https://github.com/Js-Mim/rl_singing_voice
공식 코드Unsupervised Interpretable Representation Learning for Singing Voice Separation
Papers with Code 아카이브
Music Source Separation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 42
Music source separation is the task of decomposing music into its constitutive components, e. g., yielding separated stems for the vocals, bass, and drums.
<span style="color:grey; opacity: 0.6">( Image credit: SigSep )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/JuanFMontesinos/Acappella-YNet
공식 코드https://github.com/SunnyCYC/aug4mss
공식 코드Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation
https://github.com/TomohikoNakamura/dwtls
공식 코드Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform
https://github.com/TomohikoNakamura/sfi_convtasnet
공식 코드https://github.com/Windstudent/Complex-MTASSNet
공식 코드https://github.com/asteroid-team/asteroid
공식 코드All for One and One for All: Improving Music Separation by Bridging Networks
https://github.com/asteroid-team/asteroid/tree/master/egs/musdb18/X-UMX
공식 코드All for One and One for All: Improving Music Separation by Bridging Networks
https://github.com/cgaroufis/msspt
공식 코드Pre-training Music Classification Models via Music Source Separation
https://github.com/danjacobellis/LCCL
공식 코드https://github.com/danjacobellis/mpq
공식 코드https://github.com/danjacobellis/walloc
공식 코드https://github.com/ee7u/score-mss
공식 코드https://github.com/f90/AdversarialAudioSeparation
공식 코드Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction
https://github.com/f90/Wave-U-Net
공식 코드Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation
https://github.com/facebookresearch/demucs
공식 코드https://github.com/francesclluis/point-cloud-source-separation
공식 코드https://github.com/francesclluis/source-separation-wavenet
공식 코드End-to-end music source separation: is it possible in the waveform domain?
https://github.com/gzhu06/generativesourceseparation
공식 코드https://github.com/haoheliu/2021-ismir-mss-challenge-cws-presunet
공식 코드CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet
https://github.com/jeonchangbin49/medleyvox
공식 코드MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation
https://github.com/jhtonykoo/music_mixing_style_transfer
공식 코드Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects
https://github.com/junyuchen-cjy/dttnet-pytorch
공식 코드https://github.com/karnwatcharasupat/spauq
공식 코드https://github.com/kikyo-16/a-unified-model-for-zero-shot-musical-source-separation-transcription-and-synthesis
공식 코드A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis
https://github.com/kuielab/mdx-net
공식 코드KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing
https://github.com/kuielab/sdx23
공식 코드Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3
https://github.com/kvsphantom/multitask-unet-bss
공식 코드https://github.com/kwatcharasupat/query-bandit
공식 코드A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems
https://github.com/michelemancusi/LQVAE-separation
공식 코드Unsupervised Source Separation via Bayesian Inference in the Latent Domain
https://github.com/naplab/Conv-TasNet
공식 코드Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
https://github.com/pfnet-research/meta-tasnet
공식 코드https://github.com/pierrechouteau/umss_icassp
공식 코드A fully differentiable model for unsupervised singing voice separation
https://github.com/repertorium/hq-sod-generator
공식 코드SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
https://github.com/repertorium/synthsod-baseline
공식 코드SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
https://github.com/schufo/umss
공식 코드Unsupervised Music Source Separation Using Differentiable Parametric Source Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.