Stochastic trajectory modeling for speech recognition
Yifan Gong, Jean‐Paul Haton · 2002
Models observations of phoneme-based speech units as clusters of trajectories in their parameter space. The trajectories are modeled by a mixture of state sequences of multi-variate Gaussian density functions, optimized at the state sequence level. The duration of trajectories are integrated in the modeling. The authors also provide an algorithm for sentence recognition based on the modeling. In an alphabet recognition task the resulting system trained in context-independent mode demonstrated substantially better recognition accuracy, compared to a conventional context-dependent, whole word HMM.>