# D3Net: Densely connected multidilated DenseNet for music source separation

arXiv: https://arxiv.org/abs/2010.01733 · HTML: https://mlsanity.com/paper/2010.01733/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 24 of 24)

- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data](https://mlsanity.com/paper/2112.07891/) (2021)
- [Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning](https://mlsanity.com/paper/2410.00255/) (2024)
- [On loss functions and evaluation metrics for music source separation](https://mlsanity.com/paper/2202.07968/) (2022)
- [A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes](https://mlsanity.com/paper/2403.07469/) (2024)
- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data](https://mlsanity.com/paper/2105.04727/) (2021)
- [Music Separation Enhancement with Generative Modeling](https://mlsanity.com/paper/2208.12387/) (2022)
- [A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems](https://mlsanity.com/paper/2406.18747/) (2024)
- [End-to-end lyrics Recognition with Voice to Singing Style Transfer](https://mlsanity.com/paper/2102.08575/) (2021)
- [Unsupervised Music Source Separation Using Differentiable Parametric Source Models](https://mlsanity.com/paper/2201.09592/) (2022)
- [Audiovisual Singing Voice Separation](https://mlsanity.com/paper/2107.00231/) (2021)
- [Unsupervised Source Separation via Bayesian Inference in the Latent Domain](https://mlsanity.com/paper/2110.05313/) (2021)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)
- [An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation](https://mlsanity.com/paper/2410.20773/) (2024)
- [Improving Music Source Separation with Diffusion and Consistency Refinement](https://mlsanity.com/paper/2412.06965/) (2024)
- [Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementation](https://mlsanity.com/paper/2506.08457/) (2025)
- [AI-Assisted Music Production: A User Study on Text-to-Music Models](https://mlsanity.com/paper/2509.23364/) (2025)
- [Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures](https://mlsanity.com/paper/2511.21342/) (2025)
- [Blind Source Separation in Polyphonic Music Recordings Using Deep Neural Networks Trained via Policy Gradients](https://mlsanity.com/paper/2107.04235/) (2021)
- [Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT](https://mlsanity.com/paper/2304.02160/) (2023)
- [Resource-constrained stereo singing voice cancellation](https://mlsanity.com/paper/2401.12068/) (2024)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)

## Abstract (arXiv)

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.