Abstract
Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. Specifically, AudioSep achieved strong results including a Signal-to-Distortion Ratio Improvement (SDRi) of 7.74 dB across 527 sound classes of the AudioSet; 9.14 dB on the VGGSound dataset; 8.22 dB on the AudioCaps dataset; 6.85 dB on the Clotho dataset; 10.51 dB on the MUSIC dataset; 10.04 dB on the ESC-50 dataset; 8.16 dB on the DCASE 2024 Task 9 dataset; and an SSNR of 9.21 dB on the VoicebankDemand dataset.