# Separate Anything You Describe

**Authors:** Xubo Liu, Qiuqiang Kong, Yan Zhao, Haohe Liu, Yi Yuan, Yuzhuo Liu, Rui Xia, Yuxuan Wang, Mark D. Plumbley, Wenwu Wang  
**arXiv:** [2308.05037](https://arxiv.org/abs/2308.05037)  
**Date:** 2023-08-09  
**Summary page:** https://www.summarizepaper.com/en/paper/2308.05037v1/

## Key points

- Language-queried audio source separation (LASS) is a novel approach in computational auditory scene analysis (CASA)
- LASS aims to separate specific sounds from an audio mixture based on natural language queries
- Previous works on LASS have shown promising results for separating certain sources, but struggle with open-domain audio concepts
- AudioSep is introduced as a foundation model for open-domain audio source separation using natural language queries
- AudioSep is trained on large-scale multimodal datasets and evaluated on various tasks including audio event separation, musical instrument separation, and speech enhancement
- The model demonstrates strong separation performance and impressive zero-shot generalization ability when using audio captions or text labels as queries
- Compared to previous models, AudioSep outperforms them significantly in sound separation techniques
- The authors plan to release the source code, evaluation benchmark, and pre-trained model on their GitHub repository for reproducibility of their work
- "Separate Anything You Describe" by Xubo Liu et al. presents AudioSep as a powerful tool for open-domain audio source separation with natural language queries

## Summary

Language-queried audio source separation (LASS) is a novel approach in computational auditory scene analysis (CASA) that aims to separate specific sounds from an audio mixture based on natural language queries. Previous works on LASS have shown promising results for separating certain sources, such as musical instruments or limited classes of audio events. However, they struggle with separating audio concepts in the open domain. To address this limitation, the authors introduce AudioSep – a foundation model for open-domain audio source separation using natural language queries. AudioSep is trained on large-scale multimodal datasets and evaluated on various tasks including audio event separation, musical instrument separation and speech enhancement. The model demonstrates strong separation performance and impressive zero-shot generalization ability when using audio captions or text labels as queries. Compared to previous models that use either audio-queried or language-queried sound separation techniques, AudioSep outperforms them significantly. To ensure reproducibility of their work, the authors plan to release the source code, evaluation benchmark and pre-trained model on their GitHub repository. The paper "Separate Anything You Describe" by Xubo Liu et al. presents AudioSep as a powerful tool for open-domain audio source separation with natural language queries. Its ability to separate diverse types of sounds makes it suitable for various digital audio applications.