Следене
Dmitriy Serdyuk
Dmitriy Serdyuk
Research Scientist, Google
Потвърден имейл адрес: google.com
Заглавие
Позовавания
Позовавания
Година
Attention-based models for speech recognition
J Chorowski, D Bahdanau, D Serdyuk, K Cho, Y Bengio
Advances in Neural Information Processing Systems 28, 2015
31662015
End-to-end attention-based large vocabulary speech recognition
D Bahdanau, J Chorowski, D Serdyuk, P Brakel, Y Bengio
2016 IEEE international conference on acoustics, speech and signal …, 2016
14722016
Theano: A Python framework for fast computation of mathematical expressions
R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ...
arXiv e-prints, arXiv: 1605.02688, 2016
1131*2016
Deep complex networks
C Trabelsi, O Bilaniuk, Y Zhang, D Serdyuk, S Subramanian, JF Santos, ...
6th International Conference on Learning Representations, {ICLR} 2018, 2017
9312017
Towards end-to-end spoken language understanding
D Serdyuk, Y Wang, C Fuegen, A Kumar, B Liu, Y Bengio
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
2532018
Blocks and fuel: Frameworks for deep learning
B Van Merriënboer, D Bahdanau, V Dumoulin, D Serdyuk, ...
arXiv preprint arXiv:1506.00619, 2015
2082015
Accounting for variance in machine learning benchmarks
X Bouthillier, P Delaunay, M Bronzi, A Trofimov, B Nichyporuk, J Szeto, ...
Proceedings of Machine Learning and Systems 3, 747-769, 2021
1362021
Invariant representations for noisy speech recognition
D Serdyuk, K Audhkhasi, P Brakel, B Ramabhadran, S Thomas, Y Bengio
arXiv preprint arXiv:1612.01928, 2016
812016
Twin networks: Matching the future for sequence generation
D Serdyuk, NR Ke, A Sordoni, A Trischler, C Pal, Y Bengio
6th International Conference on Learning Representations, {ICLR} 2018, 2017
75*2017
Fortified networks: Improving the robustness of deep networks by modeling the manifold of hidden representations
A Lamb, J Binas, A Goyal, D Serdyuk, S Subramanian, I Mitliagkas, ...
arXiv preprint arXiv:1804.02485, 2018
572018
Unsupervised adversarial domain adaptation for acoustic scene classification
S Gharib, K Drossos, E Cakir, D Serdyuk, T Virtanen
arXiv preprint arXiv:1808.05777, 2018
562018
Theano: A Python framework for fast computation of mathematical expressions. arXiv
R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ...
arXiv preprint arXiv:1605.02688 10, 2016
522016
Audio-Visual Speech Recognition is Worth Voxels
D Serdyuk, O Braga, O Siohan
2021 IEEE automatic speech recognition and understanding workshop (ASRU …, 2021
492021
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video
D Serdyuk, O Braga, O Siohan
Proc. 23rd Annual Conference of International Speech Communication …, 2022
352022
Mad twinnet: Masker-denoiser architecture with twin networks for monaural sound source separation
K Drossos, SI Mimilakis, D Serdyuk, G Schuller, T Virtanen, Y Bengio
2018 International Joint Conference on Neural Networks (IJCNN), 1-8, 2018
322018
Task loss estimation for sequence prediction
D Bahdanau, D Serdyuk, P Brakel, NR Ke, J Chorowski, A Courville, ...
arXiv preprint arXiv:1511.06456, 2015
322015
Deep complex networks
T Chiheb, O Bilaniuk, D Serdyuk
International Conference on Learning Representations, 2017
172017
Conformer is All You Need for Visual Speech Recognition
O Chang, H Liao, D Serdyuk, A Shahy, O Siohan
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
152024
Twin regularization for online speech recognition
M Ravanelli, D Serdyuk, Y Bengio
Interspeech 2018, 2018
152018
Bayesian rating systems with additional information on tournament results
SI Nikolenko, DV Serdyuk, AV Sirotkin
Trudy SPIIRAN 22, 189-204, 2012
6*2012
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20