219 citations · 385 across the 13 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CL2022★ 2 cited
TEVR: Improving Speech Recognition by Token Entropy Variance Reduction
Hajo Nils Krabbenhöft, Erhardt Barth
This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the…
cs.CV2022★ 5 cited
Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks
Philipp Grüning, Erhardt Barth
Min-Nets are inspired by end-stopped cortical cells with units that output the minimum of two learned filters. We insert such Min-units into state-of-the-art deep networks, such as…