GTZAN
Canonical9papers using it
2022first seen
The GTZAN dataset is a benchmark that contains a collection of music tracks used to evaluate music genre classification performance.
Papers using GTZAN (8)
- M2D-CLAP: Masked Modeling Duo Meets CLAP For Learning General-purpose Audio-language RepresentationS-KEY: Self-supervised Learning of Major and Minor Keys from AudioWhisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM TrainingEvaluating Pretrained General-Purpose Audio Representations for Music Genre ClassificationSinging Beat Tracking With Self-supervised Front-end and Linear
TransformersSingNet: A Real-time Singing Voice Beat and Downbeat Tracking SystemLeveraging Pre-Trained Autoencoders for Interpretable Prototype Learning
of Music AudioM2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose
Audio-Language Representation