Thomas Kemp

34 papers A* 1A 2Misc 8Journal 8Unranked 13
YearRankTypeTitle / Venue / Authors
2020 J jnl
Efficient Sampling for Predictor-Based Neural Architecture Search.
CoRR
Lukas Mauch, Stephen Tiedemann, Javier Alonso García, Bac Nguyen Cong, Kazuki Yoshiyama, Fabien Cardinaux, Thomas Kemp
2020 J jnl
Iteratively Training Look-Up Tables for Network Quantization.
IEEE J. Sel. Top. Signal Process.
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Lukas Mauch, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
2020 A* conf
Mixed Precision DNNs: All you need is a good parametrization.
ICLR
Stefan Uhlich, Lukas Mauch, Fabien Cardinaux, Kazuki Yoshiyama, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
2020 J jnl
Speech Synthesis and Control Using Differentiable DSP.
CoRR
Giorgio Fabbro, Vladimir Golkov, Thomas Kemp, Daniel Cremers
2019 J jnl
Differentiable Quantization of Deep Neural Networks.
CoRR
Stefan Uhlich, Lukas Mauch, Kazuki Yoshiyama, Fabien Cardinaux, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
2019 J jnl
Iteratively Training Look-Up Tables for Network Quantization.
CoRR
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Lukas Mauch, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
2018 J jnl
Improving DNN-based Music Source Separation using Phase Features.
CoRR
Joachim Muth, Stefan Uhlich, Nathanaël Perraudin, Thomas Kemp, Fabien Cardinaux, Yuki Mitsufuji
2018 J jnl
Iteratively Training Look-Up Tables for Network Quantization.
CoRR
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
2017 Misc conf
Improving music source separation based on deep neural networks through data augmentation and network blending.
ICASSP
Stefan Uhlich, Marcello Porcu, Franck Giron, Michael Enenkl, Thomas Kemp, Naoya Takahashi, Yuki Mitsufuji
2005 — conf
Mood-based navigation through large collections of musical data.
CCNC
Marta Tolos, Raquel Tato, Thomas Kemp
2004 A conf
Environmental robust features for speech detection.
INTERSPEECH
Thomas Kemp, Climent Nadeu, Yin Hay Lam, Josep Maria Sola i Caros
2004 — conf
Towards Real Life Applications in Emotion Recognition: Comparing Different Databases, Feature Sets, and Reinforcement Methods for Recognizing Emotions from Speech.
ADS
Daniel Küstner, Raquel Tato, Thomas Kemp, Beate Meffert
2003 — conf
Automatic set-up for speech recognition engines based on merit optimization.
ICASSP (1)
Gustavo Hernández Ábrego, Xavier Menéndez-Pidal, Thomas Kemp, Katsuki Minamino, Helmut Lucke
2001 J jnl
The ISL View4You Broadcast News Transcription System.
Int. J. Speech Technol.
Thomas Kemp, Manfred Weber, Alex Waibel
2000 Misc conf
Confidence measure based language identification.
ICASSP
Florian Metze, Thomas Kemp, Thomas Schaaf, Tanja Schultz, Hagen Soltau
2000 — conf
Das View4You- System: End-to-End Evaluation.
KONVENS
Florian Metze, Thomas Kemp
2000 — conf
End to end evaluation of the ISL View4You broadcast news transcription and retrieval system.
RIAO
Thomas Kemp, Alex Waibel
2000 A conf
Evaluating different information retrieval algorithms on real-world data.
INTERSPEECH
Manfred Weber, Thomas Kemp
2000 Misc conf
Strategies for automatic segmentation of audio data.
ICASSP
Thomas Kemp, Michael Schmidt, Martin Westphal, Alex Waibel
1999 — —
Ein automatisches Indexierungssystem für Fernsehnachrichtensendungen.
Thomas Kemp
1999 — ch.
Ein automatisches Indexierungssystem für Fernsehnachrichtensendungen.
Ausgezeichnete Informatikdissertationen
Thomas Kemp
1999 — conf
Unsupervised training of a speech recognizer: recent experiments.
EUROSPEECH
Thomas Kemp, Alex Waibel
1998 — conf
Reducing the OOV rate in broadcast news speech recognition.
ICSLP
Thomas Kemp, Alex Waibel
1998 — conf
The interactive systems labs view4you video indexing system.
ICSLP
Thomas Kemp, Petra Geutner, Michael Schmidt, Borislav Tomaz, Manfred Weber, Martin Westphal, Alex Waibel
1998 — conf
Unsupervised training of a speech recognizer using TV broadcasts.
ICSLP
Thomas Kemp, Alex Waibel
1997 Misc conf
Confidence measures for spontaneous speech recognition.
ICASSP
Thomas Schaaf, Thomas Kemp
1997 — conf
Estimating confidence using word lattices.
EUROSPEECH
Thomas Kemp, Thomas Schaaf
1997 Misc conf
The Karlsruhe-Verbmobil speech recognition engine.
ICASSP
Michael Finke, Petra Geutner, Hermann Hild, Thomas Kemp, Klaus Ries, Martin Westphal
1996 Misc conf
JANUS-II-translation of spontaneous conversational speech.
ICASSP
Alex Waibel, Michael Finke, Donna Gates, Marsal Gavaldà, Thomas Kemp, Alon Lavie, Lori S. Levin, Martin Maier, Laura Mayfield, Arthur E. McNair, Ivica Rogina, Kaori Shima, Tilo Sloboda, Monika Woszczyna, Torsten Zeppenfeld, Puming Zhan
1996 Misc conf
Modelling unknown words in spontaneous speech.
ICASSP
Thomas Kemp, Andreas Jusek
1996 — conf
Regelbasiert generierte Ausprachevarianten für Spontansprache.
KONVENS
Thomas Kemp
1995 Misc conf
Data-driven codebook adaptation in phonetically tied SCHMMs.
ICASSP
Thomas Kemp
1995 — conf
Integrating different learning approaches into a multilingual spoken language translation system.
Learning for Natural Language Processing
Petra Geutner, Bernhard Suhm, Finn Dag Buø, Thomas Kemp, Laura Mayfield, Arthur E. McNair, Ivica Rogina, Tanja Schultz, Tilo Sloboda, Wayne H. Ward, Monika Woszczyna, Alex Waibel
1994 — conf
JANUS 93: towards spontaneous speech translation.
ICASSP (1)
Monika Woszczyna, Naomi Aoki-Waibel, Finn Dag Buø, Noah Coccaro, Keiko Horiguchi, Thomas Kemp, Alon Lavie, Arthur E. McNair, Thomas Polzin, Ivica Rogina, Carolyn P. Rosé, Tanja Schultz, Bernhard Suhm, Masaru Tomita, Alex Waibel