Title :
A Markov random field based multi-band model
Author :
Gravier, Guillnume ; Sigelle, Marc ; Chollet, Gérard
Author_Institution :
ENST/TSI, CNRS, Paris, France
Abstract :
An extension of the multi-band model including inter-band control of time asynchrony is described. It is based on the framework of Markov random fields. The law of the speech process is given by a parametric Gibbs distribution and a maximum likelihood parameter estimation algorithm is developed. This random field model is applied to isolated word recognition. It is shown that similar performances are obtained with the new model and with standard HMM techniques in the mono-band case. In the multi-band case, it is shown that the recognition rate decreases when the number of bands is increased but that modeling inter-band synchrony limits the performance decrease
Keywords :
Markov processes; maximum likelihood estimation; random processes; speech recognition; Markov random field based multi-band model; inter-band control; inter-band synchrony; isolated word recognition; maximum likelihood parameter estimation algorithm; modeling; mono-band case; parametric Gibbs distribution; performance; recognition rate; speech process; time asynchrony; Additive noise; Cepstral analysis; Hidden Markov models; Lattices; Markov random fields; Noise robustness; Parameter estimation; Speech analysis; Speech enhancement; Speech processing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.862013