MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation
Open paper
Benchmark
Model
Rank
Results
music-source-separation-on-musdb18
TAK2
#15
SDR (avg): 6.04
SDR (vocals): 7.16
SDR (drums): 6.81
SDR (bass): 5.40
…
Rank counts only results with a code link.