Apollo uses a frequency band-split module, band-sequence modeling, and frequency band reconstruction to restore the audio quality of MP3-compressed music.
|
|
|
|
Tencent AI Lab |
|
|
|
|
|
Apollo uses a frequency band-split module, band-sequence modeling, and frequency band reconstruction to restore the audio quality of MP3-compressed music.
| Apollo is a novel music restoration method designed to address distortions and artefacts caused by audio codecs, especially at low bitrates. Operating in the frequency domain, Apollo uses a frequency band-split module, band-sequence modeling, and frequency band reconstruction to restore the audio quality of MP3-compressed music. It divides the spectrogram into sub-bands, extracts gain-shape representations, and models both sub-band and temporal information for high-quality audio recovery. Trained with a Generative Adversarial Network (GAN), Apollo outperforms existing SR-GAN models on the MUSDB18-HQ and MoisesDB datasets, excelling in complex multi-instrument and vocal scenarios, while maintaining efficiency. |
|
|
|
| Ground Truth | Codec Wav | Apollo |
|---|---|---|
|
 |
 |
|
 |
 |
|
 |
 |
| Ground Truth | Codec Wav | Apollo |
|---|---|---|
|
 |
 |
|
 |
 |
|
 |
 |
| Ground Truth | Codec Wav | Apollo |
|---|---|---|
|
 |
 |
|
 |
 |
|
 |
 |
| Ground Truth | Codec Wav | Apollo |
|---|---|---|
|
 |
 |
|
 |
 |
|
 |
 |
| Ground Truth | Codec Wav | Apollo |
|---|---|---|
|
 |
 |
|
 |
 |
|
 |
 |
| ➥ BibTeX: |
|
@article{li2024apollo, title={Apollo: Band-sequence Modeling for High-Quality Music Restoration in Compressed Audio}, author={Li, Kai and Luo, Yi}, year={2024}, journal={arXiv preprint arXiv:2409.08514} } |
Acknowledgements |