Title :
Planning, neural networks and Markov models for automatic speech recognition
Author_Institution :
Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
Abstract :
The possibility of programming the execution of multilayered networks is considered. This planned execution produces a coded description of speech segments in terms of degrees of evidence of phonetic features. Continuous-parameter-density hidden Markov models are suggested for modeling the time evolution of feature degrees. Experimental results on plosive sounds, other consonants, and vowels are presented
Keywords :
Markov processes; computerised pattern recognition; encoding; neural nets; speech recognition; automatic speech recognition; coded description; consonants; continuous-parameter-density hidden Markov models; evidence; multilayered networks; network programming; neural networks; phonetic features; planning; plosive sounds; speech segments; vowels; Automatic programming; Automatic speech recognition; Computer science; Hidden Markov models; Learning systems; Magnetooptic recording; Neural networks; Speech coding; Vector quantization; Vocabulary;
Conference_Titel :
Pattern Recognition, 1988., 9th International Conference on
Conference_Location :
Rome
Print_ISBN :
0-8186-0878-1
DOI :
10.1109/ICPR.1988.28252
