Restoration of Bone-Conducted Speech with U-Net-like Model and Energy Distance Loss

Posted on 2023-06-14 Edited on 2023-07-04 In Speech Enhancement

Author: Changtao Li
Email: lichangtao@mail.ioa.ac.cn

Restoration of Bone-Conducted Speech with U-Net-like Model and Energy Distance Loss

Audio samples

We encourage our readers to listen to the following audio samples in order to experience the audio quality of our enhanced speech.

Signals	sample1	sample2	sample3	sample4
Bone-conducted Speech
Air-conducted Speech
DPT-EGNet
EBEN
Ours (l1 loss)
Ours (energy loss)

More samples

For more samples, See https://github.com/changtaoli/model-energy

1. Restoration of Bone-Conducted Speech with U-Net-like Model and Energy Distance Loss
1. 1.1. Audio samples
2. 1.2. More samples

IOA-Audio

Audio & Speech Research Group is a research group under the Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences.
The Principal Investigator of this research group is Prof. Feiran Yang (https://people.ucas.ac.cn/~feiran). Our research interests include Blind Source Separation, Array Signal Processing, Voice Anti-Spoofing, Acoustic Echo Cancellation, Speech Enhancement. Contact us: feiran@mail.ioa.ac.cn

GitHub E-Mail