Automatic Generation of Non-uniform HMM Topologies Based on the MDL Criterion

Takatoshi JITSUHIRO  Tomoko MATSUI  Satoshi NAKAMURA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E87-D   No.8   pp.2121-2129
Publication Date: 2004/08/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
Keyword: 
speech recognition,  acoustic model,  topology training,  MDL criterion,  SSS algorithm,  

Full Text: PDF(1.2MB)>>
Buy this Article




Summary: 
We propose a new method to introduce the Minimum Description Length (MDL) criterion to the automatic generation of non-uniform, context-dependent HMM topologies. Phonetic decision tree clustering is widely used, based on the Maximum Likelihood (ML) criterion, and only creates contextual variations. However, the ML criterion needs to predetermine control parameters, such as the total number of states, empirically for use as stop criteria. Information criteria have been applied to solve this problem for decision tree clustering. However, decision tree clustering cannot create topologies with various state lengths automatically. Therefore, we propose a method that applies the MDL criterion as split and stop criteria to the Successive State Splitting (SSS) algorithm as a means of generating contextual and temporal variations. This proposed method, the MDL-SSS algorithm, can automatically create adequate topologies without such predetermined parameters. Experimental results for travel arrangement dialogs and lecture speech show that the MDL-SSS can automatically stop splitting and obtain more appropriate HMM topologies than the original one.