Speech Dereverberation Using Fully Convolutional Networks
By Ori Ernst, Shlomo E. Chazan, Sharon Gannot, Jacob Goldberger. 2018
91 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Yossi Adi
- Eliya Nachmani
- Lior Wolf
- Luc Van Gool
- Xiaogang Wang
- Dacheng Tao
- Trevor Darrell
- Andrew Zisserman
In Signal Processing
- Yossi Adi
- Lior Wolf
- Eliya Nachmani
- Alexandre D'efossez
- Adam Polyak
- Gabriel Synnaeve
- Wei-Ning Hsu
- Jade Copet
Citations in the corpus
- Voice Separation with an Unknown Number of Multiple Speakers (2020, methodology): “Additionally, most previous research was conducted at the spectrum level of the input signal (Wang & Chen, 2018; Ernst et al., 2018).”