Connectionist Optimisation of Tied Mixture Hidden Markov Models
نویسندگان
چکیده
Horacio Franco Michael Cohen SRI International Menlo Park CA 94025 USA Issues relating to the estimation of hidden Markov model (HMM) local probabilities are discussed. In particular we note the isomorphism of radial basis functions (RBF) networks to tied mixture density modellingj additionally we highlight the differences between these methods arising from the different training criteria employed. We present a method in which connectionist training can be modified to resolve these differences and discuss some preliminary experiments. Finally, we discuss some outstanding problems with discriminative training.
منابع مشابه
Tied posteriors: an approach for effective introduction of context dependency in hybrid NN/HMM LVCSR
This papers presents a method to improve the recognition rate of hybrid connectionist/HMM speech recognition systems. At the same time this approach allows the easy introduction of context dependent models in the hybrid framework. The approach is based on a standard hybrid connectionist/HMM recognizer, in which the neural nets are trained to estimate the a posteriori probabilities for all phone...
متن کاملA Tied-Mixture 2-D HMM Face Recognition System
In this paper, a simplified 2-D second-order Hidden Markov Model (HMM) with tied state mixtures is applied to the face recognition problem. The mixture of the model states is fully-tied across all models for lower complexity. Tying HMM parameters is a well-known solution for the problem of insufficient training data leading to nonrobust estimation. We show that parameter tying in HMM also enhan...
متن کاملSpeech Recognition Using Monophone and Triphone Based Continuous Density Hidden Markov Models
Speech Recognition is a process of transcribing speech to text. Phoneme based modeling is used where in each phoneme is represented by Continuous Density Hidden Markov Model. Mel Frequency Cepstral Coefficients (MFCC) are extracted from speech signal, delta and double-delta features representing the temporal rate of change of features are added which considerably improves the recognition accura...
متن کاملHybrid Training Method for Tied Mixture Density Hidden Markov Models Using Learning Vector Quantization and Viterbi Estimation
In this work the output density functions of hidden Markov models are phoneme-wise tied mixture Gaussians. For training these tied mixture density HMMs, modiied versions of the Viterbi training and LVQ based corrective tuning are described. The initialization of the mean vectors of the mixture Gaussians is performed by rst composing small Self-Organizing Maps representing each phoneme and then ...
متن کاملTied-Posteriors: A New Hybrid Speech Recognition Technology with Generic Capabilities and High Portability
This paper presents a new method for estimating the emission probabilities of general hybrid connectionist/HMM recognition systems. Contrary to the traditional hybrid approach, where a neural network is used for providing posterior probabilities in order to model the emission probabilities of one-state HMMs, our new tiedposterior approach uses the posterior probabilities resulting from the neur...
متن کامل