Thomas Kemp

Improving music source separation based on deep neural networks through data augmentation and network blending

Stefan Uhlich, Marcello Porcu, Franck Giron et al. · 2017 · 192 citations

Music, Sisec Dsd100 Dataset, Data Augmentation +15

Estimating confidence using word lattices

Thomas Kemp, Thomas Schaaf · 1997 · 169 citations

Engineering, Machine Learning, Speech Corpus +22

Strategies for automatic segmentation of audio data

Thomas Kemp, Mikkel N. Schmidt, Martin Westphal et al. · 2002 · 124 citations

Music, Engineering, Machine Learning +21

Confidence measures for spontaneous speech recognition

Thomas Schaaf, Thomas Kemp · 2002 · 107 citations

Engineering, Speech Corpus, Spoken Language Processing +20

The Karlsruhe-Verbmobil speech recognition engine

Michael Finke, Petra Geutner, Hermann Hild et al. · 2002 · 102 citations

Natural Language Processing, German Research Project, Engineering +15