Product of Gaussians for speech recognition

Authors:
M. J. F. Gales;S. S. Airey
Affiliations:
Cambridge University, Engineering Department, Trumpington Street, Cambridge CB2 1PZ, UK;Cambridge University, Engineering Department, Trumpington Street, Cambridge CB2 1PZ, UK
Venue:
Computer Speech and Language
Year:
2006

Citing 5
Cited 7

Factorial Hidden Markov Models

Machine Learning - Special issue on learning with probabilistic representations
A unifying review of linear Gaussian models

Neural Computation
Mixtures of probabilistic principal component analyzers

Neural Computation
Mixed Memory Markov Models: Decomposing Complex Stochastic Processes as Mixtures of Simpler Ones

Machine Learning
Speech recognition with dynamic bayesian networks

Speech recognition with dynamic bayesian networks

Online kernel density estimation for interactive learning

Image and Vision Computing
Arabic phoneme identification using conventional and concurrent neural networks in non native speakers

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications
Audio query by example using similarity measures between probability density functions of features

EURASIP Journal on Audio, Speech, and Music Processing - Special issue on scalable audio-content analysis
A hierarchical feature fusion framework for adaptive visual tracking

Image and Vision Computing
Dynamic world modelling by dichotomic information sets and graphical inference with focus on 3d facial pose tracking

SAMT'10 Proceedings of the 5th international conference on Semantic and digital media technologies
Language model cross adaptation for LVCSR system combination

Computer Speech and Language
Collaborative topic regression with social regularization for tag recommendation

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, there has been interest in the use of classifiers based on the product of experts (PoE) framework. PoEs offer an alternative to the standard mixture of experts (MoE) framework. It may be viewed as examining the intersection of a series of experts, rather than the union as in the MoE framework. This paper presents a particular implementation of PoEs, the normalised product of Gaussians (PoG). Here, each expert is a Gaussian mixture model. In this work, the PoG model is presented within a hidden Markov model framework. This allows the classification of variable length data, such as speech data. Training and initialisation procedures are described for this PoG system. The relationship of the PoG system with other schemes, including covariance modeling schemes, is also discussed. In addition the scheme is shown to be related to a standard speech recognition approach, multiple stream systems. The PoG system performance is examined on an automatic speech recognition task, Switchboard. The performance is compared to standard Gaussian mixture systems and multiple stream systems.