GTZAN

GTZAN is a dataset for musical genre classification of audio signals. The dataset consists of 1,000 audio tracks, each of 30 seconds long. It contains 10 genres, each represented by 100 tracks. The tracks are all 22,050Hz Mono 16-bit audio files in WAV format. The genres are: blues, classical, country, disco, hiphop, j

Papers using GTZAN (7)

S-KEY: Self-supervised Learning of Major and Minor Keys from Audio2025 · 1 citesWhisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training2026Evaluating Pretrained General-Purpose Audio Representations for Music Genre Classification2026SingNet: A Real-time Singing Voice Beat and Downbeat Tracking System2023 · 3 citesSinging Beat Tracking With Self-supervised Front-end and Linear Transformers2022 · 1 citesLeveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio2024M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation2024