May 11, 2023 · We propose a universal audio source separation framework containing: 1) an audio tagging model trained on weakly labeled data as a query net; and 2) a ...

This is the PyTorch implementation of the Universal Source Separation with Weakly labelled Data [1]. The USS system can automatically detect and separate ...

May 11, 2023 · Left: Clean source data of sound class "Flute". Right: Weakly labelled data of sound class "Air horn, truck horn" which only occurs between 2.5s ...

Since then, more weakly supervised methods have been proposed, such as using sound class as weak labels [12, 13] , and even completely unsupervised methods that ...

This repo contains supplementary materials for our paper: Source separation with weakly labelled data: An approach to computational auditory scene analysis.

Dec 15, 2021 · In this paper, we propose a three-component pipeline to train a universal audio source separator from a large, but weakly-labeled dataset: AudioSet.

May 15, 2023 · Universal Source Separation with Weakly Labelled Data abs: https://arxiv.org/abs/2305.07447 paper page: https://huggingface.co/papers/2305.07447 ...

Another way of building source separation systems is to use weakly labelled data [20, 21]. Weakly labelled data only contain audio tags of audio clips ...

Plumbley, “Source separation with weakly labelled data: An approach to computational auditory scene analysis,” in Proc. ICASSP, 2020. [8] K. Kinoshita, L ...

Kong, Y. Xu, W. Wang, and M. D. Plumbley, “A joint separation-classification model for sound event detection of weakly labelled data, ...