← Search

Andreas Kabel

2 accepted papers

2022

Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training

ICASSP 2022accepted

Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these approaches to Automatic Speech Recognition, we demonstrate that the state-of-the-art Conformer models generally have mult…

Cited by 0SourceScholar
2020

Low-Rank Gradient Approximation for Memory-Efficient on-Device Training of Deep Neural Network

ICASSP 2020accepted

Training machine learning models on mobile devices has the potential of improving both privacy and accuracy of the models. However, one of the major obstacles to achieving this goal is the memory limitation of mobile devices. Reducing training memory enables models with high-dimensional weight matri…

Cited by 0SourceScholar