TY  - CONF
ID  - henn94:micro
T1  - Neural Networks in Speech Recognition
A1  - Hennebert, Jean
A1  - Hasler, Martin
A1  - Dedieu, Hervé
TI  - 6th Microcomputer School, invited paper, Prague, Czech Republic
Y1  - 1994
SP  - 23
EP  - 40
UR  - http://diuf.unifr.ch/people/henneber/cv/download/neural-networks-in-speech.pdf
KW  - ANN
KW  - MLP
KW  - Speech Recognition
N2  - We review some of the Artificial Neural Network (ANN) approaches used in speech recognition. Some basic principles of neural networks are briefly described as well as their current applications and performances in speech recognition. Strenghtnesses and weaknesses of pure connectionnist networks in the particular context of the speech signal are then evoqued. The emphasis is put on the capabilities of connectionnist methods to improve the performances of the Hidden Markov Model approach (HMM). Some of the principles that govern the socalled hybrid HMM-ANN approach are then briefly explained. Some recent combinations of stochastic models and ANNs known as the Hidden Control Neural Networks are also presented.
ER  -