A new approach to hybrid HMM/ANN speech recognition using mutual information neural networks

Advances in Neural Information Processing Systems

Volumn , Issue , 1997, Pages 772-778

  Rigoll, G ^a   Neukirchen, C ^a  

^a UNIVERSITY OF DUISBURG ESSEN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

COMPLEX NETWORKS; HIDDEN MARKOV MODELS; HYBRID SYSTEMS; SPEECH RECOGNITION;

CONTEXT DEPENDENT; CONTINUOUS PARAMETERS; DISCRETE HIDDEN MARKOV MODEL; MAXIMUM LIKELIHOOD PRINCIPLE; MUTUAL INFORMATIONS; OUTPUT NEURONS; POSTERIOR PROBABILITY; VECTOR QUANTIZERS;

NEURAL NETWORKS;

EID: 84899033435     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Rigoll, G. (1994) Maximum Mutual Information Neural Networks for Hybrid Connectionist-HMM Speech Recognition Systems, IEEE Transactions on Speech and Audio Processing, Vol. 2, No. 1, Special Issue on Neural Networks for Speech Processing, pp. 175-184
2. Neukirchen, C. & Rigoll, G. (1996) Training of MMI Neural Networks as Vector Quantizers, Internal Report, Gerhard-Mercator-University Duisburg, Faculty of Electrical Engineering, available via http://www.fb9-ti.uni-duisburg. de/veroeffentl.html
3. Bourlard, H. & Morgan, N. (1994) Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers
4. Hochberg, M., Renals, S., Robinson, A., Cook, G. (1995) Recent Improvements to the ABBOT Large Vocabulary CSR System, in Proc. IEEE-ICASSP, Detroit, pp. 69-72
5. Rigoll, G., Neukirchen, C, Rottland, J. (1996) A New Hybrid System Based on MMI-Neural Networks for the RM Speech Recognition Task, in Proc. IEEE-ICASSP, Atlanta