【数据科学赛】THE SOUND DEMIXING CHALLENGE #音乐声源分离 #$42,000

CompHub 实时聚合多平台的数据类(Kaggle、天池…)和OJ类(Leetcode、牛客…）比赛。本账号会推送最新的比赛消息，欢迎关注！

更多比赛信息见 CompHub主页

---

以下内容摘自比赛主页（点击文末阅读原文进入）

Part1赛题介绍

题目

THE SOUND DEMIXING CHALLENGE

• MUSIC DEMIXING TRACK (音乐声源分离赛道)：Music source separation of an audio signal into separate tracks for vocals, bass, drums, and other.

• CINEMATIC SOUND DEMIXING TRACK (电影声源分离赛道)：Source separation of a cinematic audio track into dialogue, sound-effects and misc.

举办平台

AICrowd

主办方

背景

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.

Part2时间安排

• December 5, 2022 - Start Date.

• February 22, 2023 - Entry Deadline. You must accept the competition rules before this date in order to compete.

• February 22, 2023 - Team Merger Deadline. This is the last day participants may join or merge teams.

• March 1, 2023 - Final Submission Deadline.

All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if they deem it necessary.

Part3奖励机制

Music Demixing Track (MDX) 32,000 USD

Label Noise Task: 10,000 USD

• 1st prize: 5000 USD

• 2nd prize: 3000 USD

• 3rd prize: 2000 USD

Bleeding Task: 10,000 USD

• 1st prize: 5000 USD

• 2nd prize: 3000 USD

• 3rd prize: 2000 USD

Standard Music Source Separation Task(Open Track): 12,000 USD

• 1st prize: 5000 USD

• 2nd prize: 3000 USD

• 3rd prize: 2000 USD

• Bonus Prize (Human Evaluations): 2000 USD

Cinematic Sound Demixing Track (CDX) 10,000 USD

Leaderboard - Divide and Remaster (DnR) dataset Task : 5,000 USD

• 1st prize: 2500 USD

• 2nd prize: 1500 USD

• 3rd prize: 1000 USD

Leaderboard - Standard Cinematic Sound Separation(Open Track): 5,000 USD

• 1st prize: 2500 USD

• 2nd prize: 1500 USD

• 3rd prize: 1000 USD This is an Open Track where you can use any data you want.

Part4赛题描述

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 across a few categories.

Audio source separation has different declinations depending on the signal the system is working on. Music source separation systems take a song as input and output one track for each instrument. Speech enhancement systems take noisy speech as input and separate the speech content from the noise.

This year's SDX Challenge includes two new tracks.

MUSIC DEMIXING TRACK (MDX)

The previous edition of the MDX challenge focused on music source separation into four instruments: vocals, bass, drums, and others. This year, we extend the original formulation by requiring four instrument separation systems that are robust to specific and realistic issues in the training data.

We propose a challenge that tackles two types of such issues and sets up one leaderboard each. Additionally, we set up a third leaderboard (leaderboard C), which is free from any constraints for standard source separation systems for four instruments. This last leaderboard is similar to leaderboard B of the previous edition of the MDX challenge.

This track has three leaderboards that will be announced soon:

1. Label Noise

2. Bleeding

3. Standard Music Source Separation

CINEMATIC SOUND DEMIXING TRACK (CDX)

Cinematic sound separation is the task of separating movie audio into three tracks “dialogue”, “sound effects” and “music”. It has many applications ranging from language dubbing to upmixing of old movies to spatial audio and user interfaces for flexible listening.

Such a technology can be employed in many different areas, from entertainment to hearing aids. For example, the original master of old movies contains all the material (dialogue, music and sound effects) mixed in mono or stereo: thanks to source separation, we can retrieve the individual components and allow for up-mixing to surround systems. Sony has already restored two movies with this technology in their Columbia Classics collection.

This year's CDX has two tasks:

• Divide and Remaster (DnR) Dataset Task

• Standard Cinematic Sound Separation Task

More details on the dataset and leaderboards will be released soon.

---