Title :
Segmental corrective training for hidden Markov model parameter estimation in speech recognition
Author :
Kim, H.R. ; Lee, Hwang Soo
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul, South Korea
Abstract :
A modified corrective training method using state segment information in the hidden Markov model is presented. The proposed algorithm is shown to result in a higher recognition rate than the conventional corrective training method and requires less computation.
Keywords :
learning systems; neural nets; parameter estimation; speech analysis and processing; speech recognition; virtual machines; hidden Markov model; higher recognition rate; less computation; modified corrective training method; neural networks; parameter estimation; speech recognition; state segment information;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19911021
