Title :
Towards subband-based speech recognition
Author :
Bourlard, Herve ; Dupont, Stephane ; Hermansky, Hynek ; Morgan, Nelson
Author_Institution :
Faculté Polytechnique de Mons - TCTS 31, Bid. Dolez, B-7000 Mons, Belgium
Abstract :
In the framework of hidden Markov models (HMM) or hybrid HMM/Artificial Neural Network (ANN) systems, we present a new approach towards speech recognition. The general idea is to split the whole frequency band (represented in terms of critical bands) into a few sub-bands on which different recognizers are independently applied and then recombined at a certain speech unit level to yield global scores and a global recognition decision. The preliminary results presented in this paper show that such an approach, even using quite simple recombination strategies, can yield at least comparable performance on clean speech while providing significantly better robustness in the case of speech corrupted by narrowband noise.
Keywords :
Hidden Markov models; Histograms; Narrowband; Signal to noise ratio; Speech; Speech recognition;
Conference_Titel :
European Signal Processing Conference, 1996. EUSIPCO 1996. 8th
Conference_Location :
Trieste, Italy
Print_ISBN :
978-888-6179-83-6