TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/MUSDB18

MUSDB18

AudioVarious (see link)

The MUSDB18 is a dataset of 150 full lengths music tracks (~10h duration) of different genres along with their isolated drums, bass, vocals and others stems.

The dataset is split into training and test sets with 100 and 50 songs, respectively. All signals are stereophonic and encoded at 44.1kHz.

Source: https://sigsep.github.io/datasets/musdb.html#musdb18-compressed-stems Image Source: https://sigsep.github.io/datasets/musdb.html#musdb18-compressed-stems

Benchmarks

2D Classification/SDR (avg)2D Classification/SDR (vocals)2D Classification/SDR (drums)2D Classification/SDR (bass)2D Classification/SDR (other)Hearing Aid and device processing/HAAQIMusic Source Separation/SDR (avg)Music Source Separation/SDR (vocals)Music Source Separation/SDR (drums)Music Source Separation/SDR (bass)Music Source Separation/SDR (other)

Related Benchmarks

MUSDB18-HQ/2D Classification/SDR (avg)MUSDB18-HQ/2D Classification/SDR (bass)MUSDB18-HQ/2D Classification/SDR (drums)MUSDB18-HQ/2D Classification/SDR (others)MUSDB18-HQ/2D Classification/SDR (vocals)MUSDB18-HQ/Music Source Separation/SDR (avg)MUSDB18-HQ/Music Source Separation/SDR (bass)MUSDB18-HQ/Music Source Separation/SDR (drums)MUSDB18-HQ/Music Source Separation/SDR (others)MUSDB18-HQ/Music Source Separation/SDR (vocals)

Statistics

Papers
106
Benchmarks
11

Links

Homepage

Tasks

2D ClassificationAudio Source SeparationCadenza 1 - Task 1 - HeadphoneHearing Aid and device processingMusic Source Separation