Title :
Big dumb neural nets: a working brute force approach to speech recognition
Author_Institution :
Int. Comput. Sci. Inst., Berkeley, CA, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
Neural networks with over a million connections have been trained using online backpropagation and a speech corpus with over 6 million training examples (speech frames). These networks provide phonetic probabilistic estimates that are used in a continuous speech recognizer. Issues of the network training and application are discussed in this paper
Keywords :
backpropagation; learning (artificial intelligence); neural nets; speech recognition; big dumb neural nets; brute force approach; continuous speech recognizer; network training; online backpropagation; phonetic probabilistic estimates; speech frames; speech recognition; training examples; Backpropagation; Concurrent computing; Hardware; Hidden Markov models; Multilayer perceptrons; Neural networks; Probability; Programming; Speech analysis; Speech recognition;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374989
