Papers › D3Net: Densely connected multidilated DenseNet for music source separation

D3Net: Densely connected multidilated DenseNet for music source separation

5 Oct 2020arXiv:2010.01733archive 2025-07-28

Naoya Takahashi, Yuki Mitsufuji

Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and up-sampling feature maps or dilated convolution. In this paper, we claim the importance of a rapid growth of a receptive field and a simultaneous modeling of multi-resolution data in a single convolution layer, and propose a novel CNN architecture called densely connected dilated DenseNet (D3Net). D3Net involves a novel multi-dilated convolution that has different dilation factors in a single layer to model different resolutions simultaneously. By combining the multi-dilated convolution with DenseNet architecture, D3Net avoids the aliasing problem that exists when we naively incorporate the dilated convolution in DenseNet. Experimental results on MUSDB18 dataset show that D3Net achieves state-of-the-art performance with an average signal to distortion ratio (SDR) of 6.01 dB.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

sony/ai-research-code officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mixed Precision DNNs: All you need is a good parametrization (arXiv:1905.11452; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Music Source Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Music Source Separation MUSDB18 D3Net SDR (avg) 6.68 #12 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (bass) 6.20 #12 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (drums) 7.36 #12 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (other) 5.37 #12 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (vocals) 7.80 #12 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (avg) 6.01 #18 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (bass) 5.25 #18 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (drums) 7.01 #18 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (other) 4.53 #18 of 27 Archive leaderboard report
Music Source Separation MUSDB18 D3Net SDR (vocals) 7.24 #18 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConcatenated Skip ConnectionConvolutionDense BlockDense ConnectionsDilated ConvolutionDropoutGlobal Average PoolingKaiming InitializationMax PoolingReLUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections