The Sound Demixing Challenge 2023 unicodex2013 Cinematic Demixing Track
Not on the map. Why?
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.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Aug 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 3.
11 papers.
- 2024TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separationcited by 11
- 2025Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modelingcited by 10
- 2025AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refinercited by 9
- 2023A Generalized Bandsplit Neural Network for Cinematic Audio Source Separationcited by 8
- 2024Apollo: Band-sequence Modeling for High-Quality Audio Restorationcited by 8
- 2024Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Supportcited by 5
- 2026Summary of The Inaugural Music Source Restoration Challengecited by 1
- 2026Semantic visually-guided acoustic highlighting with large vision-language modelscited by 1
- 2024Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separationcited by 0
- 2024ConcateNet: Dialogue Separation Using Local And Global Feature Concatenationcited by 0
- 2026PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditionscited by 0
- 2026PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditions11 Jul 2026
- 2026Semantic visually-guided acoustic highlighting with large vision-language models12 Jan 2026
- 2026Summary of The Inaugural Music Source Restoration Challenge7 Jan 2026
- 2025AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner11 Dec 2025
- 2025Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling21 Apr 2025
- 2024TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation2 Oct 2024
- 2024Apollo: Band-sequence Modeling for High-Quality Audio Restoration13 Sep 2024
- 2024ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation16 Aug 2024
- 2024Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation7 Aug 2024
- 2024Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support9 Jul 2024
- 2023A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation5 Sep 2023