Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer

We propose a scheme that improves the robustness of continuous HMM systems that use mixture observation densities by sharing the same mixture components among different HMM states. The sets of HMM states that share the same mixture components are determined automatically using agglomerative clusteri...

Full description

Saved in:
Bibliographic Details
Main Authors: Digalakis, V., Murveit, H.
Format: Conference Proceeding
Language:English
Subjects:
Automatic speech recognition
Computational complexity
Error analysis
Hidden Markov models
Maximum a posteriori estimation
Robustness
Speech recognition
Stochastic processes
Training data
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a scheme that improves the robustness of continuous HMM systems that use mixture observation densities by sharing the same mixture components among different HMM states. The sets of HMM states that share the same mixture components are determined automatically using agglomerative clustering techniques. Experimental results on the Wall-Street Journal Corpus show that our new form of output distributions achieves a 25% reduction in error rate over typical tied-mixture systems.< >
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1994.389212