Towards a Perceptual Loss: Using a Neural Network Codec Approximation as a Loss for Generative Audio Models
© 2019 Association for Computing Machinery. Generative audio models based on neural networks have led to considerable improvements across fields including speech enhancement, source separation, and text-to-speech synthesis. These systems are typically trained in a supervised fashion using simple ele...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association for Computing Machinery (ACM)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/137115 |