Bayesian regularisation methods in a hybrid MLP-HMM system
نویسندگان
چکیده
We have applied Bayesian regularisation methods to multi-layer perceptron (MLP) training in the context of a hybrid MLP– HMM (hidden Markov model) continuous speech recognition system. The Bayesian framework adopted here allows an objective setting of the regularisation parameters, according to the training data. Experiments were carried out on the ARPA Resource Management database.
منابع مشابه
A comparison of hybrid HMM architectures using global discriminative training
This paper presents a comparison of di erent model architectures for TIMIT phoneme recognition. The baseline is a conventional diagonal covariance Gaussian mixture HMM. This system is compared to two di erent hybrid MLP/HMMs, both adhering to the same restrictions regarding input context and output states as the Gaussian mixtures. All free parameters in the three systems are jointly optimised u...
متن کاملConnectionist Probability Estimators in Hmm Using Genetic Clustering Application for Speech Recognition and Medical Diagnosis
The main goal of this paper is to compare the performance which can be achieved by five different approaches analyzing their applications’ potentiality on real world paradigms. We compare the performance obtained with (1) Multi-network RBF/LVQ structure (2) Discrete Hidden Markov Models (HMM) (3) Hybrid HMM/MLP system using a Multi LayerPerceptron (MLP) to estimate the HMM emission probabilitie...
متن کاملNew feedback method of hybrid HMM/ANN methods for continuous speech recognition
In the continuous speech recognition, the co-pronunciation between two successive phonemes seriously disturb recognition effect. It is difficult for pure hidden Markov model(HMM) methods to cope with the co-pronunciation, because HMM methods consider that two successive frames of speech are independant. The hybrid HMM and artificial neural networks(ANN) methods with feedback MLP[1,3] provide th...
متن کاملThai Word Recognition Using Hybrid MLP-HMM
The Hidden Markov Model (HMM) is a popular model for speech recognition systems. However, one of the difficulties in applying HMM is the estimation of the emission probabilities for constructing the Gaussian Mixture Models (GMMs). In this paper, we propose a method to estimate the state emission probabilities in HMM framework using Artificial Neural Networks (ANNs), particularly the Multi-Layer...
متن کاملHybrid neural network/hidden Markov model continuous-speech recognition
n M In this paper we present a hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recognib tion system, in which the advantages of both approaches are combined y using MLPs to estimate the state-dependent observation probabilities p of an HMM. New MLP architectures and training procedures are resented which allow the modeling of multiple distributio...
متن کامل