Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems
نویسندگان
چکیده
The results of our research presented in this paper are two-fold. First, an estimation of global posteriors is formalized in the framework of hybrid HMM/ANN systems. It is shown that hybrid HMM/ANN systems, in which the ANN part estimates local posteriors, can be used to modelize global model posteriors. This formalization provides us with a clear theory in which both REMAP and \classical" Viterbi trained hybrid systems are uni ed. Second, a new forwardbackward training of hybrid HMM/ANN systems is derived from the previous formulation. Comparisons of performance between Viterbi and forwardbackward hybrid systems are presented and discussed.
منابع مشابه
Enhancing Posterior Based Speech Recognition Systems
The use of local phoneme posterior probabilities has been increasingly explored for improving speech recognition systems. Hybrid hidden Markov model / artificial neural network (HMM/ANN) and Tandem are the most successful examples of such systems. In this thesis, we present a principled framework for enhancing the estimation of local posteriors, by integrating phonetic and lexical knowledge, as...
متن کاملDeveloping and enhancing posterior based speech recognition systems
Local state or phone posterior probabilities are often investigated as local scores (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., “Tandem”) to improve speech recognition systems. In this paper, we present initial results towards boosting these approaches by improving posterior estimates, using acoustic context (e.g., as available in the whole utterance), as well as p...
متن کاملIncorporation of HMM output constraints in hybrid NN/HMM systems during training
This paper describes a method to incorporate the HMM output constraints in frame based hybrid NN/HMM systems during training. While usually the NN parameters are adjusted to maximize the cross-entropy between the frame target probabilities and the network predictions assuming statistically independent outputs in time, in the approach described here the full likelihood of the utterance(s) using ...
متن کاملGlobal Solar Radiation Prediction for Makurdi, Nigeria Using Feed Forward Backward Propagation Neural Network
The optimum design of solar energy systems strongly depends on the accuracy of solar radiation data. However, the availability of accurate solar radiation data is undermined by the high cost of measuring equipment or non-functional ones. This study developed a feed-forward backpropagation artificial neural network model for prediction of global solar radiation in Makurdi, Nigeria (7.7322 N lo...
متن کاملA segment-based interpretation of HMM/ANN hybrids
Here we seek to understand the similarities and differences between two speech recognition approaches, namely the HMM/ANN hybrid and the posterior-based segmental model. Both these techniques create local posterior probability estimates and combine these estimates into global posteriors – but they are built on somewhat different concepts and mathematical derivations. The HMM/ANN hybrid combines...
متن کامل