Cognitive-driven convolutional beamforming using EEG-based auditory attention decoding
This work addresses speech enhancement for hearing aids or assistive devices by using brain signals to identify the target speaker, though it appears incremental as it builds on existing cognitive-driven methods.
The paper tackled the problem of enhancing a target speaker in multi-speaker scenarios by proposing a cognitive-driven speech enhancement system that combines neural-network-based mask estimation, convolutional beamformers, and EEG-based auditory attention decoding, with results showing it outperforms state-of-the-art systems in challenging conditions.
The performance of speech enhancement algorithms in a multi-speaker scenario depends on correctly identifying the target speaker to be enhanced. Auditory attention decoding (AAD) methods allow to identify the target speaker which the listener is attending to from single-trial EEG recordings. Aiming at enhancing the target speaker and suppressing interfering speakers, reverberation and ambient noise, in this paper we propose a cognitive-driven multi-microphone speech enhancement system, which combines a neural-network-based mask estimator, weighted minimum power distortionless response convolutional beamformers and AAD. To control the suppression of the interfering speaker, we also propose an extension incorporating an interference suppression constraint. The experimental results show that the proposed system outperforms the state-of-the-art cognitive-driven speech enhancement systems in challenging reverberant and noisy conditions.