论文信息 - Neural Network - Gaussian Mixture Hybrid for Speech Recognition or Density Estimation

Neural Network - Gaussian Mixture Hybrid for Speech Recognition or Density Estimation

The subject of this paper is the integration of multi-layered Artificial Neural Networks (ANN) with probability density functions such as Gaussian mixtures found in continuous density Hidden Markov Models (HMM). In the first part of this paper we present an ANN/HMM hybrid in which all the parameters of the system are simultaneously optimized with respect to a single criterion. In the second part of this paper, we study the relationship between the density of the inputs of the network and the density of the outputs of the networks. A few experiments are presented to explore how to perform density estimation with ANNs.

[1] Yoshua Bengio,et al. Artificial neural networks and their application to sequence recognition , 1991 .

[2] Yoshua Bengio,et al. Phonetically motivated acoustic parameters for continuous speech recognition using artificial neural networks , 1991, Speech Commun..

[3] Hervé Bourlard,et al. Speech pattern discrimination and multilayer perceptrons , 1989 .

[4] P. J. Green,et al. Density Estimation for Statistics and Data Analysis , 1987 .

[5] Esther Levin,et al. Word recognition using hidden control neural architecture , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[6] John S. Bridle,et al. Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters , 1989, NIPS.