Deep Convolutional Neural Network-based Inverse Filtering Approach For Speech De-reverberation

Abstract

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.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keychung2020deep

Related papers

• Speech Dereverberation Using Fully Convolutional Networks (2018)13.34
• Convolutive Prediction For Monaural Speech Dereverberation And Noisy-reverberant Speaker Separation (2021)11.39
• Skipconvnet: Skip Convolutional Neural Network For Speech Dereverberation Using Optimally Smoothed Spectral Mapping (2020)10.21
• Rec-rir: Monaural Blind Room Impulse Response Identification Via Dnn-based Reverberant Speech Reconstruction In STFT Domain (2025)3.06
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Speech Dereverberation With Context-aware Recurrent Neural Networks (2017)10.35
• Receptive Field Analysis Of Temporal Convolutional Networks For Monaural Speech Dereverberation (2022)6.34
• Speech Dereverberation Using Nonnegative Convolutive Transfer Function And Spectro Temporal Modeling (2017)10.48