Speaker adaptation based on judge neural networks for real world implementations of Voice-Command systems

Abstract

A "Voice-Command" system was implemented for isolated word recognition tasks in real-world environments. While the Zero-Crossings with the Peak Amplitudes (ZCPA) model successfully extracted noise-robust features, a new speaker adaptation algorithm was developed to increase recognition accuracy. A multi-layer Perceptron (MLP) was trained to transform the user-specific speech features into those of standard users. This feature transformation was done for each frame, and only a small subset of the word classes was used in the adaptation for the convenience of users. To cope with performance differences between adapted and non-adapted word classes, a simple judge network was introduced and resulted in much better recognition rates for the whole word classes. (C) 2000 Elsevier Science Inc. All rights reserved.