Second Cadenza Lyric Intelligibility Prediction (CLIP2) Dataset
Authors/Creators
-
1.
University of Sheffield
-
2.
University of Salford
Contributors
-
1.
University of Salford
- 2. University of Nottingham
-
3.
University of Manchester
- 4. Univerity of Nottingham
-
5.
University of Leeds
Description
CLIP2 is a dataset for lyric intelligibility prediction in music. It is used in the Second Cadenza Lyric Intelligibility Prediction Challenge.
Understanding the lyrics in music is key for music enjoyment [1]. People with hearing loss can have difficulty clearly and effortlessly hearing lyrics, however [2]. In speech technology, having metrics to automatically evaluate intelligibility has driven improvements in speech enhancement. We want to do the same for music with lyrics!
A detailed description of the challenge can be found on our website
Overview of Files
- cadenza_clip2_data.train.v1.0.tar.gz : Package with the training audio and metadata
- cadenza_clip2_data.valid.v1.0.tar.gz : Package with the validation audio data and metadata
- cadenza_clip2_data.eval.v1.0.tar.gz : Package with the evaluation audio data and metadata
- CHANGELOG.md: History with the changes of the data
- README.md: readme file
License
This dataset is shared under the CPC-4 License (Creative Production Commons 4.0).
Notes (English)
The data used for generating the CLIP2 dataset will be release on December 2026, after the closing of the CLIP2 challenge.
Data used to generate the music
* `original.train.v1.0.tar.gz` - Release on December 2026
* `original.valid.v1.0.tar.gz` - Release on December 2026
* `original.eval.v1.0.tar.gz` - Release on December 2026
* `master prompts.zip` - Release on December 2026
* `Prompts for ElevenLabs.zip` - Release on December 2026
Files
README.md
Files
(16.7 GB)
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
References
- [1] Fine, P. A. and Ginsborg, J., 2014. Making myself understood: perceived factors affecting the intelligibility of sung text. Frontiers in psychology, 5, 809.
- [2] Greasley, A., Crook, H. and Fulford, R., 2020. Music listening and hearing aids: perspectives from audiologists and their patients. International Journal of Audiology, 59(9), pp.694-706.