Title :
Using polynomial networks for speech recognition
Author :
Campbell, W.M. ; Broun, C.C.
Author_Institution :
Human Interface Lab., Motorola Inc., Tempe, AZ, USA
Abstract :
We consider the problem of using polynomial networks for speech recognition. Previous applications of polynomials to speech recognition have yielded systems which are difficult to train and have only moderate accuracy. We show that through a novel training algorithm, a probabilistic interpretation, and a novel scoring method, polynomial networks can be applied to speech recognition in a manner that is accurate and straightforward
Keywords :
hidden Markov models; learning (artificial intelligence); neural nets; probability; speech recognition; hidden Markov model; neural network; polynomial networks; probabilistic interpretation; scoring method; speech recognition; training algorithm; Artificial neural networks; Classification tree analysis; Databases; Hidden Markov models; Humans; Karhunen-Loeve transforms; Neural networks; Polynomials; Speech recognition; Viterbi algorithm;
Conference_Titel :
Neural Networks for Signal Processing X, 2000. Proceedings of the 2000 IEEE Signal Processing Society Workshop
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6278-0
DOI :
10.1109/NNSP.2000.890159
