Speech Dereverberation Using Fully Convolutional Networks

Abstract

Speech derverberation using a single microphone is addressed in this paper. Motivated by the recent success of the fully convolutional networks (FCN) in many image processing applications, we investigate their applicability to enhance the speech signal represented by short-time Fourier transform (STFT) images. We present two variations: a "U-Net" which is an encoder-decoder network with skip connections and a generative adversarial network (GAN) with U-Net as generator, which yields a more intuitive cost function for training. To evaluate our method we used the data from the REVERB challenge, and compared our results to other methods under the same conditions. We have found that our method outperforms the competing methods in most cases.

Stats

• citations59
• S2 citations—
• github stars0
• HF likes0
• heat score13.34
• arxiv keyernst2018speech

Related papers

• Skipconvnet: Skip Convolutional Neural Network For Speech Dereverberation Using Optimally Smoothed Spectral Mapping (2020)10.21
• Deep Convolutional Neural Network-based Inverse Filtering Approach For Speech De-reverberation (2020)7.16
• Investigating Generative Adversarial Networks Based Speech Dereverberation For Robust Speech Recognition (2018)10.74
• Speech Dereverberation With Context-aware Recurrent Neural Networks (2017)10.35
• Single-channel Speech Dereverberation Via Generative Adversarial Training (2018)8.09
• RVAE-EM: Generative Speech Dereverberation Based On Recurrent Variational Auto-encoder And Convolutive Transfer Function (2023)7.50
• Speech Dereverberation Using Nonnegative Convolutive Transfer Function And Spectro Temporal Modeling (2017)10.48
• Convolutive Prediction For Monaural Speech Dereverberation And Noisy-reverberant Speaker Separation (2021)11.39