1 Tsinghua University, Beijing, China
Model source
Source excerpt
1 Tsinghua University, Beijing, China
Sources
1 sourceVerified Sep 12
Model artifacts
1 artifactSource excerpts
2 excerpts--- license: cc-by-sa-4.0 datasets: - sebchw/musdb18 pipeline_tag: audio-to-audio tags: - music --- <p align="center"> <img src="https://cslikai.cn/Apollo/asserts/apollo-logo.png" alt="Logo" width="150"/> </p> <p align="center"> <strong>Kai Li<sup>1,2</sup>, Yi Luo<sup>2</sup></strong><br> <strong><sup>1</sup>Tsinghua University, Beijing, China</strong><br> <strong><sup>2</sup>Tencent AI Lab, Shenzhen, China</strong><br> <a href="#">ArXiv</a> | <a href="https://cslikai.cn/Apollo/">Demo</a> <p align="center"> <img src="https://visitor-badge.laobi.icu/badge?page_id=JusperLee.Apollo" alt="访客统计" /> <img src="https://img.shields.io/github/stars/JusperLee/Apollo?style=social" alt="GitHub stars" /> <img alt="Static Badge" src="https://img.shields.io/badge/license-CC%20BY--SA%204.0-blue"> </p> <p align="center"> # 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](https://cslikai.cn/Apollo/). - [2024.09.106] Apollo checkpoints and pre-trained models are available for download. ## ⚡️ Installation clone the repository ```bash git clone https://github.com/JusperLee/Apollo.git && cd Apollo conda create --name look2hear --file look2hear.yml conda activate look2hear ``` ## 🖥️ Usage ### 🗂️ Datasets Apollo is trained on the MUSDB18-HQ and MoisesDB datasets. To download the datasets, run the following commands: ```bash wget https://zenodo.org/records/3338373/files/musdb18hq.zip?download=1 wget https://ds-website-downloads.55c2710389d9da776875002a7d018e59.r2.cloudflarestorage.com/moisesdb.zip ``` During data pre...
Source context: 0 downloads · 40 likes · Pipeline audio-to-audio · Repo JusperLee/Apollo