Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
A framework for the cooperation of learning algorithms
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Integrating time alignment and neural networks for high performance continuous speech recognition
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
A discriminative neural prediction system for speech recognition
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
| Hi-index | 0.00 |
In this paper, we give a detailed description of a new hybrid system for accoustic decoding. It uses a cooperation between a multi-layer perceptron (MLP) and an adaptive dynamic programming (DP) module. We show how to train the whole system in an optimal way using an adaptive gradient technique. The DP module optimizes cost functions inspired from k-means and learning vector quantization (L VQ). This module allows the training of synthetic references which incorporate discriminant information and improves the performances and/or speed of usual dynamic programming systems. We analyse and provide solutions to some problems which may occur when training the whole hybrid system and show that they are common to many modular architectures. These theoretical issues are illustrated through experiments on an isolated-word database.