Deep Convolutional Neural Network-based Inverse Filtering Approach for Speech De-reverberation
This addresses speech clarity issues in noisy environments, but it is incremental as it builds on existing CNN and CTF methods.
The paper tackles speech de-reverberation in realistic conditions with long room impulse responses by using a deep CNN to estimate an inverse filter based on the convolutive transfer function model, achieving better performance than benchmark algorithms.
In this paper, we introduce a spectral-domain inverse filtering approach for single-channel speech de-reverberation using deep convolutional neural network (CNN). The main goal is to better handle realistic reverberant conditions where the room impulse response (RIR) filter is longer than the short-time Fourier transform (STFT) analysis window. To this end, we consider the convolutive transfer function (CTF) model for the reverberant speech signal. In the proposed framework, the CNN architecture is trained to directly estimate the inverse filter of the CTF model. Among various choices for the CNN structure, we consider the U-net which consists of a fully-convolutional auto-encoder network with skip-connections. Experimental results show that the proposed method provides better de-reverberation performance than the prevalent benchmark algorithms under various reverberation conditions.