Folgen
Markus Nussbaum-Thom
Markus Nussbaum-Thom
Bestätigte E-Mail-Adresse bei i6.informatik.rwth-aachen.de
Titel
Zitiert von
Zitiert von
Jahr
Multilingual representations for low resource speech recognition and keyword search
J Cui, B Kingsbury, B Ramabhadran, A Sethy, K Audhkhasi, X Cui, ...
2015 IEEE workshop on automatic speech recognition and understanding (ASRU …, 2015
1142015
Knowledge distillation across ensembles of multilingual models for low-resource languages
J Cui, B Kingsbury, B Ramabhadran, G Saon, T Sercu, K Audhkhasi, ...
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
752017
The rwth 2010 quaero asr evaluation system for english, french, and german
M Sundermeyer, M Nußbaum-Thom, S Wiesler, C Plahl, AED Mousa, ...
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
592011
Speech recognition for machine translation in quaero
L Lamel, S Courcinous, J Despres, JL Gauvain, Y Josse, K Kilgour, F Kraft, ...
Proceedings of the 8th International Workshop on Spoken Language Translation …, 2011
502011
Spoken language translation using automatically transcribed text in training
S Peitz, S Wiesler, M Nußbaum-Thom, H Ney
Proceedings of the 9th International Workshop on Spoken Language Translation …, 2012
312012
The RWTH 2009 QUAERO ASR evaluation system for English and German
M Nußbaum-Thom, S Wiesler, M Sundermeyer, C Plahl, S Hahn, ...
Eleventh Annual Conference of the International Speech Communication Association, 2010
272010
Acoustic Modeling Using Bidirectional Gated Recurrent Convolutional Units.
M Nussbaum-Thom, J Cui, B Ramabhadran, V Goel
Interspeech, 390-394, 2016
232016
Investigations on features for log-linear acoustic models in continuous speech recognition
S Wiesler, M Nußbaum-Thom, G Heigold, R Schlüter, H Ney
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 52-57, 2009
232009
Discriminative HMMs, log-linear models, and CRFs: what is the difference?
G Heigold, S Wiesler, M Nußbaum-Thom, P Lehnen, R Schlüter, H Ney
2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010
182010
Novel tight classification error bounds under mismatch conditions based on f-Divergence
R Schlüter, M Nussbaum-Thom, E Beck, T Alkhouli, H Ney
2013 IEEE Information Theory Workshop (ITW), 1-5, 2013
162013
Does the cost function matter in Bayes decision rule?
R Schluter, M Nussbaum-Thom, H Ney
IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (2), 292-301, 2011
152011
On the relationship between Bayes risk and word error rate in ASR
R Schluter, M Nussbaum-Thom, H Ney
IEEE transactions on audio, speech, and language processing 19 (5), 1103-1112, 2010
152010
Improvements in RWTH LVCSR evaluation systems for Polish, Portuguese, English, urdu, and Arabic.
MAB Shaik, Z Tüske, MA Tahir, M Nußbaum-Thom, R Schlüter, H Ney
INTERSPEECH, 3154-3158, 2015
132015
Compound Word Recombination for German LVCSR.
M Nußbaum-Thom, AED Mousa, R Schlüter, H Ney
INTERSPEECH, 1449-1452, 2011
122011
The rwth aachen speech recognition and machine translation system for iwslt 2012
S Peitz, S Mansour, M Freitag, M Feng, M Huck, J Wuebker, M Nuhn, ...
Proceedings of the 9th International Workshop on Spoken Language Translation …, 2012
112012
A discriminative splitting criterion for phonetic decision trees.
S Wiesler, G Heigold, M Nußbaum-Thom, R Schlüter, H Ney
INTERSPEECH, 54-57, 2010
112010
Relative error bounds for statistical classifiers based on the f-divergence.
M Nussbaum-Thom, E Beck, T Alkhouli, R Schlüter, H Ney
Interspeech, 2197-2201, 2013
102013
On the relation of Bayes risk, word error, and word posteriors in ASR.
R Schlüter, M Nussbaum-Thom, H Ney
INTERSPEECH, 230-233, 2010
82010
RWTH LVCSR systems for quaero and EU-bridge: German, Polish, Spanish and Portuguese
MAB Shaik, Z Tüske, MA Tahir, M Nußbaum-Thom, R Schlüter, H Ney
Fifteenth Annual Conference of the International Speech Communication …, 2014
62014
The RWTH Aachen German and English LVCSR systems for IWSLT-2013
MAB Shaik, Z Tüske, S Wiesler, M Nußbaum-Thom, S Peitz, R Schlüter, ...
Proceedings of the 10th International Workshop on Spoken Language …, 2013
62013
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20