Personal
Welcome to the homepage of Mohammad Zeineldeen.
I am a PhD student at Machine Learning and Human Language Technology Group of RWTH Aachen University since January 2020. I also work as a speech scientist at AppTek.
My personal research interests include
- Recurrent networks, LSTMs
- Neural Attention models
- Automatic Speech Recognition (ASR)
- Acoustic Modeling
- End-to-end models for ASR
- Streaming ASR
Other links:
Email: zeineldeen@cs.rwth-aachen.de
List of Publications
-
C. Lüscher, M. Zeineldeen, Z. Yang, T. Raissi, P. Vieting, K. Le-Duc, W. Wang, R. Schlüter, and H. Ney. Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech. In ITG Conference on Speech Communication, pages 161-165, Aachen, Germany, September 2023.
-
C. Lüscher, J. Xu, M. Zeineldeen, R. Schlüter, and H. Ney. Analyzing And Improving Neural Speaker Embeddings for ASR. In ITG Conference on Speech Communication, pages 205-209, Aachen, Germany, September 2023.
-
C. Herold, Y. Gao, M. Zeineldeen, and H. Ney. Improving Language Model Integration for Neural Machine Translation. In Findings of the Association for Computational Linguistics (ACL23), volume 61, Toronto, Canada, July 2023.
-
W. Zhou, H. Wu, J. Xu, M. Zeineldeen, C. Lüscher, R. Schlüter, and H. Ney. Enhancing and Adversarial: Improve ASR with Speaker Labels. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, Greece, June 2023.
[poster].
-
M. Zeineldeen, K. Audhkhasi, M. K. Baskar, and B. Ramabhadran. Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, Greece, June 2023.
[poster].
-
F. Meyer, W. Michel, M. Zeineldeen, R. Schlüter, and H. Ney. Automatic Learning of Subword Dependent Model Scales. In Interspeech, Incheon, Korea, September 2022.
-
M. Zeineldeen, J. Xu, C. Lüscher, R. Schlüter, and H. Ney. Improving the Training Recipe for a Robust Conformer-based Hybrid Model. In Interspeech, Incheon, Korea, September 2022.
[poster].
-
M. Zeineldeen, J. Xu, C. Lüscher, W. Michel, A. Gerstenberger, R. Schlüter, and H. Ney. Conformer-based Hybrid ASR System for Switchboard Dataset. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Singapore, May 2022.
[poster].
-
M. Gansen, J. Lou, F. Freye, T. Gemmeke, F. Merchant, A. Zeyer, M. Zeineldeen, R. Schlüter, and X. Fan. Discrete Steps towards Approximate Computing. In International Symposium on Quality Electronic Design (ISQED), pages 1-6, April 2022.
DOI: 10.1109/ISQED54688.2022.9806215.
-
N. Rossenbach, M. Zeineldeen, B. Hilmes, R. Schlüter, and H. Ney. Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures. In IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Cartagena, Colombia, December 2021.
-
W. Zhou, M. Zeineldeen, Z. Zheng, R. Schlüter, and H. Ney. Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition. In Interspeech, pages 2886-2890, August 2021.
[slides].
-
M. Zeineldeen, A. Glushko, W. Michel, A. Zeyer, R. Schlüter, and H. Ney. Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models. In Interspeech, pages 2856-2860, August 2021.
[slides] [video].
-
Mohammad Zeineldeen, Albert Zeyer, Wei Zhou, Thomas Ng, Ralf Schlüter, and Hermann Ney. A Systematic Comparison of Grapheme-based vs. Phoneme-based Label Units for Encoder-Decoder-Attention Models. , November, 2020.
Preprint arXiv:2005.09336.
-
M. Zeineldeen, A. Zeyer, R. Schlüter, and H. Ney. Layer-normalized LSTM for Hybrid-HMM and End-to-End ASR. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 7679-7683, Barcelona, Spain, May 2020.
[slides].
Full list of publications
of the chair.