Abstract not found

“Segmental hidden Markov models ” (SHMMs) are intended to overcome important speech-modelling limitations of the conventional-HMM approach by representing sequences (or segments) of features and incorporating the concept of trajectories to describe how features change over time. A novel feature of the approach presented in this paper is that extra-segmental variability between different examples of a sub-phonemic speech segment is modelled separately from intra-segmental variability within any one example. The extra-segmental component of the model is represented in terms of variability in the trajectory parameters, and these models are therefore referred to as “probabilistic-trajectory segmental HMMs ” (PTSHMMs). This paper presents the theory of PTSHMMs using a linear trajectory description characterized by slope and mid-point parameters, and presents theoretical and experimental comparisons between different types of PTSHMMs, simpler SHMMs and conventional HMMs. Experiments have demonstrated that, for any given feature set, a linear PTSHMM can substantially reduce the error rate in comparison with a conventional HMM, both for a connected-digit recognition task and for a phonetic classification task. Performance benefits have been demonstrated from incorporating a linear trajectory description and additionally from modelling variability in the mid-point parameter. c ○ 1999 British Crown Copyright/DERA 1.

Currently the most popular acoustic model for speech recognition is the hidden Markov model (HMM). However, HMMs are based on a series of assumptions some of which are known to be poor. In particular, the assumption that successive speech frames are conditionally independent given the discrete state that generated them is not a good assumption for speech recognition. State space models may be used to address some shortcomings of this assumption. State space models are based on a continuous state vector evolving through time according to a state evo-

Abstract not found

The aim of the research described in this paper is to overcome the modeling limitation of conventional hidden Markov models. We present a segmental model that consists of two elements. The first is a nonparametric representation of both the mean and variance trajectories, which describes the local dynamics. The second element is some parameterized transformation (e.g., random shift) of the trajectory that is global to the segment and models long-term variations such as speaker identity. Introduction Speech sounds are produced by a time-varying dynamic system. Consequently, speech signals are highly correlated and nonstationary. In spite of this fact, in most implementations of hidden Markov models (HMMs) to speech recognition, the assumption that successive observations in a state are independent and identically distributed is inherent to the model. These limitations of the HMM are due to the fact that the HMM is a frame-based approach. An alternative approach is segmental modeling, w...