Learning with segment boundaries for hierarchical HMMs

Authors:
Naoto Gotou;Akira Hayashi;Nobuo Suematu
Affiliations:
Graduate School of Information Sciences, Hiroshima City University, Hiroshima, Japan;Graduate School of Information Sciences, Hiroshima City University, Hiroshima, Japan;Graduate School of Information Sciences, Hiroshima City University, Hiroshima, Japan
Venue:
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
Year:
2005

Citing 2
Cited 2

Fundamentals of speech recognition

Fundamentals of speech recognition
The Hierarchical Hidden Markov Model: Analysis and Applications

Machine Learning

A discriminative model corresponding to hierarchical HMMs

IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Sports video segmentation using a hierarchical hidden CRF

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hierarchical hidden Markov models (HHMMs) can be used for time series segmentation. However, it is difficult to obtain a desirable segmentation result, because the form of learning for HHMMs is unsupervised. In the paper, we present a semisupervised learning algorithm for HHMMs. It is semisupervised in the sense that the supervisor teaches segmentation boundaries but not segment labels. The learning performance of the proposed algorithm is demonstrated through an experiment using music data.