Title :
Stochastic modeling of temporal information in speech for hidden Markov models
Author :
Dai, Jianing ; MacKenzie, Iain G. ; Tyler, Jon E M
Author_Institution :
Dept. of Comput. Sci., Nanjing Univ., China
Abstract :
A Markov chain, namely, the temporal Markov model, is used to model the time-ordering information of the feature vectors of a spoken word. An empirical method is suggested to combine the temporal Markov model (TMM) with the hidden Markov model (HMM) for word recognition. Experiments on speaker-independent isolated English alphabet recognition showed that this method is effective in terms of improved recognition.
Keywords :
hidden Markov models; speech analysis and processing; speech recognition; empirical method; feature vectors; hidden Markov models; speaker-independent isolated English alphabet recognition; spoken word; stochastic modeling; temporal Markov model; temporal information; time-ordering information; word recognition; Hidden Markov models; Humans; Markov processes; Prototypes; Signal generators; Signal processing; Speech processing; Speech recognition; Stochastic processes; Testing;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
