A successive state splitting algorithm for efficient allophone modeling

The authors propose an algorithm, successive state splitting (SSS), for simultaneously finding an optimal set of phoneme context classes, an optimal topology, and optimal parameters for hidden Markov models (HMMs) commonly using a maximum likelihood criterion. With this algorithm, a hidden Markov ne...

Full description

Saved in:
Bibliographic Details
Main Authors: Takami, J., Sagayama, S.
Format: Conference Proceeding
Language:English
Subjects:
Acoustic distortion
Context modeling
Hidden Markov models
Intelligent networks
Laboratories
Network topology
Robustness
Speech recognition
Telephony
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The authors propose an algorithm, successive state splitting (SSS), for simultaneously finding an optimal set of phoneme context classes, an optimal topology, and optimal parameters for hidden Markov models (HMMs) commonly using a maximum likelihood criterion. With this algorithm, a hidden Markov network (HM-Net), which is an efficient representation of phoneme-context-dependent HMMs, can be generated automatically. The authors implemented this algorithm, and tested it on the recognition of six Japanese consonants ( mod b mod , mod d mod , mod g mod , mod m mod , mod n mod and mod N mod ). The HM-Net gave better recognition results with a lower number of total output probability density distributions than conventional phoneme-context-independent mixture Gaussian density HMMs.< >
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1992.225855