Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed
원문 초록
We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments. State-of-the-art approaches predict soft masks over mixture spectrograms while methods working on the waveform are lagging behind as measured on the standard MusDB benchmark. Our contribution is two fold. (i) We introduce a simple convolutional and recurrent model that outperforms the state-of-the-art model on waveforms, that is, Wave-U-Net, by 1.6 points of SDR (signal to distortion ratio). (ii) We propose a new scheme to leverage unlabeled music. We train a first model to extract parts with at least one source silent in unlabeled tracks, for instance without bass. We remix this extract with a bass line taken from the supervised dataset to form a new weakly supervised training example. Combining our architecture and scheme, we show that waveform methods can play in the same ballpark as spectrogram ones.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Music Source Restoration
Training-Free Multi-Step Audio Source Separation
Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music
Learned Compression for Compressed Learning
SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation
A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems
토론
이 논문과 연결된 포럼 글이 아직 없습니다.