Title :
High performance connected digit recognition using maximum mutual information estimation
Author :
Cardin, Régis ; Normandin, Yves ; de Mori, Renato
Author_Institution :
Centre de Recherche Inf. de Montreal, Que., Canada
Abstract :
The authors describe the latest development by the speech research group at CRIM (Centre de Recherche Informatique de Montreal) in speaker-independent connected digit recognition, using hidden Markov Models (HMMs) trained with maximum mutual information estimation, in conjunction with connectionist models. The experiments described were all done on the complete adult portion of the 10 kHz speaker-independent TI/NIST connected digit database. The baseline system, using discrete HMMs and maximum likelihood estimation, has a 98.6% word recognition rate and a 96.1% string recognition rate. The authors describe techniques that made it possible to improve greatly the baseline system recognition rate. The 99.3% recognition rate and 98.0% string recognition rate were obtained with a single model per unit using discrete HMMs and recurrent neural networks. Using semi-continuous HMMs with two models per digit (one for male and one for female speakers), a 99.5% word recognition rate and a 98.4% string recognition rate were achieved
Keywords :
Markov processes; estimation theory; information theory; neural nets; speech recognition; 10 kHz; CRIM; Centre de Recherche Informatique de Montreal; HMM; TI/NIST connected digit database; baseline system; connected digit recognition; connectionist models; hidden Markov Models; maximum likelihood estimation; maximum mutual information estimation; recurrent neural networks; speaker independent recognition; speech research; string recognition rate; word recognition rate; Code standards; Databases; Hidden Markov models; Maximum likelihood estimation; Mutual information; Power system modeling; Probability distribution; Recurrent neural networks; Speech; Topology;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150394