Continuous Speech Recognition Based on General Factor Dependent Acoustic Models

Hiroyuki SUZUKI  Heiga ZEN  Yoshihiko NANKAKU  Chiyomi MIYAJIMA  Keiichi TOKUDA  Tadashi KITAMURA  

IEICE TRANSACTIONS on Information and Systems   Vol.E88-D   No.3   pp.410-417
Publication Date: 2005/03/01
Online ISSN: 
DOI: 10.1093/ietisy/e88-d.3.410
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Feature Extraction and Acoustic Medelings
continuous speech recognition,  triphone HMMs,  context clustering,  Bayesian networks,  voice characteristic,  noise environment,  

Full Text: PDF(487.4KB)>>
Buy this Article

This paper describes continuous speech recognition incorporating the additional complement information, e.g., voice characteristics, speaking styles, linguistic information and noise environment, into HMM-based acoustic modeling. In speech recognition systems, context-dependent HMMs, i.e., triphone, and the tree-based context clustering have commonly been used. Several attempts to utilize not only phonetic contexts, but additional complement information based on context (factor) dependent HMMs have been made in recent years. However, when the additional factors for testing data are unobserved, methods for obtaining factor labels is required before decoding. In this paper, we propose a model integration technique based on general factor dependent HMMs for decoding. The integrated HMMs can be used by a conventional decoder as standard triphone HMMs with Gaussian mixture densities. Moreover, by using the results of context clustering, the proposed method can determine an optimal number of mixture components for each state dependently of the degree of influence from additional factors. Phoneme recognition experiments using voice characteristic labels show significant improvements with a small number of model parameters, and a 19.3% error reduction was obtained in noise environment experiments.