Benjamin Schubert — accepted AI-conference papers

2023

Frequentist Uncertainty Quantification in Semi-Structured Neural Networks

Emilio Dorigatti, Benjamin Schubert, Bernd Bischl, David Ruegamer

AISTATS 2023poster

Semi-structured regression (SSR) models jointly learn the effect of structured (tabular) and unstructured (non-tabular) data through additive predictors and deep neural networks (DNNs), respectively. Inference in SSR models aims at deriving confidence intervals for the structured predictor, although…

Cited by 4 Source ↗PDF ↗Scholar ↗

2015

Improved error resilience for volte and VoIP with 3GPP EVS channel aware coding

Venkatraman Atti, Daniel J. Sinder, Shaminda Subasingha, Vivek Rajendran, Duminda A. Dewasurendra, Venkata Chebiyyam +6

ICASSP 2015accepted

A highly error resilient mode of the newly standardized 3GPP EVS speech codec is described. Compared to the AMR-WB codec and other conversational codecs, the EVS channel aware mode offers significantly improved error resilience in voice communication over packet-switched networks such as Voice-over-…

Cited by 0 Source ↗Scholar ↗