Discriminative semi-parametric trajectory model for speech recognition

摘要

Hidden Markov models (HMMs) are the most commonly used acoustic model for speech recognition. In HMMs, the probability of successive observations is assumed independent given the state sequence. This is known as the conditional independence assumption. Consequently, the temporal (inter-frame) correlations are poorly modelled. This limitation may be reduced by incorporating some form of trajectory modelling. In this paper, a general perspective on trajectory modelling is provided, where time-varying model parameters are used for the Gaussian components. A discriminative semi-parametric trajectory model is then described where the Gaussian mean vector and covariance matrix parameters vary with time. The time variation is modelled as a semi-parametric function of the observation sequence via a set of cent-roids in the acoustic space. The model parameters are estimated discriminatively using the minimum phone error (MPE) criterion. The performance of these models is investigated and benchmarked against a state-of-the-art CUHTK Mandarin evaluation systems.