metadata
license: apache-2.0
language:
- en
tags:
- hearing loss
- challenge
- signal processing
- source separation
- lyrics intelligibility
Cadenza Challenge: CAD2-Task1
This repo contains the NonCausal Lyrics/Accompaniment separation model. This model separates the vocal line from the instrumental accompaniment used in the CDA2-Task1 baseline system.
Dataset
The model was trained on the training split of the MUSDB18-HQ dataset.