Comparison of Smoothing Techniques for Robust Context Dependent Acoustic Modelling in Hybrid NN/HMM Systems
نویسندگان
چکیده
Hybrid Neural Network/Hidden Markov Model (NN/HMM) systems have been found to yield high quality phone recognition performance. One issue with modelling the Context Dependent (CD) NN/HMM is the robust estimation of the NN parameters to reliably predict the large number of CD state posteriors. Previously, factorization based on conditional probabilities has been commonly adopted to circumvent this problem. This paper proposes two factorization schemes based on the product-of-expert framework, depending on the choice of the experts. In addition, smoothing and interpolation schemes were introduced to improve robustness. Experimental results on the WSJCAM0 reveal that the proposed CD NN/HMM parameter estimation techniques achieved consistent improvement compared to CI hybrid systems. The best hybrid system achieves a 21.7% relative phone error rate reduction and a 17.6% word error reduction compared to a discriminative trained context dependent triphone GMM/HMM system.
منابع مشابه
Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling
One method to achieve robust speech recognition in adverse conditions including noise and reverberation is to employ acoustic modelling techniques involving neural networks. Using long short-term memory (LSTM) recurrent neural networks proved to be efficient for this task in a setup for phoneme prediction in a multi-stream GMM-HMM framework. These networks exploit a self-learnt amount of tempor...
متن کاملImproving performance on switchboard by combining hybrid HME/HMM and mixture of Gaussians acoustic models
This paper presents results of our eeorts on combining standard mixture of Gaussians acoustic model-ing 10] with a context-dependent hybrid connectionist HME/HMM architecture 3, 4] for the Switchboard corpus. Using a score normalization scheme which is independent of the stream's modeling paradigm and adaptive methods for combining multiple probability distributions, we achieve a relative decre...
متن کاملA Comparitive Survey of ANN and Hybrid HMM/ANN Architectures for Robust Speech Recognition
This paper proposes two hybrid connectionist structural acoustical models for robust context independent phone like and word like units for speaker-independent recognition system. Such structure combines strength of Hidden Markov Models (HMM) in modeling stochastic sequences and the non-linear classification capability of Artificial Neural Networks (ANN). Two kinds of Neural Networks (NN) are i...
متن کاملSpeech Recognition using Neural Networks
This thesis examines how artificial neural networks can benefit a large vocabulary, speaker independent, continuous speech recognition system. Currently, most speech recognition systems are based on hidden Markov models (HMMs), a statistical framework that supports both acoustic and temporal modeling. Despite their state-of-the-art performance, HMMs make a number of suboptimal modeling assumpti...
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 کامل