# On loss functions and evaluation metrics for music source separation

arXiv: https://arxiv.org/abs/2202.07968 · HTML: https://mlsanity.com/paper/2202.07968/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Upsampling artifacts in neural audio synthesis](https://mlsanity.com/paper/2010.14356/) (2020)
- [D3Net: Densely connected multidilated DenseNet for music source separation](https://mlsanity.com/paper/2010.01733/) (2020)
- [Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks](https://mlsanity.com/paper/1808.06719/) (2018)
- [An empirical study of Conv-TasNet](https://mlsanity.com/paper/2002.08688/) (2020)
- [Demystifying TasNet: A Dissecting Approach](https://mlsanity.com/paper/1911.08895/) (2019)
- [Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction](https://mlsanity.com/paper/1711.00048/) (2017)
- [On permutation invariant training for speech source separation](https://mlsanity.com/paper/2102.04945/) (2021)
- [Spectrogram Feature Losses for Music Source Separation](https://mlsanity.com/paper/1901.05061/) (2019)

## Built on by (most cited first, 17 of 17)

- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [Fast Text-to-Audio Generation with Adversarial Post-Training](https://mlsanity.com/paper/2505.08175/) (2025)
- [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models](https://mlsanity.com/paper/2409.12346/) (2024)
- [Latent Autoregressive Source Separation](https://mlsanity.com/paper/2301.08562/) (2023)
- [Music Separation Enhancement with Generative Modeling](https://mlsanity.com/paper/2208.12387/) (2022)
- [Adversarial Permutation Invariant Training for Universal Sound Separation](https://mlsanity.com/paper/2210.12108/) (2022)
- [MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction](https://mlsanity.com/paper/2505.23305/) (2025)
- [Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model](https://mlsanity.com/paper/2511.20470/) (2025)
- [Distribution Preserving Source Separation With Time Frequency Predictive Models](https://mlsanity.com/paper/2303.05896/) (2023)
- [Improving Music Source Separation with Diffusion and Consistency Refinement](https://mlsanity.com/paper/2412.06965/) (2024)
- [StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction](https://mlsanity.com/paper/2510.18938/) (2025)
- [Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation](https://mlsanity.com/paper/2405.20059/) (2024)
- [Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencoder](https://mlsanity.com/paper/2408.07020/) (2024)
- [Solving Copyright Infringement on Short Video Platforms: Novel Datasets and an Audio Restoration Deep Learning Pipeline](https://mlsanity.com/paper/2504.21772/) (2025)
- [Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models](https://mlsanity.com/paper/2607.23395/) (2026)
- [Iterative Audio Separation with Mixture Consistency via MIMO Model Extension](https://mlsanity.com/paper/2609.07226/) (2026)
- [Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment](https://mlsanity.com/paper/2609.12724/) (2026)

## Abstract (arXiv)

We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation. To that end, we first survey the most representative audio source separation losses we identified, to later consistently benchmark them in a controlled experimental setup. We also explore using such losses as evaluation metrics, via cross-correlating them with the results of a subjective test. Based on the observation that the standard signal-to-distortion ratio metric can be misleading in some scenarios, we study alternative evaluation metrics based on the considered losses.