MusicCaps

Dataset Information
Modalities
Texts, Music
Languages
English, Vietnamese
Introduced
2023
License
CC BY-SA 4.0
Homepage
Official Website
Contents

Overview

MusicCaps is a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts. For each 10-second music clip, MusicCaps provides:

1) A free-text caption consisting of four sentences on average, describing the music and

2) A list of music aspects, describing genre, mood, tempo, singer voices, instrumentation, dissonances, rhythm, etc.

Source:MusicLM: Generating Music From Text

Variants: MusicCaps

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Text-to-Music Generation ETTA ETTA: Elucidating the Design Space … 2024-12-26
Text-to-Music Generation FLUXMusic FLUX that Plays Music 2024-09-01
Text-to-Music Generation Stable Audio Open Stable Audio Open 2024-07-19
Text-to-Music Generation TANGO-AF Improving Text-To-Audio Models with Synthetic … 2024-06-18
Text-to-Music Generation MeLFusion (image-conditioned) MeLFusion: Synthesizing Music from Image … 2024-06-07
Text-to-Music Generation OpenMusic (QA-MDT) Quality-aware Masked Diffusion Transformer for … 2024-05-24
Text-to-Music Generation Stable Audio Fast Timing-Conditioned Latent Audio Diffusion 2024-02-07
Text-to-Music Generation AudioLDM2-large AudioLDM 2: Learning Holistic Audio … 2023-08-10
Text-to-Music Generation AudioLDM2-music AudioLDM 2: Learning Holistic Audio … 2023-08-10
Text-to-Music Generation AudioLDM 2-Full AudioLDM 2: Learning Holistic Audio … 2023-08-10
Text-to-Music Generation JEN-1 JEN-1: Text-Guided Universal Music Generation … 2023-08-09
Text-to-Music Generation MusicGen w/ random melody (1.5B) Simple and Controllable Music Generation 2023-06-08
Text-to-Music Generation MusicGen w/o melody (1.5B) Simple and Controllable Music Generation 2023-06-08
Text-to-Music Generation MusicGen w/o melody (3.3B) Simple and Controllable Music Generation 2023-06-08
Text-to-Music Generation MeLoDy Efficient Neural Music Generation 2023-05-25
Text-to-Music Generation Noise2Music spectrogram Noise2Music: Text-conditioned Music Generation with … 2023-02-08
Text-to-Music Generation Noise2Music waveform Noise2Music: Text-conditioned Music Generation with … 2023-02-08
Text-to-Music Generation Riffusion MusicLM: Generating Music From Text 2023-01-26
Text-to-Music Generation Mubert MusicLM: Generating Music From Text 2023-01-26
Text-to-Music Generation MusicLM MusicLM: Generating Music From Text 2023-01-26

Research Papers

Recent papers with results on this dataset:

External Links: