eCite Digital Repository

State mixture modelling applied to speech and speaker recognition


Tran, D and Wagner, M and Zheng, T, State mixture modelling applied to speech and speaker recognition, Journal of Pattern Recognition Letter, 20, (11-13) pp. 1449-1456. ISSN 0167-8655 (1999) [Refereed Article]

DOI: doi:10.1016/S0167-8655(99)00113-0


In state mixture modelling (SMM), the temporal structure of the observation sequences is represented by the state joint probability distribution where mixtures of states are considered. This technique is considered in an iterative scheme via maximum likelihood estimation. A fuzzy estimation approach is also introduced to cooperate with the SMM model. This new approach not only saves calculations from 2N TT (HMM direct calculation) and N 2T (Forward-backward algorithm) to just only 2NT calculations, but also achieves a better recognition result.

Item Details

Item Type:Refereed Article
Research Division:Information and Computing Sciences
Research Group:Library and information studies
Research Field:Human information interaction and retrieval
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Information systems, technologies and services not elsewhere classified
UTAS Author:Zheng, T (Dr Tongtao Zheng)
ID Code:15899
Year Published:1999
Deposited By:Asian Languages and Studies
Deposited On:1999-08-01
Last Modified:2000-05-23

Repository Staff Only: item control page