For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System
Keiichiro OURA Heiga ZEN Yoshihiko NANKAKU Akinobu LEE Keiichi TOKUDA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/11/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
speech recognition, hidden Markov model, hidden semi-Markov model, weighted finite-state transducer,
Full Text: PDF(531.3KB)>>
In a hidden Markov model (HMM), state duration probabilities decrease exponentially with time, which fails to adequately represent the temporal structure of speech. One of the solutions to this problem is integrating state duration probability distributions explicitly into the HMM. This form is known as a hidden semi-Markov model (HSMM). However, though a number of attempts to use HSMMs in speech recognition systems have been proposed, they are not consistent because various approximations were used in both training and decoding. By avoiding these approximations using a generalized forward-backward algorithm, a context-dependent duration modeling technique and weighted finite-state transducers (WFSTs), we construct a fully consistent HSMM-based speech recognition system. In a speaker-dependent continuous speech recognition experiment, our system achieved about 9.1% relative error reduction over the corresponding HMM-based system.