Audio Prompt Tuning for Universal Sound Separation

1 code implementation • 30 Nov 2023 • Yuzhuo Liu, Xubo Liu, Yan Zhao, Yuanyuan Wang, Rui Xia, Pingchuan Tain, Yuxuan Wang

Specifically, APT improves the separation performance of specific sources through training a small number of prompt parameters with limited audio samples, while maintaining the generalization of the USS model by keeping its parameters frozen.

Separate Anything You Describe

1 code implementation • 9 Aug 2023 • Xubo Liu, Qiuqiang Kong, Yan Zhao, Haohe Liu, Yi Yuan, Yuzhuo Liu, Rui Xia, Yuxuan Wang, Mark D. Plumbley, Wenwu Wang

In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries.

Audio Source Separation Natural Language Queries +2

Power pooling: An adaptive pooling function for weakly labelled sound event detection

no code implementations • 20 Oct 2020 • Yuzhuo Liu, Hangting Chen, YunWang, Pengyuan Zhang

While this paper focuses on sound event detection applications, the proposed method can be applied to MIL tasks in other domains.

Event Detection Multiple Instance Learning +1