Perceptually-motivated Environment-specific Speech Enhancement
2019
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.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
36
References
7
Citations
NaN
KQI