Scene-Agnostic Multi-Microphone Speech Dereverberation
This addresses the limitation of fixed microphone arrays in speech processing, enabling more flexible deployment in real-world scenarios, though it is an incremental improvement over existing methods.
The paper tackles the problem of speech dereverberation with microphone arrays of unknown number and positions, proposing a scene-agnostic neural network architecture that outperforms scene-aware frameworks and state-of-the-art methods like WPE in most cases, even with fewer microphones.
Neural networks (NNs) have been widely applied in speech processing tasks, and, in particular, those employing microphone arrays. Nevertheless, most existing NN architectures can only deal with fixed and position-specific microphone arrays. In this paper, we present an NN architecture that can cope with microphone arrays whose number and positions of the microphones are unknown, and demonstrate its applicability in the speech dereverberation task. To this end, our approach harnesses recent advances in deep learning on set-structured data to design an architecture that enhances the reverberant log-spectrum. We use noisy and noiseless versions of a simulated reverberant dataset to test the proposed architecture. Our experiments on the noisy data show that the proposed scene-agnostic setup outperforms a powerful scene-aware framework, sometimes even with fewer microphones. With the noiseless dataset we show that, in most cases, our method outperforms the position-aware network as well as the state-of-the-art weighted linear prediction error (WPE) algorithm.