A MICROPHONE ARRAY FOR CAR ENVIRONMENTS

This paper describes a microphone array for speech recording in car environments. The array is designed for hands-free radiotelephone, and is also used as a front-end for an automatic speech recognition system (this study has been realised within the european ESPRIT project ARS ''adverse environment recognition of speech''). We first summarise the adaptive beamforming techniques that we have used. We then describe several aspects of the implementation of the array (configuration, design of fixed beamformers, adaptation, complexity reduction). In the last section, we evaluate the performance of the array. Two measures of performance have been retained, one is the signal-to-noise ratio, and the other is the score obtained with the speech recognition system.