A controlled study of the suitability and limitations of static modeling of speech

摘要

A static model (SM) in the form of a single vector is proposed to represent the temporal properties of a sequence of speech feature vectors. In contrast to a hidden Markov model which captures the conditional probabilities of state transitions of consecutive observations x/sub t/ and x/sub t+1/ over time, an SM captures their average joint probabilities of belonging to a pair of phonetic classes omega /sub i/ and omega /sub j/ without any Markovian assumption. An artificial vocabulary of ten words is designed to study the limitations of SM. Experimental results indicate that apart from a rather mild limitation of SM in handling certain types of vocabulary, SM performs better in terms of recognition rate as far as isolated word recognition is concerned.