A tutorial on hidden Markov models and selected applications in speech recognition
Readings in speech recognition
Continuously variable duration hidden Markov models for automatic speech recognition
Computer Speech and Language
Proceedings of the 2011 Workshop on Historical Document Imaging and Processing
Hi-index | 0.00 |
Explicit duration modeling has been shown to increase the effectiveness of hidden Markov models in automatic speech recognition. Ferguson found the optimum parameters of the duration model for the case where duration is assumed to be distributed according to a non-parametric probability mass function. Levinson determined the best gamma density to model duration. In this paper, duration is assumed to be modeled by some probability mass function in the exponential family. An iterative procedure for determining the maximum likelihood parameters is presented. Also given is a method for choosing an appropriate member from the exponential family.