Title :
Nonlinear predictive vector quantisation with recurrent neural nets
Author :
Wu, Lizhong ; Niranjan, Mahesan ; Fallside, Frank
Author_Institution :
Dept. of Eng., Cambridge Univ., UK
Abstract :
The nonlinear prediction capability of neural nets is applied to the design of improved predictive speech coders. Performance evaluations and comparisons with linear predictive speech coding are presented. These tests show the applicability of nonlinear prediction to speech coding and the improvement in coding performance
Keywords :
prediction theory; recurrent neural nets; speech coding; vector quantisation; nonlinear predictive vector quantisation; performance evaluation; predictive speech coders; recurrent neural nets; Information filtering; Information filters; Neural networks; Nonlinear equations; Predictive models; Propagation losses; Recurrent neural networks; Speech coding; Testing; Vector quantization;
Conference_Titel :
Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop
Conference_Location :
Linthicum Heights, MD
Print_ISBN :
0-7803-0928-6
DOI :
10.1109/NNSP.1993.471851
