New state clustering of hidden Markov network with Korean phonological rules for speech recognition

Se Jin Oh, Hyun Yeol Chung, Cheol Jun Hwang, Bum Koog Kim, Akinori Ito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper, we adopted the Korean phonological rules to state clustering of contextual domain for representing the unknown contexts and tying the model parameters of new states in state clustering of SSS (Successive State Splitting). We used the Decision Tree-based Successive State Splitting (DT-SSS) algorithm, which splits the state of contexts based on phonetic knowledge. The SSS algorithm proposed by Sagayama is a powerful technique, which designed topologies of tied-state HMMs automatically, but it doesnt generate unknown contexts adequately. In addition it has some problem in the contextual splits procedure. In this paper, the speaker independent Korean isolated word and sentence recognition experiments are carried out. In word recognition experiments, this method shows an average of 6.3% higher word recognition accuracy than the conventional HMMs. And in sentence recognition experiments, it shows an average of 90.9% recognition accuracy.

Original languageEnglish
Title of host publication2001 IEEE Fourth Workshop on Multimedia Signal Processing
EditorsJ.-L. Dugelay, K. Rose, J.-L. Dugelay, K. Rose
Pages39-44
Number of pages6
Publication statusPublished - 2001 Dec 1
Externally publishedYes
Event2001 IEEE fourth Workshop on Multimedia Signal Processing - Cannes, France
Duration: 2001 Oct 32001 Oct 5

Publication series

Name2001 IEEE Fourth Workshop on Multimedia Signal Processing

Other

Other2001 IEEE fourth Workshop on Multimedia Signal Processing
CountryFrance
CityCannes
Period01/10/301/10/5

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'New state clustering of hidden Markov network with Korean phonological rules for speech recognition'. Together they form a unique fingerprint.

Cite this