# The Sound Demixing Challenge 2023 unicodex2013 Cinematic Demixing Track

arXiv: https://arxiv.org/abs/2308.06981 · HTML: https://mlsanity.com/paper/2308.06981/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2023.

## Built on by (most cited first, 11 of 11)

- [TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation](https://mlsanity.com/paper/2410.01469/) (2024)
- [Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling](https://mlsanity.com/paper/2504.15071/) (2025)
- [AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner](https://mlsanity.com/paper/2512.10571/) (2025)
- [A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation](https://mlsanity.com/paper/2309.02539/) (2023)
- [Apollo: Band-sequence Modeling for High-Quality Audio Restoration](https://mlsanity.com/paper/2409.08514/) (2024)
- [Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support](https://mlsanity.com/paper/2407.07275/) (2024)
- [Summary of The Inaugural Music Source Restoration Challenge](https://mlsanity.com/paper/2601.04343/) (2026)
- [Semantic visually-guided acoustic highlighting with large vision-language models](https://mlsanity.com/paper/2601.08871/) (2026)
- [Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation](https://mlsanity.com/paper/2408.03588/) (2024)
- [ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation](https://mlsanity.com/paper/2408.08729/) (2024)
- [PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditions](https://mlsanity.com/paper/2607.10345/) (2026)

## Abstract (arXiv)

This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the structure of the competition and the datasets used. Especially, we detail CDXDB23, a new hidden dataset constructed from real movies that was used to rank the submissions. The paper also offers insights into the most successful approaches employed by participants. Compared to the cocktail-fork baseline, the best-performing system trained exclusively on the simulated Divide and Remaster (DnR) dataset achieved an improvement of 1.8 dB in SDR, whereas the top-performing system on the open leaderboard, where any data could be used for training, saw a significant improvement of 5.7 dB. A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail.