Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/Hybrid Demucs

Hybrid Demucs

Reported on 20 benchmarks across 2 tasks · 1 paper · 20 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Music10 results

Music Source SeparationonMUSDB18
SDR (avg)· 2021-11-05
7.72
best: 9.2 (Sparse HT Demucs (fine tuned))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18
SDR (bass)· 2021-11-05
8.67
best: 10.47 (Sparse HT Demucs (fine tuned))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18
SDR (drums)· 2021-11-05
8.58
best: 10.83 (Sparse HT Demucs (fine tuned))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18
SDR (other)· 2021-11-05
5.59
best: 7.08 (Band-Split RNN (semi-sup.))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18
SDR (vocals)· 2021-11-05
8.04
best: 10.47 (Band-Split RNN (semi-sup.))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18-HQ
SDR (avg)· 2021-11-05
7.68
best: 11.99 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18-HQ
SDR (bass)· 2021-11-05
8.76
best: 13.32 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18-HQ
SDR (drums)· 2021-11-05
8.24
best: 12.91 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18-HQ
SDR (others)· 2021-11-05
5.59
best: 9.01 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
Music Source SeparationonMUSDB18-HQ
SDR (vocals)· 2021-11-05
8.13
best: 12.72 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600

Methodology10 results

2D ClassificationonMUSDB18
SDR (avg)· 2021-11-05
7.72
best: 9.2 (Sparse HT Demucs (fine tuned))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18
SDR (bass)· 2021-11-05
8.67
best: 10.47 (Sparse HT Demucs (fine tuned))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18
SDR (drums)· 2021-11-05
8.58
best: 10.83 (Sparse HT Demucs (fine tuned))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18
SDR (other)· 2021-11-05
5.59
best: 7.08 (Band-Split RNN (semi-sup.))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18
SDR (vocals)· 2021-11-05
8.04
best: 10.47 (Band-Split RNN (semi-sup.))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18-HQ
SDR (avg)· 2021-11-05
7.68
best: 11.99 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18-HQ
SDR (bass)· 2021-11-05
8.76
best: 13.32 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18-HQ
SDR (drums)· 2021-11-05
8.24
best: 12.91 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18-HQ
SDR (others)· 2021-11-05
5.59
best: 9.01 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600
2D ClassificationonMUSDB18-HQ
SDR (vocals)· 2021-11-05
8.13
best: 12.72 (BS-RoFormer (L=12, OA))
SOTA
Hybrid Spectrogram and Waveform Source Separation arXiv:2111.03600