A curated list of source separation, inspired by awesome-computer-vision.
This list mainly focuses on deep learning based models. It aims to introduce milestones works and essential things for beginner researchers(including myself).
This list may contain incorrect informations and I don't want this list to be exhaustive. If I miss important papers or anyone found incorrect informations, please let me know via Github issue.
WIP: This list is in construction.
Please feel free to send me pull requests or email(jaechang@postech.ac.kr).
- What is source separation?
- survey papers
- papers
- datasets
- open-source projects
- competitions
Separating a mixture into sources. Major researches are about sound source separation. You can refer Stöter's nice tutorials. As the problem itself is an under-determined problem(for single-channel), additional priors should be used. The priors include distrubution of sources and addtional information(score, video, ...).
- An Overview of Lead and Accompaniment Separation in Music - Z. Rafii et al., 2018
- Deep clustering: Discriminative embeddings for segmentation and separation - J. Hershey et al., ICASSP 2016
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation - Yi Luo et al., TASLP 2019
- wave-u-net
- Permutation invariant training of deep models for speaker-independent multi-talker speech separation - D. Yu et al., ICASSP 2017
- Voice Separation with an Unknown Number of Multiple Speakers
- Demucs - A. Défossez, 2021,
- https://arxiv.org/abs/2111.03600 (version 3)
- HIERARCHICAL MUSICAL INSTRUMENT SEPARATION - E. Manilow et al., ISMIR 2020.
- Score-informed source separation of choral music
- AUDIO QUERY-BASED MUSIC SOURCE SEPARATION
- Weakly informed audio source separation
- Conditioned Source Separation for Musical Instrument Performances.
- Co-separating sounds of visual objects - R. Gao et al., ICCV 2019
- Unsupervised Sound Separation Using Mixture Invariant Training - S. Wisdom et al., NeurIPS 2020.
- Universal sound separation - I. Kavalerov, WASPAA 2019.
- The Cone of Silence: Speech Separation by Localization - T. Jenrungrot, NeurIPS 2020.
- Performance measurement in blind audio source separation - E. Vincent, TASLP 2006
- SDR – Half-baked or Well Done? - J. Le Roux, ICASSP 2019.
- MUSDB18 (for music)
- wsj0 (for speech)
- WHAM!
- FUSS (for universal source separation)
- asteroid
- sisec 2018
- Music Demixing Challenge 2021