[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[AUDITORY] ICASSP Grand Challenge: Lyric Intelligibility Prediction



This ICASSP signal processing challenge is now live and the data ready to download at https://cadenzachallenge.org/
Cadenza is working to improve music for those with hearing loss. Hearing loss is a growing global problem due to the aging population and increased exposure to loud sound. Hearing loss can make picking out lyrics more difficult.
In speech technology, having metrics to automatically evaluate intelligibility has driven improvements in speech enhancement. We want to do the same for music. There has been little research into Lyric Intelligibility Prediction, so there is lots of scope to learn from Speech Intelligibility Prediction and Music Information Retrieval and do novel research.
The top 5 ranked teams will be invited to submit papers to ICASSP-2026, Barcelona, Spain.
We will challenge entrants to develop systems that predict lyric intelligibility from song excerpts of popular Western music. The systems will take stereo audio as input and estimate the word correct rate a listener is likely to achieve in a perceptual test.
What will be provided:
Important Dates:


Trevor Cox
Professor of Acoustic Engineering
Newton Building, University of Salford, Salford M5 4WT, UK.
Mobile: 07986 557419
www.acoustics.salford.ac.uk
@trevor_cox