The present contribution aims at increasing our understanding of automatic speech recognition (ASR) errors involving frequent homophone or almost homophone words by confronting th...
ive CLP® ABSTRACT Ali A. Milani Broadband speech enhancement and active noise control nvironment ABSTRACT Vanishree Gopalakrishna Real-Time Implementation of Signal Processing Str...
Abstract. The network measurement community has proposed multiple machine learning (ML) methods for traffic classification during the last years. Although several research works ha...
We propose a new local learning scheme that is based on the principle of decisiveness: the learned classifier is expected to exhibit large variability in the direction of the test ...
Scarcity and infeasibility of human supervision for large
scale multi-class classification problems necessitates active
learning. Unfortunately, existing active learning methods
...
Prateek Jain (University of Texas at Austin), Ashi...