# Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data

arXiv: https://arxiv.org/abs/2307.12576 · HTML: https://mlsanity.com/paper/2307.12576/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 24 Jul 2023.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [Music Demixing Challenge 2021](https://mlsanity.com/paper/2108.13559/) (2021)
- [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://mlsanity.com/paper/2111.12203/) (2021)
- [All for One and One for All: Improving Music Separation by Bridging Networks](https://mlsanity.com/paper/2010.04228/) (2020)
- [DALI: a large Dataset of synchronized Audio, LyrIcs and notes, automatically created using teacher-student machine learning paradigm](https://mlsanity.com/paper/1906.10606/) (2019)
- [A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis](https://mlsanity.com/paper/2108.03456/) (2021)
- [Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects](https://mlsanity.com/paper/2211.02247/) (2022)
- [Deep convolutional networks on the pitch spiral for musical instrument recognition](https://mlsanity.com/paper/1605.06644/) (2016)
- [An Attention Mechanism for Musical Instrument Recognition](https://mlsanity.com/paper/1907.04294/) (2019)
- [Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition](https://mlsanity.com/paper/2107.07029/) (2021)
- [Deep convolutional neural networks for predominant instrument recognition in polyphonic music](https://mlsanity.com/paper/1605.09507/) (2016)
- [Multitask learning for frame-level instrument recognition](https://mlsanity.com/paper/1811.01143/) (2018)
- [Frame-level Instrument Recognition by Timbre and Pitch](https://mlsanity.com/paper/1806.09587/) (2018)
- [An Attention-based Approach to Hierarchical Multi-label Music Instrument Classification](https://mlsanity.com/paper/2302.08136/) (2023)
- [Show Me the Instruments: Musical Instrument Retrieval from Mixture Audio](https://mlsanity.com/paper/2211.07951/) (2022)
- [Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training](https://mlsanity.com/paper/2302.00286/) (2023)
- [Semi-supervised learning using teacher-student models for vocal melody extraction](https://mlsanity.com/paper/2008.06358/) (2020)
- [Towards robust music source separation on loud commercial music](https://mlsanity.com/paper/2208.14355/) (2022)

## Built on by (most cited first, 1 of 1)

- [MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction](https://mlsanity.com/paper/2505.23305/) (2025)

## Abstract (arXiv)

Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering mislabeled individual instrument tracks becomes a significant challenge to address. This paper introduces an automated technique for refining the labels in a partially mislabeled dataset. Our proposed self-refining technique, employed with a noisy-labeled dataset, results in only a 1% accuracy degradation in multi-label instrument recognition compared to a classifier trained on a clean-labeled dataset. The study demonstrates the importance of refining noisy-labeled data in MSS model training and shows that utilizing the refined dataset leads to comparable results derived from a clean-labeled dataset. Notably, upon only access to a noisy dataset, MSS models trained on a self-refined dataset even outperform those trained on a dataset refined with a classifier trained on clean labels.