paper-with-me

홈 › Papers

Audio Source Separation Using Variational Autoencoders and Weak Class Supervision

2018-10-31 · Ertuğ Karamatlı, Ali Taylan Cemgil, Serap Kırbız

In this paper, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isolated sources. Since our method does not require source class labels for every time-frequency bin but only a single label for each source constituting the mixture signal, we call this scenario as weak class supervision. We associate a variational autoencoder (VAE) with each source class within a non-negative (compositional) model. Each VAE provides a prior model to identify the signal from its associated class in a sound mixture. After training the model on mixtures, we obtain a generative model for each source class and demonstrate our method on one-second mixtures of utterances of digits from 0 to 9. We show that the separation performance obtained by source class supervision is as good as the performance obtained by source signal supervision.

📄 PDF Abstract BibTeX arXiv:1810.13104

Code (1)

ertug/Weak_Class_Source_Separation 공식 구현 pytorch

Tasks

Audio Source SeparationDenoising

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음
USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation

2023-12-07 · Xiaoyu Lin, Laurent Girin, Xavier Alameda-Pineda

In this paper, we propose a latent-variable generative model called mixture of dynamical variational autoencoders (MixDVAE) to model the dynamics of a system composed of multiple moving sources. A DVAE model is pre-train…

Audio Source SeparationMulti-Object TrackingObject TrackingTrajectory Modeling

Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencoder

2024-08-12 · Leonardo Berti

I developed a neural audio codec model based on the residual quantized variational autoencoder architecture. I train the model on the Slakh2100 dataset, a standard dataset for musical source separation, composed of multi…

Zero-shot Audio Source Separation through Query-based Learningfrom Weakly-labeled Data

2021-12-15 · AAAI 2021 12 · Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma 외

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal se…

Audio Source SeparationEvent DetectionSound Event DetectionZero-shot Generalization

Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data

2021-12-15 · Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma 외

Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although some universal se…

Audio Source SeparationAudio TaggingEvent DetectionSound Event Detection+1

Weakly-supervised Audio-visual Sound Source Detection and Separation

2021-03-25 · Tanzila Rahman, Leonid Sigal

Learning how to localize and separate individual object sounds in the audio channel of the video is a difficult task. Current state-of-the-art methods predict audio masks from artificially mixed spectrograms, known as Mi…

Audio Source SeparationDenoisingObjectSegmentation+3