activity
20182022
most citedSound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes

30 citations · 51 across the 9 of their papers we have counts for

collaborators

16 papers

cs.SD2022

How to Listen? Rethinking Visual Sound Localization

Ho-Hsiang Wu, Magdalena Fuentes, Prem Seetharaman +1

Localizing visual sounds consists on locating the position of objects that emit sound within an image. It is a growing research area with potential applications in monitoring natur…

cs.SD2021

Unsupervised Source Separation By Steering Pretrained Music Models

Ethan Manilow, Patrick O'Reilly, Prem Seetharaman +1

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 generati…

cs.SD2020

What's All the FUSS About Free Universal Sound Separation Data?

Scott Wisdom, Hakan Erdogan, Daniel Ellis +6

We introduce the Free Universal Sound Separation (FUSS) dataset, a new corpus for experiments in separating mixtures of an unknown number of sounds from an open domain of sound typ…

cs.SD202030 cited

Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes

Nicolas Turpault, Romain Serizel, Scott Wisdom +5

We propose a benchmark of state-of-the-art sound event detection systems (SED). We designed synthetic evaluation sets to focus on specific sound event detection challenges. We anal…

cs.SD2020

A Study of Transfer Learning in Music Source Separation

Andreas Bugler, Bryan Pardo, Prem Seetharaman

Supervised deep learning methods for performing audio source separation can be very effective in domains where there is a large amount of training data. While some music domains ha…

eess.AS2020

AutoClip: Adaptive Gradient Clipping for Source Separation Networks

Prem Seetharaman, Gordon Wichern, Bryan Pardo +1

Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter. We present AutoClip, a simple method fo…