Neural nets for speech recognition
William Y. C. Huang, Richard P. Lippmann, Thao N. N. Nguyen · The Journal of the Acoustical Society of America · 1988
Artificial neural networks are of interest for two main reasons. First, they provide architectures to implement many algorithms used in speech rccognizcrs with fine grain massive parallelism. Second, they are leading to new computational algorithms and new approaches to speech recognition inspired by biological nervous systems. Neural net approaches to the problems of speech preprocessing, pattern classification, and time alignment are reviewed. Preprocessors using auditory nerve time-synchrony models have provided improved recognition performance in noise [O. Ghitza, ICASSP 87, 2372–2375]. Highly parallel neural net architectures exist to implement many important traditional classification algorithms, such as k-nearest neighbor and Gaussian classifiers [R. Lippmann, IEEE ASSP Mag. 4(2), 4–22 (1987)]. Newer multilayer perceptron classifiers trained with back propagation can form arbitrary decision regions, are robust, and train rapidly for convex decision regions. These nets performed as well as conventional classification algorithms for digit and vowel classification tasks [W. Huang et al., 1st ICNN IV, 485 (1987)]. Neural net approaches to the problem of time alignment are reviewed, including a neural net model called a Viterbi net that implements the Viterbi decoder used successfully in continuous distribution hidden Markov models (HMMs) [R. Lippmann et al., 1st ICNN IV, 417 (1987)]. [This work was sponsored by the Defense Advanced Research Projects Agency and the Department of the Air Force.]