The paper first points out a defect in hidden Markov modeling (HMM) of continuous speech, referred as trajectory folding phenomenon. A new approach to modeling phoneme-based speech units is then proposed, which represents the acoustic observations of a phoneme as clusters of trajectories in a parameter space. The trajectories are modeled by mixture of probability density functions of random sequence of states. Each state is associated with a multivariate Gaussian density function, optimized at state sequence level. Conditional trajectory duration probability is integrated in the modeling, An efficient sentence search procedure based on trajectory modeling is also formulated, Experiments with a speaker-dependent, 2010-word continuous speech recognition application with a word-pair perplexity of 50, using vocabulary-independent acoustic training, monophone models trained with 80 sentences per speaker, reported about 1% word error rate. The new models were experimentally compared to continuous density mixture HMM (CDHMM) on a same recognition task, and gave significantly smaller word error rates. These results suggest that the stochastic trajectory model provides a more in-depth modeling of continuous speech signals.
