no code implementations • 17 Aug 2023 • Julia Wilkins, Justin Salamon, Magdalena Fuentes, Juan Pablo Bello, Oriol Nieto
We show that our system, trained using our automatic data curation pipeline, significantly outperforms baselines trained on in-the-wild data on the task of HQ SFX retrieval for video.
1 code implementation • 14 Apr 2023 • Giovana Morais, Matthew E. P. Davies, Marcelo Queiroz, Magdalena Fuentes
Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations.
1 code implementation • 15 Nov 2022 • Rajsuryan Singh, Pablo Zinemanas, Xavier Serra, Juan Pablo Bello, Magdalena Fuentes
Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner, and by design excludes temporal information present in videos.
no code implementations • 20 Mar 2022 • Sangeeta Srivastava, Ho-Hsiang Wu, Joao Rulff, Magdalena Fuentes, Mark Cartwright, Claudio Silva, Anish Arora, Juan Pablo Bello
To accomplish this, we imitate channel effects by injecting perturbations to the audio signal and measure the shift in the new (perturbed) embeddings with three distance measures, making the evaluation domain-dependent but not task-dependent.
no code implementations • 26 Sep 2021 • Magdalena Fuentes, Justin Salamon, Pablo Zinemanas, Martín Rocamora, Genís Paja, Irán R. Román, Marius Miron, Xavier Serra, Juan Pablo Bello
Soundata is a Python library for loading and working with audio datasets in a standardized way, removing the need for writing custom loaders in every project, and improving reproducibility by providing tools to validate data against a canonical version.
1 code implementation • 2 Jun 2021 • Ho-Hsiang Wu, Magdalena Fuentes, Juan P. Bello
We train music instrument classifiers that can take both images or sounds as input, and perform comparably to sound-only or image-only classifiers.
no code implementations • 11 Sep 2020 • Mark Cartwright, Jason Cramer, Ana Elisa Mendez Mendez, Yu Wang, Ho-Hsiang Wu, Vincent Lostanlen, Magdalena Fuentes, Graham Dove, Charlie Mydlarz, Justin Salamon, Oded Nov, Juan Pablo Bello
In this article, we describe our data collection procedure and propose evaluation metrics for multilabel classification of urban sound tags.