Speech Recognition Using Linear Dynamic Models

Using dialogue-based dynamic language models for improving speech recognition

We present a new approach to dynamically create and manage different language models to be used on a spoken dialogue system. We apply an interpolation based approach, using several measures obtained by the Dialogue Manager to decide what LM the system will interpolate and also to estimate the interpolation weights. We propose to use not only semantic information (the concepts extracted from eac...

Hidden feature models for speech recognition using dynamic Bayesian networks

In this paper, we investigate the use of dynamic Bayesian networks (DBNs) to explicitly represent models of hidden features, such as articulatory or other phonological features, for automatic speech recognition. In previous work using the idea of hidden features, the representation has typically been implicit, relying on a single hidden state to represent a combination of features. We present a...

Recognition using linear models

Using linear combinations of models to solve object recognition problems is not a new idea, still it’s widely use in current research. One of the motivations for using linear models is that they enable us to use well-known techniques from Linear Algebra to do the hard work. Indeed, powerful tools (ex: Matlab) exist to solve large system of linear equations, or to give optimally estimated soluti...

Linear Gaussian Models for Speech Recognition

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 ...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words