Application of vector quantized hidden markov modeling to telephone network based connected digit recognition

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

Volumn 1, Issue , 1994, Pages I105-I108

  Buhrke, Eric R ^a   Cardin, Regis ^b   Normandin, Yves ^b   Rahim, Mazin ^a   Wilpon, Jay ^a  

^a LUCENT TECHNOLOGIES   (United States)

^b Cent de Recherche Informatique de Montreal   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL EFFICIENCY; HIDDEN MARKOV MODELS; SIGNAL PROCESSING; STEREOPHONIC BROADCASTING; TELEPHONE SETS;

DISCRETE DENSITIES; HIDDEN MARKOV MODELS (HMMS); MAXIMUM MUTUAL INFORMATION; MODEL ARCHITECTURE; RECOGNITION ACCURACY; SPEECH TECHNOLOGY; TELEPHONE NETWORKS; TEXAS INSTRUMENTS;

SPEECH RECOGNITION;

EID: 0343685370     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1994.389344     Document Type: Conference Paper

References (4)

1. R. Leonard G. Doddington, "A Database for Speaker- Independent Digit Recognition", ICASSP-84, paper 42-11.
2. R. Cardin, Y. Normandin. E. Millien, "Inter-Word Coarticulation Modelling and MMIE Training for Improved Connected Digit Recognition", ICASSP-93 Minneapolis, MN, pp. 243-246, April 1993.
3. R. Cardin, Y. Normandin, R. DeMori, "High Performance Connected Digit Recognition Using Codebook Exponents", ICASSP-92 San Francicso, CA, pp. 505-508, May 1992.
4. R Haeb-Umbach, D. Geller, H. Ney, "Improvements in Connected Digit Recognition Using Linear Discriminant Analysis and Mixture Densities", ICASSP-93 Minneapolis, MN, pp. 239-242, April 1993.