Kai Li1,2, Yi Luo2 1Tsinghua University, Beijing, China 2Tencent AI Lab, Shenzhen, China ArXiv | Demo
访客统计
GitHub stars
Static Badge
Apollo: Band-sequence Modeling for High-Quality Music Restoration in Compressed Audio
📖 Abstract
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.
🔥 News
[2024.09.10] Apollo is now available on ArXiv and Demo.
[2024.09.106] Apollo checkpoints and pre-trained models are available for download.
During data preprocessing, we drew inspiration from music separation techniques and implemented the following steps:
Source Activity Detection (SAD):
We used a Source Activity Detector (SAD) to remove silent regions from the audio tracks, retaining only the significant portions for training.
Data Augmentation:
We performed real-time data augmentation by mixing tracks from different songs. For each mix, we randomly selected between 1 and 8 stems from the 11 available tracks, extracting 3-second clips from each selected stem. These clips were scaled in energy by a random factor within the range of [-10, 10] dB relative to their original levels. The selected clips were then summed together to create simulated mixed music.
Simulating Dynamic Bitrate Compression:
We simulated various bitrate scenarios by applying MP3 codecs with bitrates of [24000, 32000, 48000, 64000, 96000, 128000].
Rescaling:
To ensure consistency across all samples, we rescaled both the target and the encoded audio based on their maximum absolute values.
Saving as HDF5:
After preprocessing, all data (including the source stems, mixed tracks, and compressed audio) was saved in HDF5 format, making it easy to load for training and evaluation purposes.
🚀 Training
To train the Apollo model, run the following command:
python train.py --conf_dir=configs/apollo.yml
🎨 Evaluation
To evaluate the Apollo model, run the following command:
Here, you can include a brief overview of the performance metrics or results that Apollo achieves using different bitrates
Different methods' SDR/SI-SNR/VISQOL scores for various types of music, as well as the number of model parameters and GPU inference time. For the GPU inference time test, a music signal with a sampling rate of 44.1 kHz and a length of 1 second was used.
Apollo is developed by the Look2Hear at Tsinghua University.
Citation
If you use Apollo in your research or project, please cite the following paper:
@article{li2024apollo,
title={Apollo: Band-sequence Modeling for High-Quality Music Restoration in Compressed Audio},
author={Li, Kai and Luo, Yi},
journal={xxxxxx},
year={2024}
}
Contact
For any questions or feedback regarding Apollo, feel free to reach out to us via email: tsinghua.kaili@gmail.com
