Multi-sensor adaptive speech enhancement using diverse sub-band processing

Citation

Hussain A (2000) Multi-sensor adaptive speech enhancement using diverse sub-band processing. International Journal of Robotics and Automation, 15 (2), pp. 78-84.

Abstract
A multi-microphone adaptive speech-enhancement scheme has been developed which employs diverse sub-band processing. A computationally-efficient robust metric is presented which is capable of real-time implementation, in order to automatically select a suitable form of diverse processing within each sub-band. Comparative results achieved in simulation experiments using both simulated room and real-reverberant automobile data demonstrate that the proposed scheme employing diverse sub-band processing is capable of outperforming conventional full-band noise-cancellation schemes.

Keywords
Speech Enhancement; Sub-band Processing; Multi-Sensor Noise Cancellation; Coherence Estimation

Journal
International Journal of Robotics and Automation: Volume 15, Issue 2