Joint Neural AEC and Beamforming with Double-Talk Detection
This work addresses the problem of acoustic feedback and noise in communication systems for users, but it is incremental as it builds on previous self-attentive RNN beamformer methods.
The paper tackles acoustic echo cancellation in full-duplex communication systems by proposing a deep learning-based joint AEC and beamforming model (JAECBF) that integrates multi-channel neural-AEC with a joint AEC-RNN beamformer and double-talk detection, and it outperforms other multi-channel AEC and denoising systems in speech recognition rate and overall speech quality.
Acoustic echo cancellation (AEC) in full-duplex communication systems eliminates acoustic feedback. However, nonlinear distortions induced by audio devices, background noise, reverberation, and double-talk reduce the efficiency of conventional AEC systems. Several hybrid AEC models were proposed to address this, which use deep learning models to suppress residual echo from standard adaptive filtering. This paper proposes deep learning-based joint AEC and beamforming model (JAECBF) building on our previous self-attentive recurrent neural network (RNN) beamformer. The proposed network consists of two modules: (i) multi-channel neural-AEC, and (ii) joint AEC-RNN beamformer with a double-talk detection (DTD) that computes time-frequency (T-F) beamforming weights. We train the proposed model in an end-to-end approach to eliminate background noise and echoes from far-end audio devices, which include nonlinear distortions. From experimental evaluations, we find the proposed network outperforms other multi-channel AEC and denoising systems in terms of speech recognition rate and overall speech quality.