paper-with-me

Papers

Problems using deep generative models for probabilistic audio source separation

2020-11-03 · NeurIPS Workshop ICBINB 2020 12 · Maurice Frank, Maximilian Ilse

Recent advancements in deep generative modeling make it possible to learn prior distributions from complex data that subsequently can be used for Bayesian inference. However, we find that distributions learned by deep generative models for audio signals do not exhibit the right properties that are necessary for tasks like audio source separation using a probabilistic approach. We observe that the learned prior distributions are either discriminative and extremely peaked or smooth and non-discriminative. We quantify this behavior for two types of deep generative models on two audio datasets.

📄 PDF Abstract BibTeX arXiv:2011.01761

Code (0)

등록된 구현이 없습니다.

Tasks

Audio Source SeparationBayesian Inference

Similar Papers 제목 키워드 기반

High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling

2025-09-26 · Chao Huang, Susan Liang, Yapeng Tian, Anurag Kumar 외 arxiv

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-bas…

Unsupervised Source Separation By Steering Pretrained Music Models

2021-10-25 · Ethan Manilow, Patrick O'Reilly, Prem Seetharaman, Bryan Pardo

We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixt…

Audio GenerationAudio Source SeparationMusic GenerationMusic Tagging+1

High-Quality Visually-Guided Sound Separation from Diverse Categories

2023-07-31 · Chao Huang, Susan Liang, Yapeng Tian, Anurag Kumar 외

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-bas…

AudioSlots: A slot-centric generative model for audio separation

2023-05-09 · Pradyumna Reddy, Scott Wisdom, Klaus Greff, John R. Hershey 외

In a range of recent works, object-centric architectures have been shown to be suitable for unsupervised scene decomposition in the vision domain. Inspired by these methods we present AudioSlots, a slot-centric generativ…

blind source separationDecoderSpeech Separation

ZeroSep: Separate Anything in Audio with Zero Training

2025-05-29 · Chao Huang, Yuesheng Ma, Junxuan Huang, Susan Liang 외

Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the n…

Audio Source SeparationDenoising