Deep-learning driven reverberation-aware microphone array speech enhancement
Abstract
Traditional microphone array speech enhancement algorithms suffer from significant performance degradation in complex and diverse speech application scenarios. The adoption of data-driven microphone array optimization models based on machine learning (deep learning) is capable of achieve significant performance improvements. However, such methods exhibit data dependency. A deep learning based reverberation-aware microphone array speech enhancement algorithm is proposed. The proposed algorithm first obtains the reverberation pattern through reverberation-aware environment probing, and then extracts the main component features to train reverberation-aware network (RAN). This operation enables the RAN to have the ability to decouple and generate adaptive de-reverberation beamforming coefficients based on reverberation features. Simulation and experiments are provided to verify the effectiveness and robustness of the proposed method in different reverbrant environments.
Related Papers
- → Spherical microphone array for spatial sound localization for a mobile robot(2012)18 cited
- → Circular microphone array for robot's audition(2006)24 cited
- → Performance evaluation of beamforming techniques for speech enhancement(2017)6 cited
- → Speech enhancement using microphone array in moving vehicle environment(2004)13 cited
- Microphone Array Speech Enhancement Based on Adjustable Beamformer Generalized Sidelobe Canceller(2013)