# Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet

arXiv: https://arxiv.org/abs/2402.17701 · HTML: https://mlsanity.com/paper/2402.17701/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 22 of 22)

- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [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)
- [Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation](https://mlsanity.com/paper/2109.05418/) (2021)
- [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://mlsanity.com/paper/2111.12203/) (2021)
- [All for One and One for All: Improving Music Separation by Bridging Networks](https://mlsanity.com/paper/2010.04228/) (2020)
- [Meta-learning Extractors for Music Source Separation](https://mlsanity.com/paper/2002.07016/) (2020)
- [Filterbank design for end-to-end speech separation](https://mlsanity.com/paper/1910.10400/) (2019)
- [STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency](https://mlsanity.com/paper/2204.09911/) (2022)
- [Demystifying TasNet: A Dissecting Approach](https://mlsanity.com/paper/1911.08895/) (2019)
- [Perceptual Loss Function for Neural Modelling of Audio Systems](https://mlsanity.com/paper/1911.08922/) (2019)
- [Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes](https://mlsanity.com/paper/2011.00801/) (2020)
- [On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems](https://mlsanity.com/paper/2206.07340/) (2022)
- [MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation](https://mlsanity.com/paper/1802.00300/) (2018)
- [The Whole Is Greater than the Sum of Its Parts: Improving Music Source Separation by Bridging Network](https://mlsanity.com/paper/2305.07855/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Two-Stage Band-Split Mamba-2 Network For Music Separation](https://mlsanity.com/paper/2409.06245/) (2024)
- [How much to Dereverberate? Low-Latency Single-Channel Speech Enhancement in Distant Microphone Scenarios](https://mlsanity.com/paper/2505.01338/) (2025)
- [Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment](https://mlsanity.com/paper/2609.12724/) (2026)

## Abstract (arXiv)

There have been significant advances in deep learning for music demixing in recent years. However, there has been little attention given to how these neural networks can be adapted for real-time low-latency applications, which could be helpful for hearing aids, remixing audio streams and live shows. In this paper, we investigate the various challenges involved in adapting current demixing models in the literature for this use case. Subsequently, inspired by the Hybrid Demucs architecture, we propose the Hybrid Spectrogram Time-domain Audio Separation Network HS-TasNet, which utilises the advantages of spectral and waveform domains. For a latency of 23 ms, the HS-TasNet obtains an overall signal-to-distortion ratio (SDR) of 4.65 on the MusDB test set, and increases to 5.55 with additional training data. These results demonstrate the potential of efficient demixing for real-time low-latency music applications.