A novel objective function for improved phoneme recognition using time-delay neural networks

Authors:
J. B. Hampshire, II;A. H. Waibel
Affiliations:
Carnegie-Mellon Univ., Pittsburgh, PA;-
Venue:
IEEE Transactions on Neural Networks
Year:
1990

Citing 0
Cited 6

Data classification with multilayer perceptrons using a generalized error function

Neural Networks
Infant cry classification to identify asphyxia using time-frequency analysis and radial basis neural networks

Expert Systems with Applications: An International Journal
Sensitivity Analysis for Selective Learning by Feedforward Neural Networks

Fundamenta Informaticae
Sensitivity Analysis for Selective Learning by Feedforward Neural Networks

Fundamenta Informaticae
Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural network

Computer Methods and Programs in Biomedicine
Self-Adjustable Neural Network for speech recognition

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Single-speaker and multispeaker recognition results are presented for the voice-stop consonants /b,d,g/ using time-delay neural networks (TDNNs) with a number of enhancements, including a new objective function for training these networks. The new objective function, called the classification figure of merit (CFM), differs markedly from the traditional mean-squared-error (MSE) objective function and the related cross entropy (CE) objective function. Where the MSE and CE objective functions seek to minimize the difference between each output node and its ideal activation, the CFM function seeks to maximize the difference between the output activation of the node representing incorrect classifications. A simple arbitration mechanism is used with all three objective functions to achieve a median 30% reduction in the number of misclassifications when compared to TDNNs trained with the traditional MSE back-propagation objective function alone