Background noise reduction via dual-channel scheme for speech recognition in vehicular environment

This work concerns an effective dual-channel noise reduction method to increase the performance of robust speech recognition in a vehicular environment. While various single channel methods have already been developed and dual-channel methods have been studied somewhat, their effectiveness in real environments, such as in vehicular, has not yet been formally proven in terms of achieving an acceptable performance level. Our aim is to remedy the low performance of the single and dual-channel noise reduction methods. In particular, we propose a dual-channel noise reduction method based on a high-pass filter and front-end processing, using the eigendecomposition method. Representative experiments were conducted with a real multichannel car corpus and results were compared with respect to the microphone arrangements. From the analysis and results, we show that the enhanced eigendecomposition method, combined with high-pass filter, indeed significantly improves the speech recognition performance under a dual-channel environment.