Microphone Array Generalization for Multichannel Narrowband Deep Speech Enhancement
This addresses the challenge of array-specific limitations in speech enhancement systems, enabling more flexible deployment across different hardware setups, though it is incremental as it builds on existing narrowband networks.
The paper tackles the problem of training a deep neural network for multichannel speech enhancement that generalizes well to unseen microphone arrays by using data from various array geometries, resulting in performance close to or exceeding array-specific training and outperforming other methods.
This paper addresses the problem of microphone array generalization for deep-learning-based end-to-end multichannel speech enhancement. We aim to train a unique deep neural network (DNN) potentially performing well on unseen microphone arrays. The microphone array geometry shapes the network's parameters when training on a fixed microphone array, and thus restricts the generalization of the trained network to another microphone array. To resolve this problem, a single network is trained using data recorded by various microphone arrays of different geometries. We design three variants of our recently proposed narrowband network to cope with the agnostic number of microphones. Overall, the goal is to make the network learn the universal information for speech enhancement that is available for any array geometry, rather than learn the one-array-dedicated characteristics. The experiments on both simulated and real room impulse responses (RIR) demonstrate the excellent across-array generalization capability of the proposed networks, in the sense that their performance measures are very close to, or even exceed the network trained with test arrays. Moreover, they notably outperform various beamforming methods and other advanced deep-learning-based methods.