# MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation

arXiv: https://arxiv.org/abs/1805.02410 · HTML: https://mlsanity.com/paper/1805.02410/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2018.

## Built on by (most cited first, 19 of 19)

- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [A Survey of Sound Source Localization with Deep Learning Methods](https://mlsanity.com/paper/2109.03465/) (2021)
- [Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data](https://mlsanity.com/paper/2112.07891/) (2021)
- [A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis](https://mlsanity.com/paper/2108.03456/) (2021)
- [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models](https://mlsanity.com/paper/2409.12346/) (2024)
- [A cappella: Audio-visual Singing Voice Separation](https://mlsanity.com/paper/2104.09946/) (2021)
- [Latent Autoregressive Source Separation](https://mlsanity.com/paper/2301.08562/) (2023)
- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [Music Source Restoration](https://mlsanity.com/paper/2505.21827/) (2025)
- [Audiovisual Singing Voice Separation](https://mlsanity.com/paper/2107.00231/) (2021)
- [The Radio-Frequency Transformer for Signal Separation](https://mlsanity.com/paper/2603.09201/) (2026)
- [Unsupervised Source Separation via Bayesian Inference in the Latent Domain](https://mlsanity.com/paper/2110.05313/) (2021)
- [Improved singing voice separation with chromagram-based pitch-aware remixing](https://mlsanity.com/paper/2203.15092/) (2022)
- [A Two-Stage Band-Split Mamba-2 Network For Music Separation](https://mlsanity.com/paper/2409.06245/) (2024)
- [Adversarial Unsupervised Domain Adaptation for Harmonic-Percussive Source Separation](https://mlsanity.com/paper/2101.00701/) (2021)
- [Deep Generative Multimedia Children's Literature](https://mlsanity.com/paper/2209.13129/) (2022)
- [Sampling-Frequency-Independent Universal Sound Separation](https://mlsanity.com/paper/2309.12581/) (2023)
- [Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment](https://mlsanity.com/paper/2609.12724/) (2026)

## Abstract (arXiv)

Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MMDenseNet was successfully employed to solve the ASS problem of estimating source amplitudes, and state-of-the-art results were obtained for DSD100 dataset. To further enhance MMDenseNet, here we propose a novel architecture that integrates long short-term memory (LSTM) in multiple scales with skip connections to efficiently model long-term structures within an audio context. The experimental results show that the proposed method outperforms MMDenseNet, LSTM and a blend of the two networks. The number of parameters and processing time of the proposed model are significantly less than those for simple blending. Furthermore, the proposed method yields better results than those obtained using ideal binary masks for a singing voice separation task.