Cadenza Project
Published August 9, 2024 | Version V1.0.0
Dataset Open

Cadenza Challenge ICASSP 2024 (ICASSP24): Submission audio samples for the ICASSP 2024 Cadenza Grand Challenge - Baseline systems

Authors/Creators

  • 1. ROR icon University of Salford
  • 2. ROR icon University of Sheffield

Contributors

  • 1. ROR icon University of Nottingham
  • 2. ROR icon University of Salford
  • 3. ROR icon University of Leeds
  • 4. ROR icon University of Sheffield

Description

Cadenza

This is the baseline submission data for the ICASSP 2024 Cadenza Grand Challenge (ICASSP24).

The Cadenza Challenges are improving music production and processing for people with a hearing loss. According to The World Health Organization, 430 million people worldwide have a disabling hearing loss. Studies show that not being able to understand lyrics is an important problem to tackle for those with hearing loss. Consequently, this task is about improving the intelligibility of lyrics when listening to pop/rock over headphones. But this needs to be done without losing too much audio quality - you can't improve intelligibility just by turning off the rest of the band! We will be using one metric for intelligibility and another metric for audio quality, and giving you different targets to explore the balance between these metrics.

Please see the Cadenza website for a full description of the data

Technical info

This dataset contains the baselines submission audio signals for the ICASSP24 challenge. The signals correspond to 10-second consecutive segments of the MUSDB18-HQ test split.  The signals were processed according the ICASSP24 requirements. Please refer to the Cadenza challenge website and to the paper for details.

Description of files:

  1. submission_T001.zip: package containing the audio signals of Baseline 1
  2. submission_T002.zip: package containing the audio signals of Baseline 2
  3. gains.json:  Json file with all posible gain combinations.
  4. head_loudspeaker_positions.json: Json file with the different combination of head rotations
  5. listeners.test.json: Json file with the listeners audiograms
  6. scenes.test.json: Json file with the scenes descriptions
  7. scene_listeners.test.json: Json file with the list of listeners to process per scene
  8. musdb18.test.json: Json file with the description of the MUSDB18-HQ test split
  9. HAAQI_scores.zip: ZIP file containing one CSV per Team with HAAQI scores

The audio signals are organised as:

enhanced_signals/scene_<Scene_ID>_<Listener_ID>_remix.flac

where:

  • Scene_ID:  is the unique id to identify each scene.
  • Listener_ID:  53 unique ids to identify each listener.

Other

Cite as:

G. Roa-Dabike, M. A. Akeroyd, S. Bannister, J. P. Barker, T. J. Cox, B. Fazenda, J. Firth, S. Graetzer, A. Greasley, R. R. Vos and W. M. Whitmer, "The First Cadenza Challenges: Using Machine Learning Competitions to Improve Music for Listeners With a Hearing Loss," in IEEE Open Journal of Signal Processing.

Notes

This repository only includes the submission samples for both baselines. If you need access to the submission samples for all submissions, please contact us at cadenzachallengecontact@gmail.com.

All submissions description:

  • 19 packages (including baselines)
  • A total size of 384 GB (including baselines)
  • 19,200 signals per team

Files

gains.json

Files (39.3 GB)

Name Size Download all
md5:9ab13633eb9584cc3dcd8baae9826f79
118.6 kB Preview Download
md5:e1dfcc5a686e1f44ce4b20719e738492
40.6 MB Preview Download
md5:3944cbfd2853563b8198c58614088e06
19.5 kB Preview Download
md5:8bd264e7fcf0c44028ad05ab28d8e11c
20.6 kB Preview Download
md5:40e05f6b2e5fcb755c21309215d5c005
9.9 kB Preview Download
md5:94b5bcdc2b37e0dab4b1ee7672e54e19
352.3 kB Preview Download
md5:e9292223fb8a2fca5f069154a22f6cf7
193.3 kB Preview Download
md5:311a7ec50711ba2f13a74fddcde28a08
19.6 GB Preview Download
md5:ee7f4a504c50af016bc8c60d6f3e158b
19.7 GB Preview Download

Additional details

Funding

UK Research and Innovation
EnhanceMusic: Machine Learning Challenges to Revolutionise Music Listening for People with Hearing Loss EP/W019434/1

Software

Repository URL
https://github.com/claritychallenge/clarity
Programming language
Python