36 citations · 103 across the 8 of their papers we have counts for
9 papers
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…
Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
Efthymios Tzinis, Scott Wisdom, Aren Jansen +4
Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural video…
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…
Unsupervised Learning of Semantic Audio Representations
Aren Jansen, Manoj Plakal, Ratheet Pandya +5
Even in the absence of any explicit semantic annotation, vast collections of audio recordings provide valuable information for learning the categorical structure of sounds. We cons…
CNN Architectures for Large-Scale Audio Classification
Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis +10
Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of…
Accelerating Inference: towards a full Language, Compiler and Hardware stack
Shawn Hershey, Jeff Bernstein, Bill Bradley +4
We introduce Dimple, a fully open-source API for probabilistic modeling. Dimple allows the user to specify probabilistic models in the form of graphical models, Bayesian networks,…