mlsanityData to 7 Oct 2026

Meta-learning Extractors for Music Source Separation

arXiv 2002.07016 ↗First posted 17 Feb 2020cs.SD cs.LG eess.AScited by 18

Not on the map. Why?

Abstract (arXiv)

We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models. This enables efficient parameter-sharing, while still allowing for instrument-specific parameterization. Meta-TasNet is shown to be more effective than the models trained independently or in a multi-task setting, and achieve performance comparable with state-of-the-art methods. In comparison to the latter, our extractors contain fewer parameters and have faster run-time performance. We discuss important architectural considerations, and explore the costs and benefits of this approach.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 1; 2023: 3; 2024: 4; 2025: 1.

18 papers.

Sort:

By area:

  1. 2022Music Source Separation with Band-split RNNcited by 69
  2. 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
  3. 2021A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesiscited by 18
  4. 2021A cappella: Audio-visual Singing Voice Separationcited by 12
  5. 2024A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stemscited by 7
  6. 2021Points2Sound: From mono to binaural audio using 3D point cloud scenescited by 4
  7. 2023Toward Deep Drum Source Separationcited by 4
  8. 2024Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNetcited by 3
  9. 2021Music source separation conditioned on 3D point cloudscited by 2
  10. 2021AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queriescited by 2
  11. 2024A Two-Stage Band-Split Mamba-2 Network For Music Separationcited by 2
  12. 2025User-guided Generative Source Separationcited by 2
6 more
  1. 2023Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoderscited by 1
  2. 2021Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Methodcited by 0
  3. 2021LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separationcited by 0
  4. 2021Learning source-aware representations of music in a discrete latent spacecited by 0
  5. 2023Sampling-Frequency-Independent Universal Sound Separationcited by 0
  6. 2024Resource-constrained stereo singing voice cancellationcited by 0