Acoustic modeling with deep neural networks using raw time signal for LVCSR. Z Tüske, P Golik, R Schlüter, H Ney INTERSPEECH, 890-894, 2014 | 247 | 2014 |
Convolutional Neural Networks for Acoustic Modeling of Raw Time Signal in LVCSR P Golik, Z Tüske, R Schlüter, H Ney Sixteenth Annual Conference of the International Speech Communication …, 2015 | 145 | 2015 |
LSTM, GRU, highway and a bit of attention: an empirical overview for language modeling in speech recognition K Irie, Z Tüske, T Alkhouli, R Schlüter, H Ney Interspeech, 3519-3523, 2016 | 128 | 2016 |
Evolutionary stochastic gradient descent for optimization of deep neural networks X Cui, W Zhang, Z Tüske, M Picheny Advances in neural information processing systems, 6048-6058, 2018 | 127 | 2018 |
RASR - the RWTH Aachen university open source speech recognition toolkit D Rybach, S Hahn, P Lehnen, D Nolden, M Sundermeyer, Z Tüske, ... Proc. IEEE Automatic Speech Recognition and Understanding Workshop, 2011 | 115 | 2011 |
Multilingual representations for low resource speech recognition and keyword search J Cui, B Kingsbury, B Ramabhadran, A Sethy, K Audhkhasi, Z Tüske, ... ASRU, 259-266, 2015 | 114 | 2015 |
Advancing RNN transducer technology for speech recognition G Saon, Z Tüske, D Bolanos, B Kingsbury ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 110 | 2021 |
Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard Z Tüske, G Saon, K Audhkhasi, B Kingsbury Interspeech 2020, 2020 | 81 | 2020 |
Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages. Z Tüske, P Golik, D Nolden, R Schlüter, H Ney INTERSPEECH, 1420-1424, 2014 | 70 | 2014 |
Improved recognition of spontaneous Hungarian speech—Morphological and acoustic modeling techniques for a less resourced task P Mihajlik, Z Tüske, B Tarján, B Németh, T Fegyó Audio, Speech, and Language Processing, IEEE Transactions on 18 (6), 1588-1600, 2010 | 64 | 2010 |
Alignment-Length Synchronous Decoding for RNN Transducer G Saon, Z Tüske, K Audhkhasi ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal …, 2020 | 60 | 2020 |
Lattice decoding and rescoring with long-Span neural network language models. M Sundermeyer, Z Tüske, R Schlüter, H Ney INTERSPEECH, 661-665, 2014 | 58 | 2014 |
Investigation on cross-and multilingual MLP features under matched and mismatched acoustical conditions Z Tüske, J Pinto, D Willett, R Schlüter Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International …, 2013 | 58 | 2013 |
Integrating Gaussian mixtures into deep neural networks: softmax layer with hidden variables Z Tüske, MA Tahir, R Schlüter, H Ney | 56 | 2015 |
Multilingual MRASTA features for low-resource keyword search and speech recognition systems Z Tüske, D Nolden, R Schlüter, H Ney Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International …, 2014 | 56 | 2014 |
On the limit of English conversational speech recognition Z Tüske, G Saon, B Kingsbury arXiv preprint arXiv:2105.00982, 2021 | 54 | 2021 |
Context-dependent MLPs for LVCSR: TANDEM, hybrid or both? Z Tüske, M Sundermeyer, R Schlüter, H Ney Thirteenth Annual Conference of the International Speech Communication …, 2012 | 42 | 2012 |
Sequence Noise Injected Training for End-to-end Speech Recognition G Saon, Z Tüske, K Audhkhasi, B Kingsbury ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 39 | 2019 |
Deep hierarchical bottleneck MRASTA features for LVCSR Z Tüske, R Schlüter, H Ney Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International …, 2013 | 39 | 2013 |
A morpho-graphemic approach for the recognition of spontaneous speech in agglutinative languages-like Hungarian. P Mihajlik, T Fegyó, Z Tüske, P Ircing INTERSPEECH, 1497-1500, 2007 | 38 | 2007 |