Seguir
Wilfried Michel
Wilfried Michel
PhD Student, RWTH Aachen University
Email confirmado em cs.rwth-aachen.de - Página inicial
Título
Citado por
Citado por
Ano
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention
C Lüscher, E Beck, K Irie, M Kitza, W Michel, A Zeyer, R Schlüter, H Ney
Submitted to Interspeech, 2019
311*2019
The RWTH ASR System for Ted-Lium Release 2: Improving Hybrid HMM With Specaugment
W Zhou, W Michel, K Irie, M Kitza, R Schlüter, H Ney
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
522020
Investigating methods to improve language model integration for attention-based encoder-decoder ASR models
M Zeineldeen, A Glushko, W Michel, A Zeyer, R Schlüter, H Ney
arXiv preprint arXiv:2104.05544, 2021
472021
Conformer-based hybrid ASR system for Switchboard dataset
M Zeineldeen, J Xu, C Lüscher, W Michel, A Gerstenberger, R Schlüter, ...
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
332022
Librispeech Transducer Model with Internal Language Model Prior Correction
A Zeyer, A Merboldt, W Michel, R Schlüter, H Ney
arXiv preprint arXiv:2104.03006, 2021
312021
Efficient Training of Neural Transducer for Speech Recognition
W Zhou, W Michel, R Schlüter, H Ney
arXiv preprint arXiv:2204.10586, 2022
232022
Parallel Neural Network Features for Improved Tandem Acoustic Modeling
Z Tüske, W Michel, R Schlüter, H Ney
Proc. Interspeech 2017, 1651-1655, 2017
142017
Early Stage LM Integration Using Local and Global Log-Linear Combination
W Michel, R Schlüter, H Ney
Interspeech 2020, 3605--3609, 2020
112020
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
W Michel, R Schlüter, H Ney
arXiv preprint arXiv:1907.01409, 2019
112019
On Architectures and Training for Raw Waveform Feature Extraction in ASR
P Vieting, C Lüscher, W Michel, R Schlüter, H Ney
IEEE ASRU, 2021
92021
The RWTH/UPB System Combination for the CHiME 2018 Workshop
M Kitza, W Michel, C Boeddeker, J Heitkaemper, T Menne, R Schlüter, ...
7*
The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task
W Michel, Z Tüske, MAB Shaik, R Schlüter, H Ney
62016
Efficient Sequence Training of Attention Models Using Approximative Recombination
NP Wynands, W Michel, J Rosendahl, R Schlüter, H Ney
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
42022
Frame-Level MMI as a Sequence Discriminative Training Criterion for LVCSR
W Michel, R Schlüter, H Ney
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
42020
Automatic Learning of Subword Dependent Model Scales
F Meyer, W Michel, M Zeineldeen, R Schlüter, H Ney
arXiv preprint arXiv:2110.09324, 2021
22021
End-To-End Training of a Neural HMM with Label and Transition Probabilities
D Mann, T Raissi, W Michel, R Schlüter, H Ney
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023
12023
Feature Replacement and Combination for Hybrid ASR Systems
P Vieting, C Lüscher, W Michel, R Schlüter, H Ney
arXiv preprint arXiv:2104.04298, 2021
2021
O sistema não pode efectuar a operação agora. Tente mais tarde.
Artigos 1–17