Neural Networks and Speech ProcessingWe would like to take this opportunity to thank all of those individ uals who helped us assemble this text, including the people of Lockheed Sanders and Nestor, Inc., whose encouragement and support were greatly appreciated. In addition, we would like to thank the members of the Lab oratory for Engineering Man-Machine Systems (LEMS) and the Center for Neural Science at Brown University for their frequent and helpful discussions on a number of topics discussed in this text. Although we both attended Brown from 1983 to 1985, and had offices in the same building, it is surprising that we did not meet until 1988. We also wish to thank Kluwer Academic Publishers for their profes sionalism and patience, and the reviewers for their constructive criticism. Thanks to John McCarthy for performing the final proof, and to John Adcock, Chip Bachmann, Deborah Farrow, Nathan Intrator, Michael Perrone, Ed Real, Lance Riek and Paul Zemany for their comments and assistance. We would also like to thank Khrisna Nathan, our most unbi ased and critical reviewer, for his suggestions for improving the content and accuracy of this text. A special thanks goes to Steve Hoffman, who was instrumental in helping us perform the experiments described in Chapter 9. |
Contents
Introduction | 1 |
The Mammalian Auditory System | 9 |
An Artificial Neural Network Primer | 41 |
Copyright | |
9 other sections not shown
Other editions - View all
Neural Networks and Speech Processing David P. Morgan,Christopher L. Scofield No preview available - 2012 |
Common terms and phrases
acoustic activation function algorithm architecture auditory nerve auditory system basilar membrane bigram Chapter class regions classifier cochlea cochlear nucleus complex computed consists database encoded Equation error example false alarms feature extraction feature space feature vectors feedforward fibers Figure filter filterbank formant frequency hidden cells Hopfield network IEEE illustrated inferior colliculus input layer input patterns keyword KWS system language models learning linear modular module multiple N-gram NETgram neural networks neurons nodes noise nonlinear number of cells output cell output layer paradigms parameters perceptron performance phonemes problem RCE network recognition accuracy represent representation response second hidden layer second layer selected sentence sigmoid signal processing speaker-independent spectral speech processing speech recognition speech signal stimulus structure talker TDNN techniques temporal three-layer threshold tion training data training set unsupervised learning utterance values Viterbi algorithm vocabulary vocal tract vowel weights word category zero