1.[About the Audio Demixing Challenge 2023](#about-the-music-demixing-challenge-2023)
1.[About the Sound Demixing Challenge 2023](#about-the-sound-demixing-challenge-2023)
2.[Evaluation](#evaluation)
3.[Baselines](#baselines)
4.[How to test and debug locally](#how-to-test-and-debug-locally)
...
...
@@ -25,7 +25,7 @@ Quick Links:
7.[Setting up your codebase](#setting-up-your-codebase)
8.[FAQs](#faqs)
# 🎶 About the Audio Demixing Challenge 2023
# 🎶 About the Sound Demixing Challenge 2023
Have you ever sung using a karaoke machine or made a DJ music mix of your favourite song? Have you wondered how hearing aids help people listen more clearly or how video conference software reduces background noise?
...
...
@@ -33,7 +33,7 @@ They all use the magic of audio separation.
Music source separation (MSS) attracts professional music creators as it enables remixing and revising songs in a way traditional equalisers don't. Suppressed vocals in songs can improve your karaoke night and provide a richer audio experience than conventional applications.
The Audio Demixing Challenge 2023 (ADX23) is an opportunity for researchers and machine learning enthusiasts to test their skills by creating a system to **perform audio source separation**.
The Sound Demixing Challenge 2023 (SDX23) is an opportunity for researchers and machine learning enthusiasts to test their skills by creating a system to **perform audio source separation**.
Given an **audio signal as input** (referred to as a "mixture"), you must **decompose in its different parts**.
...
...
@@ -94,7 +94,7 @@ You can use the submission script `source submit.sh <submission_text>`
More information on submissions can be found in [SUBMISSION.md](/docs/submission.md).
#### A high level description of the Challenge Procedure:
1.**Sign up** to join the competition [on the AIcrowd website](https://www.aicrowd.com/challenges/music-demixing-challenge-2023).
1.**Sign up** to join the competition [on the AIcrowd website](https://www.aicrowd.com/challenges/sound-demixing-challenge-2023).
2.**Clone** this repo and start developing your solution.
3.**Train** your models on IGLU, and ensure run.sh will generate rollouts.
4.**Submit** your trained models to [AIcrowd Gitlab](https://gitlab.aicrowd.com)
...
...
@@ -106,7 +106,7 @@ of the competition.
# 💽 Dataset
Download the public dataset for this task using this [link](https://www.aicrowd.com/challenges/music-demixing-challenge-2023/problems/music-demixing-track/dataset_files), you'll need to accept the rules of the competition to access the data. The data is same as the well known MUSDB18-HQ dataset and its compressed version.
Download the public dataset for this task using this [link](https://www.aicrowd.com/challenges/sound-demixing-challenge-2023/problems/music-demixing-track/dataset_files), you'll need to accept the rules of the competition to access the data. The data is same as the well known MUSDB18-HQ dataset and its compressed version.
# 📑 Setting Up Your Codebase
...
...
@@ -179,11 +179,11 @@ The machine where the submission will run will have following specifications:
You may also like the new [Cinematic Sound Demixing track](https://www.aicrowd.com/challenges/music-demixing-challenge-2023/problems/cinematic-sound-demixing-track)
You may also like the new [Cinematic Sound Demixing track](https://www.aicrowd.com/challenges/sound-demixing-challenge-2023/problems/cinematic-sound-demixing-track)
