulary Isolated-Word Recognition, Computer Speech and Language 6, pp.345 - 359.
5. P.C. Ching, Tan Lee and Eric Zee (1994), From Phonology and Acoustic Properties to Automatic Recognition ofCantonese, Proceedings of ISSIPNN '94, Hong Kong, Vol.1, pp.127 - 132.