# LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation

arXiv: https://arxiv.org/abs/2111.12516 · HTML: https://mlsanity.com/paper/2111.12516/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 24 Nov 2021.

## Builds on (most cited first, 19 of 19)

- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network](https://mlsanity.com/paper/1911.04697/) (2019)
- [Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations](https://mlsanity.com/paper/1907.01277/) (2019)
- [All for One and One for All: Improving Music Separation by Bridging Networks](https://mlsanity.com/paper/2010.04228/) (2020)
- [Simultaneous Separation and Transcription of Mixtures with Multiple Polyphonic and Percussive Instruments](https://mlsanity.com/paper/1910.12621/) (2019)
- [Meta-learning Extractors for Music Source Separation](https://mlsanity.com/paper/2002.07016/) (2020)
- [Conditioned Source Separation for Music Instrument Performances](https://mlsanity.com/paper/2004.03873/) (2020)
- [A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis](https://mlsanity.com/paper/2108.03456/) (2021)
- [Audio query-based music source separation](https://mlsanity.com/paper/1908.06593/) (2019)
- [Multi-scale Multi-band DenseNets for Audio Source Separation](https://mlsanity.com/paper/1706.09588/) (2017)
- [LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation](https://mlsanity.com/paper/2010.11631/) (2020)
- [Recursive speech separation for unknown number of speakers](https://mlsanity.com/paper/1904.03065/) (2019)
- [Class-conditional embeddings for music source separation](https://mlsanity.com/paper/1811.03076/) (2018)
- [Deep Clustering and Conventional Networks for Music Separation: Stronger Together](https://mlsanity.com/paper/1611.06265/) (2016)
- [Multi-channel U-Net for Music Source Separation](https://mlsanity.com/paper/2003.10414/) (2020)
- [Investigating U-Nets with various Intermediate Blocks for Spectrogram-based Singing Voice Separation](https://mlsanity.com/paper/1912.02591/) (2019)
- [AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries](https://mlsanity.com/paper/2104.13553/) (2021)
- [Interleaved Multitask Learning for Audio Source Separation with Independent Databases](https://mlsanity.com/paper/1908.05182/) (2019)

## Abstract (arXiv)

Conditioned source separations have attracted significant attention because of their flexibility, applicability and extensionality. Their performance was usually inferior to the existing approaches, such as the single source separation model. However, a recently proposed method called LaSAFT-Net has shown that conditioned models can show comparable performance against existing single-source separation models. This paper presents LightSAFT-Net, a lightweight version of LaSAFT-Net. As a baseline, it provided a sufficient SDR performance for comparison during the Music Demixing Challenge at ISMIR 2021. This paper also enhances the existing LightSAFT-Net by replacing the LightSAFT blocks in the encoder with TFC-TDF blocks. Our enhanced LightSAFT-Net outperforms the previous one with fewer parameters.Conditioned source separations have attracted significant attention because of their flexibility, applicability and extensionality. Their performance was usually inferior to the existing approaches, such as the single source separation model. However, a recently proposed method called LaSAFT-Net has shown that conditioned models can show comparable performance against existing single-source separation models. This paper presents LightSAFT-Net, a lightweight version of LaSAFT-Net. As a baseline, it provided a sufficient SDR performance for comparison during the Music Demixing Challenge at ISMIR 2021.