Title :
Isolated word recognition using Markov chain models
Author_Institution :
Dept. of Comput. Sci., Nanjing Univ., China
fDate :
11/1/1995 12:00:00 AM
Abstract :
The paper describes how Markov chains may be applied to speech recognition. In this application, a spectral vector is modeled by a state of the Markov chain, and an utterance is represented by a sequence of states. The Markov chain model (MCM) offers a substantial reduction in computation, but at the expense of a significant increase in memory requirement when compared to the hidden Markov model (HMM). Experiments on isolated word recognition show that the MCM achieved results that are comparable to those of the HMMs tested for comparison
Keywords :
Markov processes; spectral analysis; speech processing; speech recognition; HMM; Markov chain models; experiments; hidden Markov model; isolated word recognition; memory requirement; spectral vector; speech modelling; speech recognition; Computational efficiency; Costs; Hidden Markov models; Lagrangian functions; Maximum likelihood estimation; Parameter estimation; Smoothing methods; Speech; State-space methods; Vocabulary;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
