Paper Info
Title
Piecewise Polynomial High-Order Hidden Markov Models with Applications in Speech Recognition
Abstract
The assumptions on the hidden Markov model will limit the output of a model to be a piecewise stationary random sequence that may not be a good fit for real processes. In this paper we propose a piecewise polynomial high-order hidden Markov model so that the output of a model can be more versatile. We derived formulas for the calculation of the probability that a given sequence is produced by a model. We also derived the posterior probability of the states and the state transitions and used them in an expectation maximization algorithm to update the model parameters. Experiments on speech recognition of Mandarin digits were conducted to investigate the effectiveness of the proposed model. Experimental results showed that the proposed model can reduce the recognition error rate compared to a baseline hidden Markov model.
Year
DOI
Venue
2016
10.1109/CIT.2016.33
2016 IEEE International Conference on Computer and Information Technology (CIT)
Keywords
Field
DocType
speech recognition,expectation maximization algorithm,piecewise,polynomial,high-order,hidden Markov model
Maximum-entropy Markov model,Markov property,Forward algorithm,Computer science,Markov model,Markov chain,Speech recognition,Variable-order Markov model,Hidden Markov model,Hidden semi-Markov model
Conference
ISBN
Citations 
PageRank 
978-1-5090-4315-6
0
0.34
References 
Authors
6
1
Name
Order
Citations
PageRank
Lee-Min Lee1468.10