Title :
Homomorphic vector quantisation
Author_Institution :
Czechoslovak Academy of Sciences, Institute of Radio Engineering & Electronics, Prague, Czechoslovakia
Abstract :
A new approach is proposed for vector quantisation in linear predictive speech coding. The problem is formulated as speech model recognition by minimising the Euclidean distance measure of real cepstra of models with unit power transmission. The procedure is robust with respect to quantisation of both the cepstral coefficients and operational results.
Keywords :
speech analysis and processing; speech recognition; Euclidean distance measure of real cepstra; homomorphic vector quantisation; linear predictive speech coding; speech model recognition; speech recognition;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19870402
