Parametric trajectory mixtures for LVCSR

Parametric trajectory models explicitly represent the temporal evolution of the speech features as a Gaussian process with time-varying parameters. HMMs are a special case of such models, one in which the trajectory constraints in the speech segment are ignored by the assumption of conditional independence across frames within the segment. In this paper, we investigate in detail some extensions to our trajectory modeling approach aimed at improving LVCSR performance: (i) improved modeling of mixtures of trajectories via better initialization, (ii) modeling of context dependence, and (iii) improved segment boundaries by means of search. We will present results in terms of both phone classi cation and recognition accuracy on the Switchboard corpus.