add arxiv link
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ tags:
|
|
| 13 |
- phase
|
| 14 |
---
|
| 15 |
# εar-VAE: High Fidelity Music Reconstruction Model
|
| 16 |
-
[[Demo Page](https://eps-acoustic-revolution-lab.github.io/EAR_VAE/)] - [[Codes](https://github.com/Eps-Acoustic-Revolution-Lab/EAR_VAE)]
|
| 17 |
|
| 18 |
This repository contains the official inference code for εar-VAE, aa 44.1 kHz music signal reconstruction model that rethinks and optimizes VAE training for audio. It targets two common weaknesses in existing open-source VAEs—phase accuracy and stereophonic spatial representation—by aligning objectives with auditory perception and introducing phase-aware training. Experiments show substantial improvements across diverse metrics, with particular strength in high-frequency harmonics and spatial characteristics.
|
| 19 |
|
|
|
|
| 13 |
- phase
|
| 14 |
---
|
| 15 |
# εar-VAE: High Fidelity Music Reconstruction Model
|
| 16 |
+
[[Demo Page](https://eps-acoustic-revolution-lab.github.io/EAR_VAE/)] - [[Codes](https://github.com/Eps-Acoustic-Revolution-Lab/EAR_VAE)] - [[Paper](http://arxiv.org/abs/2509.14912)]
|
| 17 |
|
| 18 |
This repository contains the official inference code for εar-VAE, aa 44.1 kHz music signal reconstruction model that rethinks and optimizes VAE training for audio. It targets two common weaknesses in existing open-source VAEs—phase accuracy and stereophonic spatial representation—by aligning objectives with auditory perception and introducing phase-aware training. Experiments show substantial improvements across diverse metrics, with particular strength in high-frequency harmonics and spatial characteristics.
|
| 19 |
|