3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in singer-identification-5
No benchmarks available.
Use these libraries to find singer-identification-5 models and implementations
No subtasks available.
The proposed approach to self-supervised contrastive learning to acquire feature representations attentive to either vocal timbre or singing expression but not to the other by changing how the transformations are incorporated is extended.
This paper employs open-unmix, an open source tool with state-of-the-art performance in source separation, to separate the vocal and instrumental tracks of music, and investigates two means to train a singer identification model: by learning from the separated vocal only, or from an augmented set of data where the singers are artificially made to sing in different contexts.
Adding a benchmark result helps the community track progress.