| 2025 | ICASSP | The Conformer Encoder May Reverse the Time Dimension. | Robin Schmitt, Albert Zeyer, Mohammad Zeineldeen, Ralf Schlter, Hermann Ney |
| 2025 | Interspeech | Dynamic Acoustic Model Architecture Optimization in Training for ASR. | Jingjing Xu, Zijian Yang, Albert Zeyer, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2024 | ICASSP | Chunked Attention-Based Encoder-Decoder Model for Streaming Speech Recognition. | Mohammad Zeineldeen, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR Models. | Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | Librispeech Transducer Model with Internal Language Model Prior Correction. | Albert Zeyer, Andr Merboldt, Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept. | Wei Zhou, Albert Zeyer, Andr Merboldt, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition. | Parnia Bahar, Nikita Makarov, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | A Comprehensive Study of Residual CNNS for Acoustic Modeling in ASR. | Vitalii Bozheniuk, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems. | Nick Rossenbach, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR. | Mohammad Zeineldeen, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | A New Training Pipeline for an Improved Neural Transducer. | Albert Zeyer, Andr Merboldt, Ralf Schlter, Hermann Ney |
| 2019 | ASRU | Training Language Models for Long-Span Cross-Sentence Evaluation. | Kazuki Irie, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | ASRU | A Comparison of Transformer and LSTM Encoder Decoder Models for ASR. | Albert Zeyer, Parnia Bahar, Kazuki Irie, Ralf Schlter, Hermann Ney |
| 2019 | ICASSP | On Using 2D Sequence-to-sequence Models for Speech Recognition. | Parnia Bahar, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Language Modeling with Deep Transformers. | Kazuki Irie, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | RWTH ASR Systems for LibriSpeech: Hybrid vs Attention. | Christoph Lscher, Eugen Beck, Kazuki Irie, Markus Kitza, Wilfried Michel, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | An Analysis of Local Monotonic Attention Variants. | Andr Merboldt, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2018 | ACL | RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition. | Albert Zeyer, Tamer Alkhouli, Hermann Ney |
| 2018 | Interspeech | Improved Training of End-to-end Attention Models for Speech Recognition. | Albert Zeyer, Kazuki Irie, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | Returnn: The RWTH extensible training framework for universal recurrent neural networks. | Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilia Kulikov, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition. | Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | Faster sequence training. | Albert Zeyer, Ilia Kulikov, Ralf Schlter, Hermann Ney |
| 2017 | Interspeech | CTC in the Context of Generalized Full-Sum HMM Training. | Albert Zeyer, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2016 | ICFHR | Bidirectional Decoder Networks for Attention-Based End-to-End Offline Handwriting Recognition. | Patrick Doetsch, Albert Zeyer, Hermann Ney |
| 2016 | Interspeech | Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models. | Albert Zeyer, Ralf Schlter, Hermann Ney |