Evaluation of a rapid environment adaptation algorithm in adverse environments

Abstract

This paper reports results for a rapid environment adaptation algorithm in adverse car environments. It is known that the difference between training and testing environments degrades speech recognition performance. This degradation becomes serious especially in applications such as telephone speech recognition and speech recognition inside a running vehicle, where the testing environment may drastically change. To solve this problem, a rapid environmental adaptation method (hereafter referred to as REALISE) is proposed and its performance is measured in telephone speech recognition. REALISE estimates the differences in multiplicative and additional noise in the spectral domain between the training and testing environments and uses them to adapt acoustic features of reference patterns to the testing environment. Utterances in a car were also recorded to investigate the performance of REALISE under more severe conditions. The testing data were 100 city names uttered by three males and three females under three running conditions (idling, 50 kph, and 100 kph). Whereas the average recognition rate achieved by a conventional spectral subtraction technique was 75.6%, REALISE achieved 85.7%. This result proves the effectiveness of REALISE in a very noisy vehicle environment.