Title :
Global maximum likelihood voice decoding
Author :
Dean, Richard A.
Author_Institution :
Dept. of Defense, Ft. Meade, MD, USA
Abstract :
Research on a technique for improving speech coder performance in the presence of errors is presented. It is shown that significant performance advantages can be achieved by combining conventional maximum-likelihood decoding with the context within the speech signal to make global decisions. The hidden Markov model (HMM) is integrated into a combined channel and speech decoder. A theoretical development of a global maximum-likelihood decoder is presented. Results of testing in channel errors are presented, demonstrating enhanced error performance
Keywords :
Markov processes; coding errors; decoding; error statistics; probability; speech analysis and processing; channel errors; combined channel/speech decoder; error performance; global maximum-likelihood decoder; hidden Markov model; speech coder performance; voice decoding; Bandwidth; Data compression; Delay; Digital communication; Distortion measurement; Error correction; Hidden Markov models; Maximum likelihood decoding; Rate-distortion; Speech; Speech coding; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
DOI :
10.1109/ICASSP.1990.115573
