Title :
The application of neural networks to wordspotting
Author :
Naylor, J.A. ; Huang, W.Y. ; Nguyen, M. ; Li, K.P.
Author_Institution :
ITT Aerosp. Commun. Div., San Diego, CA, USA
Abstract :
The application of dynamic neural networks for improving keyword spotter performance is discussed. A conventional wordspotter, which is based on template matching, provides an initial screening of incoming speech for possible keyword occurrences. The role of the neural network is to provide a second layer of discriminant analysis in which the final accept/reject decision is made. In experiments conducted on standard corpora for wordspotting, secondary scoring with temporally constrained Kohonen feature maps resulted in reduced false alarm rates. Preliminary results using a recurrent neural network are also presented
Keywords :
learning (artificial intelligence); recurrent neural nets; self-organising feature maps; speech recognition; accept/reject decision; discriminant analysis; dynamic neural networks; incoming speech; keyword spotter performance; recurrent neural network; reduced false alarm rates; secondary scoring; standard corpora; subword network training; template matching; temporally constrained Kohonen feature maps; wordspotting; Aerodynamics; Automatic speech recognition; Filter bank; Hidden Markov models; Natural languages; Neural networks; Performance evaluation; Recurrent neural networks; Target recognition; Testing;
Conference_Titel :
Signals, Systems and Computers, 1992. 1992 Conference Record of The Twenty-Sixth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-3160-0
DOI :
10.1109/ACSSC.1992.269132
