23 citations · 53 across the 7 of their papers we have counts for
8 papers
Recomposer: Event-roll-guided generative audio editing
Daniel P. W. Ellis, Eduardo Fonseca, Ron J. Weiss +7
Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their str…
Dataset balancing can hurt model performance
R. Channing Moore, Daniel P. W. Ellis, Eduardo Fonseca +3
Machine learning from training data with a skewed distribution of examples per class can lead to models that favor performance on common classes at the expense of performance on ra…
The Benefit Of Temporally-Strong Labels In Audio Event Classification
Shawn Hershey, Daniel P W Ellis, Eduardo Fonseca +4
To reveal the importance of temporal precision in ground truth audio event labels, we collected precise (~0.1 sec resolution) "strong" labels for a portion of the AudioSet dataset.…
Self-Supervised Learning from Automatically Separated Sound Scenes
Eduardo Fonseca, Aren Jansen, Daniel P. W. Ellis +7
Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The associati…
Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking
Eduardo Fonseca, Shawn Hershey, Manoj Plakal +4
The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels,…
Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Aren Jansen, Daniel P. W. Ellis, Shawn Hershey +4
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-lab…