Separate Anything You Describe
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910721208483840 |
|---|---|
| author | Liu, Xubo Kong, Qiuqiang Zhao, Yan Liu, Haohe Yuan, Yi Liu, Yuzhuo Xia, Rui Wang, Yuxuan Plumbley, Mark D. Wang, Wenwu |
| author_facet | Liu, Xubo Kong, Qiuqiang Zhao, Yan Liu, Haohe Yuan, Yi Liu, Yuzhuo Xia, Rui Wang, Yuxuan Plumbley, Mark D. Wang, Wenwu |
| contents | 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. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_05037 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Separate Anything You Describe Liu, Xubo Kong, Qiuqiang Zhao, Yan Liu, Haohe Yuan, Yi Liu, Yuzhuo Xia, Rui Wang, Yuxuan Plumbley, Mark D. Wang, Wenwu Audio and Speech Processing Artificial Intelligence Multimedia Sound 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. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep. |
| title | Separate Anything You Describe |
| topic | Audio and Speech Processing Artificial Intelligence Multimedia Sound |
| url | https://arxiv.org/abs/2308.05037 |