Incorporation of HMM output constraints in hybrid NN/HMM systems during training
نویسنده
چکیده
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 also the HMM output constraints, like for conventional HMM systems, is maximized. This is achieved by maximizing the state occupation probabilities after a forward/backward pass using the scaled likelihoods coming from the network. Making a simplifying approximation for the derivative for the back-propagation through the forward/backward pass, tests show that the proposed method gives consistently higher string (phoneme) recognition rates than the conventional approach that aims at maximizing cross-entropy at the frame level.
منابع مشابه
Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems
Speaker variability is one of the major error sources for ASR systems. Speaker adaptation estimates speaker specific models from the speaker independent ones to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. One of the commonly adopted approaches is the transformation based method. In this paper, the discriminative input and output transform...
متن کاملNovel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition
In this work we propose two hybrid NN/HMM systems for handwriting recognition. The tied posterior model approximates the output probability density function of a Hidden Markov Model (HMM) with a neural net (NN). This allows a discriminative training of the model. The second system is the tandem approach: A NN is used as part of the feature extraction, and then a standard HMM apporach is applied...
متن کاملProtein Modeling with Hybrid Hidden Markov Model/Neural Network Architectures
Hidden Markov Models (HMMs) are useful in a number of tasks in computational molecular biology, and in particular to model and align protein families. We argue that HMMs are somewhat optimal within a certain modeling hierarchy. Single first order HMMs, however, have two potential limitations: a large number of unstructured parameters, and a built-in inability to deal with long-range dependencie...
متن کاملA NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction
This paper deals with a hybrid NN/HMM architecture for continuous speech recognition. We present a novel approach to set up a neural linear or nonlinear feature transformation that is used as a preprocessor on top of the HMM system’s RBF-network to produce discriminative feature vectors that are well suited for being modeled by mixtures of Gaussian distributions. In order to omit the computatio...
متن کاملAdvanced training methods and new network topologies for hybrid MMI-connectionist/HMM speech recognition systems
This paper deals with the construction and optimization of a hybrid speech recognition system that consists of a combination of a neural vector quantizer (VQ) and discrete HMMs. In our investigations an integration of VQ based classi cation in the continuous classi er framework is given and some constraints are derived that must hold for the pdfs in the discrete pattern classi er context. Furth...
متن کامل