To refer to this page use:
|Abstract:||This paper introduces a deep learning approach to enhance speech recordings made in a specific environment. A single neural network learns to ameliorate several types of recording artifacts, including noise, reverberation, and non-linear equalization. The method relies on a new perceptual loss function that combines adversarial loss with spectrogram features. Both subjective and objective evaluations show that the proposed approach improves on state-of-the-art baseline methods.|
|Citation:||Su, Jiaqi, Adam Finkelstein, and Zeyu Jin. "Perceptually-motivated Environment-specific Speech Enhancement." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019): pp. 7015-7019. IEEE, 2019. doi:10.1109/ICASSP.2019.8683654|
|Pages:||7015 - 7019|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.