The Gamma MLP for Speech
نویسندگان
چکیده
We deene a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma lters (as proposed by de Vries and Principe (de Vries & Principe 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We nd that both the inclusion of gamma lters in all layers, and the inclusion of synaptic gains, improves the performance of the Gamma MLP. We compare the Gamma MLP with TDNN, Back-Tsoi FIR MLP, and Back-Tsoi IIR MLP architectures, and a local approximation scheme. We nd that the Gamma MLP results in a substantial reduction in error rates.
منابع مشابه
The Gamma MLP for Speech Phoneme Recognition
We define a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma filters (as proposed by de Vries and Principe (de Vries and Principe, 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We find that both the inclusion of gamma filters in all layer...
متن کاملThe Gamma MLP for Speech PhonemeRecognitionSteve
We deene a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma lters (as proposed by de Vries and Principe (de Vries & Principe 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We nd that both the inclusion of gamma lters in all layers, and the...
متن کاملThe Gamma MLP – Using Multiple Temporal Resolutions for Improved Classification
We have previously introduced the Gamma MLP which is defined as an MLP with the usual synaptic weights replaced by gamma filters and associated gain terms throughout all layers. In this paper we apply the Gamma MLP to a larger scale speech phoneme recognition problem, analyze the operation of the network, and investigate why the Gamma MLP can perform better than alternatives. The Gamma MLP is c...
متن کاملLearning Temporal Dependencies in Connectionist Speech Recognition
Hybrid connectionistfHMM systems model time both using a Markov chain and through properties of a connectionist network. In this paper, we discuss the nature of the time dependence currently employed in our systems using recurrent networks (RNs) and feed-forward multi-layer perceptrons (MLPs). In particular, we introduce local recurrences into a MLP to produce an enhanced input representation. ...
متن کاملEmpirical comparison of two multilayer perceptron-based keyword speech recognition algorithms
In this paper, an empirical comparison of two multilayer perceptron (MLP)-based techniques for keyword speech recognition (wordspotting) is described. The techniques are the predictive neural model (PNM)-based wordspotting, in which the MLP is applied as a speech pattern predictor to compute a local distance between the acoustic vector and the phone model, and the hybrid HMM/MLP-based wordspott...
متن کامل