Search Results for author:
Found 7 papers, 2 papers with code
Normalise for Fairness: A Simple Normalisation Technique for Fairness in Regression Machine Learning Problems
We present a theoretical analysis of the method, in addition to an empirical comparison against two standard methods for fairness, namely data balancing and adversarial training.
Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning
The selected techniques are trained on a non-medical dataset and then tested on two out-of-domain, human cell datasets.
Tokenization Repair in the Presence of Spelling Errors
We identify three key ingredients of high-quality tokenization repair, all missing from previous work: deep language models with a bidirectional component, training the models on text with spelling errors, and making use of the space information already present.
"I have vxxx bxx connexxxn!": Facing Packet Loss in Deep Speech Emotion Recognition
We explore matched, mismatched, and multi-condition training settings.
On Deep Speech Packet Loss Concealment: A Mini-Survey
In this mini-survey, we review all the literature we found to date, that attempt to solve the packet-loss in speech using deep learning methods.
ConcealNet: An End-to-end Neural Network for Packet Loss Concealment in Deep Speech Emotion Recognition
Additionally, extending this with an end-to-end emotion prediction neural network provides a network that performs SER from audio with lost frames, end-to-end.
DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking
Convolutional Siamese neural networks have been recently used to track objects using deep features.
