| 2022 | EMNLP | Towards Need-Based Spoken Language Understanding Model Updates: What Have We Learned? | Quynh Do, Judith Gaspers, Daniil Sorokin, Patrick Lehnen |
| 2021 | EMNLP | Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding. | Tobias Falke, Patrick Lehnen |
| 2021 | Interspeech | Predicting Temporal Performance Drop of Deployed Production Spoken Language Understanding Models. | Quynh Do, Judith Gaspers, Daniil Sorokin, Patrick Lehnen |
| 2021 | Interspeech | The Impact of Intent Distribution Mismatch on Semi-Supervised Spoken Language Understanding. | Judith Gaspers, Quynh Do, Daniil Sorokin, Patrick Lehnen |
| 2020 | COLING | Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances. | Tobias Falke, Markus Boese, Daniil Sorokin, Caglar Tirkaz, Patrick Lehnen |
| 2015 | NAACL | A Comparison of Update Strategies for Large-Scale Maximum Expected BLEU Training. | Joern Wuebker, Sebastian Muehr, Patrick Lehnen, Stephan Peitz, Hermann Ney |
| 2013 | Interspeech | Improving LVCSR with hidden conditional random fields for grapheme-to-phoneme conversion. | Stefan Hahn, Patrick Lehnen, Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Structure learning in hidden conditional random fields for grapheme-to-phoneme conversion. | Patrick Lehnen, Alexandre Allauzen, Thomas Lavergne, Franois Yvon, Stefan Hahn, Hermann Ney |
| 2012 | Interspeech | Hidden Conditional Random Fields with M-to-N Alignments for Grapheme-to-Phoneme Conversion. | Patrick Lehnen, Stefan Hahn, Vlad-Andrei Guta, Hermann Ney |
| 2011 | ICASSP | Powerful extensions to CRFS for grapheme to phoneme conversion. | Stefan Hahn, Patrick Lehnen, Hermann Ney |
| 2011 | ICASSP | EM-style optimization of hidden conditional random fields for grapheme-to-phoneme conversion. | Georg Heigold, Stefan Hahn, Patrick Lehnen, Hermann Ney |
| 2011 | ICASSP | Incorporating alignments into Conditional Random Fields for grapheme to phoneme conversion. | Patrick Lehnen, Stefan Hahn, Andreas Guta, Hermann Ney |
| 2011 | Interspeech | N-Grams for Conditional Random Fields or a Failure-Transition(f) Posterior for Acyclic FSTs. | Patrick Lehnen, Stefan Hahn, Hermann Ney |
| 2010 | AMTA | A Comparison of Various Types of Extended Lexicon Models for Statistical Machine Translation. | Matthias Huck, Martin Ratajczak, Patrick Lehnen, Hermann Ney |
| 2010 | ICASSP | Discriminative HMMS, log-linear models, and CRFS: What is the difference? | Georg Heigold, Simon Wiesler, Markus Nubaum-Thom, Patrick Lehnen, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | Optimizing CRFs for SLU tasks in various languages using modified training criteria. | Stefan Hahn, Patrick Lehnen, Georg Heigold, Hermann Ney |
| 2009 | Interspeech | Large-scale Polish SLU. | Patrick Lehnen, Stefan Hahn, Hermann Ney, Agnieszka Mykowiecka |
| 2008 | Interspeech | System combination for spoken language understanding. | Stefan Hahn, Patrick Lehnen, Hermann Ney |
| 2008 | Interspeech | On the equivalence of Gaussian and log-linear HMMs. | Georg Heigold, Patrick Lehnen, Ralf Schlter, Hermann Ney |
| 2008 | LREC | A Comparison of Various Methods for Concept Tagging for Spoken Language Understanding. | Stefan Hahn, Patrick Lehnen, Christian Raymond, Hermann Ney |