Continuous speech recognition using dynamic synapse neural network
Alireza Afshordi Dibazar, Hassan H. Namarvar, Theodore W. Berger · The Journal of the Acoustical Society of America · 2004
The modified architecture of the dynamic synapse neural network (DSNN) is used to model windowed short time speech signal. The quasi-linearization algorithm is applied to train the network. The parameters of the trained network, which are representatives of the signal, are fed into the GMM/HMM based classifier. The performance of the modified architecture with GMM/HMM based classifier is demonstrated by recognition of continuous speech from unprocessed, noisy raw waveforms spoken by multiple speakers. Our results indicate that the features obtained from DSNN are robust in the presence of additive white Gaussian noise with respect to state-of-the-art Mel frequency features. [Work supported in part by DARPA, NASA and ONR.]