Title :
Query-based HMM training method for ASR
Author :
Kyung, YounJeong ; Jung, Jio ; Moon, SeokYong
Author_Institution :
Dept. of Comput. Sci., Tokyo Inst. of Technol., Japan
Abstract :
A query-based hidden Markov model (HMM) training method for refinement of classification boundary is proposed. For this work, an HMM inversion with minimisation of mean-square error (MMSE) criterion is defined. The proposed algorithm is compared with conventional training methods on an isolated digit recognition problem. The proposed query-based HMM learning algorithm decreased the recognition error rate to 60% in conducted experiments.
Keywords :
hidden Markov models; least mean squares methods; speech recognition; MMSE criterion; active learning; automatic speech recognition; classification boundary refinement; inversion algorithm; isolated digit recognition; query-based hidden Markov model training method;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20030774
