Audio Source Separation

Ask about this topic

Overview

Audio source separation estimates the individual sounds hidden in a recording, supporting clearer speech, editable music stems, and selective control of noisy soundscapes. Methods range from spatial filtering and nonnegative matrix factorization to neural mask estimators such as Demucs and Band-Split RNN, with newer Transformer, flow-matching, and diffusion models guided by text, video, speaker identity, or musical scores. Systems are tested on speech mixtures such as Libri2Mix, music benchmarks such as MUSDB18, and open-domain sound datasets, using signal metrics alongside listening tests and downstream tasks. A central challenge is balancing separation quality and perceptual naturalness with generalization, real-time efficiency, and reliable performance when separated audio is used for tasks such as speech recognition.

Latest papers

CardsList

66 papers11 papers in the last four weeks, down 42% on the four weeks before. 0.1% of all new papers.

  1. Supervised Source Separation of Electric Vehicle Interior Noise Using a Hybrid Transformer Architecture

    Oct 23, 2026Philipp Diel, Zhuo Cao, Arne Hildenbrand +4Audio Source Separation

    Chair of Thermodynamics of Mobile Energy Conversion Systems, RWTH Aachen University, Aachen, Germany · IAS-8, Forschungszentrum Jülich, Jülich, Germany · Chair of Vibroacoustics of Vehicles and Machines, Technical University of Munich, Garching, Germany

  2. Soloist: A Generative Model for Blind Voice Separation in the Wild

    Oct 14, 2026Chen Yang, ChuFan Yu, Botian Jiang +5Audio Source SeparationSpeech Separation

    Fudan University · Shanghai Innovation Institute

  3. FLOMSS: Generative Music Source Separation by Flow Matching

    Oct 13, 2026Shuyang Cui, Zhi Zhong, Keisuke Toyama +10Music Source SeparationAudio Source Separation

    Sony Group Corporation

  4. FlowGRPO for Vocal Separation: From Reward Analysis to Reward Design

    Oct 11, 2026Lishi Zuo, Chong-Xin Gan, Zezhong Jin +3Music Source SeparationAudio Source Separation

    Dept. of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, China

  5. Learning Where to Split: Dynamic Band Splitting for Audio Source Separation

    Oct 10, 2026Bingzhe Zhang, Kai Li, Xiaolin HuAudio Source Separation

    Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua University, Beijing 100084, China · IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China · Chinese Institute for Brain Research (CIBR), Beijing 100010, China

  6. Lightweight Systems for Spatial Semantic Segmentation of Sound Scenes

    Oct 8, 2026Mayank Mishra, Paul Magron, Romain SerizelSpatial AudioAudio Source Separation

    Universit´e de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France

  7. SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model

    Oct 8, 2026Aviad Dahan, Rajaei Khatib, Yonatan Bitton +3Audio-Video GenerationAudio Source Separation

    Tel Aviv University · Google

  8. A Study on Improving Multi-class Audio Source Separation Via Decoupled CLAP Query Optimization and an Automated Data Engine

    Oct 7, 2026Amirhossein Hajavi, Hanhee Lee, Pushya Jain +4Audio Source SeparationPrompt Optimization

    Noah’s Ark Lab, Huawei Technologies Canada co.

  9. Restore, Separate, Restore: A Modular Framework for Music Source Restoration

    Oct 6, 2026Tobias Morocutti, Emmanouil Karystinaios, Gerhard WidmerAudio Source SeparationMusic Source Separation

    Institute of Computational Perception, Johannes Kepler University Linz, Austria · LIT Artificial Intelligence Lab, Linz, Austria

  10. GAANet: Global-guided Asymmetric Attention Network for Audio-Visual Speech Separation

    Oct 2, 2026Zhiyuan Zhang, Jingyuan Xu, Yiming Tang +2Audio Source SeparationMultimodal Fusion

    School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui 230601, China

  11. Trigger Sound Suppression for Misophonia

    Sep 28, 2026Vaishnavi Vidyasagar, Jasmine Zhang, Mahima Uliyar +4Mental HealthAudio Source Separation

    University of Washington · Duke Center for Misophonia and Emotion Regulation

  12. SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings

    Sep 27, 2026Yiheng Lu, Hao-Wen DongAudio Source SeparationMusic Source Separation

    The Chinese University of Hong Kong, Shenzhen · University of Michigan

  13. Music Source Separation via Stem Discovery

    Sep 25, 2026V. Valtteri Kallinen, Eloi Moliner, Lauri Juvela +1Music Source SeparationAudio Source Separation

    Acoustics Lab, Dept. of Information and Communications Eng., Aalto University, Espoo, Finland

  14. Spot, Separate, and Enhance: Fully Generative Approach for Audio Mixing

    Sep 24, 2026Ilpo Viertola, Giulio Cengarle, Gouthaman KV +2Audio EditingAudio Source Separation

    Dolby Laboratories · Tampere University

  15. On a Separate Note: Robust Score-Informed Note Separation with a Two-Stream TFC-TDF U-Net and Adaptive Set Ownership

    Sep 24, 2026Benjamin Shiue-Hal Chou, Purvish Jajal, Nicholas John Eliopoulos +5Audio Source SeparationMusic Source Separation

    Purdue University · Loyola University Chicago · University of Michigan

  16. MambaVoice: Lightweight Audiovisual Singing Voice Separation Via A Hybrid Mamba-Transformer Model

    Sep 22, 2026Adithi Shankar, Gopika Krishnan, Gloria Haro +2Hybrid Mamba-Transformer ArchitecturesAudio Source Separation

    Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain · Intelligent Multimodal Vision Analysis Group, Universitat Pompeu Fabra, Barcelona, Spain · Serra Húnter Fellow Programme, Universitat Pompeu Fabra, Barcelona, Spain

  17. TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum

    Sep 22, 2026Xinyue Guo, Jianxuan Yang, Daiguo Zhou +4Audio-Visual UnderstandingAudio Source Separation

    MiLM Plus, Xiaomi Inc.

  18. LiteCASS: A Lightweight End-to-End Network for Real-Time Stereo Cinematic Audio Source Separation

    Sep 20, 2026Yuanxin Guo, Qiang Ji, Mengmei Liu +3Spatial AudioAudio Source Separation

    Southwestern University of Finance and Economics, Chengdu, China · Xiaomi Automobile Co., Ltd., Beijing, China · Wuhan University, Wuhan, China

  19. Investigating the Performance and Energy Costs of Replicating Band-Split RNN for Music Source Separation

    Sep 18, 2026Paul Magron, Romain Serizel, Constance DouwesAudio Source SeparationML Reproducibility

    Université de Lorraine, CNRS Inria, LORIA, F-54000 Nancy, France · Centrale Med, Aix Marseille Univ CNRS, LIS, Marseille, France

  20. Online Algorithms for Independent Low-Rank Matrix Analysis and Rank-Constrained Spatial Covariance Matrix Estimation Based on Maximum Weighted Likelihood Estimation

    Sep 18, 2026Yuto Ishikawa, Norihiro Takamune, Tomohiko Nakamura +4Audio Source SeparationCovariance Estimation

    Graduate School of Information Science and Technology, The University of Tokyo, Tokyo 113-8656, Japan · National Institute of Technology, Kagawa College, Takamatsu, Kagawa 761-8058, Japan · Yamaha Corporation, Hamamatsu-shi, Shizuoka 430-8650, Japan

  21. Differentiable Digital Signal Processing Mixture Model-Guided Diffusion for Synthesis Parameter Estimation from Harmonic Sound Mixtures

    Sep 13, 2026Kengo Takemoto, Tomohiko Nakamura, Hiroshi SaruwatariParameter EstimationAudio Source Separation

    The University of Tokyo, Tokyo, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan

  22. Real-Time Music Source Separation on a Low-Power Audio DSP

    Sep 10, 2026Jianan Li, Li Liu, Ken Malsky +1Efficient Neural Network InferenceMusic Information Retrieval

    Analog Devices, Inc., Norwood, MA, USA

  23. Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Model

    Sep 10, 2026Sicheng Mao, Baihan Li, Mathieu Fontaine +2Audio Source SeparationSpeaker Diarization

    LTCI, Telecom Paris, Institut Polytechnique Paris, France · SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, China · LIUM, Le Mans University, France

  24. Open-Set Ego-Noise Separation for Legged-Robot Audition via Annotation-Free Adaptation and Pretrained-Model Transfer

    Sep 7, 2026Koki Shoda, Jun Younes Louhi Kasahara, Aoba Koyanagi +2Legged RoboticsUnsupervised Domain Adaptation

    The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.

  25. Iterative Audio Separation with Mixture Consistency via MIMO Model Extension

    Sep 7, 2026Yukara Ikemiya, WeiHsiang Liao, Yuki MitsufujiAudio Source Separation

    SonyAI

  26. Lead Vocal Separation from Vocal Ensemble Mixtures Using Phoneme Alignment

    Sep 6, 2026Yuma Narahata, Tomohiko Nakamura, Yuki Saito +1Audio Source SeparationMusic Source Separation

    The University of Tokyo, Tokyo, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan

  27. What Selects, What Reconstructs: Repairing Exemplar-Based Complex-Spectrum Separation

    Sep 4, 2026Maxime BaeldeAudio Source SeparationSpectral Unmixing

  28. Geometric Ceilings on Time-Frequency Masking for Single-Channel Separation

    Sep 3, 2026Maxime BaeldeMusic Information RetrievalAudio Source Separation

    Independent researcher, Lille, France

  29. XVAE-WMT: Explainable Wavelet-Temporal Variational Autoencoder for Blind Source Separation of Heart and Lung Sounds

    Aug 31, 2026Yasaman Torabi, Shahram Shirani, James P. ReillyVariational AutoencodersAudio Source Separation

    Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON L8S 4K1, Canada. · L.R. Wilson/Bell Canada Chair in Data Communications, Hamilton, ON L8S 4L7, Canada.

  30. Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment Separation

    Aug 31, 2026Lishi Zuo, Youzhi Tu, Lu Yi +4Flow MatchingFlow-Based Generative Modeling

    Dept. of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, China