A SPEECH ENHANCEMENT SYSTEM BASED ON NEGATIVE BEAMFORMING AND SPECTRAL SUBTRACTION

Beamforming Filtering techniques are well known for their angular selectivity in speech enhancement applications with noisy backgrounds. Besides, Negative Beamformers achieve an important advantage compared with classical array structures: the lower number of signal sensors (microphones) required. The scheme that is proposed in this paper combines Negative Beamforming and Spectral Subtraction in order to obtain large gains in the SNR at a reasonable low computational cost. This method may be used to eliminate or enhance a specific signal using a binaural array. Applications of this technique may be found in Surveillance Systems, Domotic Control and also, to improve Speech Recognition.