# KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing

arXiv: https://arxiv.org/abs/2111.12203 · HTML: https://mlsanity.com/paper/2111.12203/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2021.

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

- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [SingSong: Generating musical accompaniments from singing](https://mlsanity.com/paper/2301.12662/) (2023)
- [Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation](https://mlsanity.com/paper/2501.15907/) (2025)
- [Live Music Models](https://mlsanity.com/paper/2508.04651/) (2025)
- [A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation](https://mlsanity.com/paper/2309.02539/) (2023)
- [A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems](https://mlsanity.com/paper/2406.18747/) (2024)
- [Benchmarks and leaderboards for sound demixing tasks](https://mlsanity.com/paper/2305.07489/) (2023)
- [Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3](https://mlsanity.com/paper/2306.09382/) (2023)
- [Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet](https://mlsanity.com/paper/2402.17701/) (2024)
- [Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation](https://mlsanity.com/paper/2408.16126/) (2024)
- [MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling](https://mlsanity.com/paper/2505.15772/) (2025)
- [A Two-Stage Band-Split Mamba-2 Network For Music Separation](https://mlsanity.com/paper/2409.06245/) (2024)
- [Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model](https://mlsanity.com/paper/2511.20470/) (2025)
- [Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data](https://mlsanity.com/paper/2307.12576/) (2023)
- [Remixing Music for Hearing Aids Using Ensemble of Fine-Tuned Source Separators](https://mlsanity.com/paper/2401.06203/) (2024)
- [The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss](https://mlsanity.com/paper/2409.05095/) (2024)
- [Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT](https://mlsanity.com/paper/2304.02160/) (2023)
- [Improving Real-Time Music Accompaniment Separation with MMDenseNet](https://mlsanity.com/paper/2407.00657/) (2024)
- [MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation](https://mlsanity.com/paper/2501.03689/) (2025)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)
- [PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing](https://mlsanity.com/paper/2604.09111/) (2026)
- [MusicMark: A Robust Generative Watermarking Framework for Music Generation](https://mlsanity.com/paper/2607.11117/) (2026)
- [Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models](https://mlsanity.com/paper/2607.23395/) (2026)

## Abstract (arXiv)

Recently, many methods based on deep learning have been proposed for music source separation. Some state-of-the-art methods have shown that stacking many layers with many skip connections improve the SDR performance. Although such a deep and complex architecture shows outstanding performance, it usually requires numerous computing resources and time for training and evaluation. This paper proposes a two-stream neural network for music demixing, called KUIELab-MDX-Net, which shows a good balance of performance and required resources. The proposed model has a time-frequency branch and a time-domain branch, where each branch separates stems, respectively. It blends results from two streams to generate the final estimation. KUIELab-MDX-Net took second place on leaderboard A and third place on leaderboard B in the Music Demixing Challenge at ISMIR 2021. This paper also summarizes experimental results on another benchmark, MUSDB18. Our source code is available online.