| 2021 | ICASSP | Using Synthetic Audio to Improve the Recognition of Out-of-Vocabulary Words in End-to-End Asr Systems. | Xianrui Zheng, Yulan Liu, Deniz Gunceler, Daniel Willett |
| 2021 | Interspeech | Bootstrap an End-to-End ASR System by Multilingual Training, Transfer Learning, Text-to-Text Mapping and Synthetic Audio. | Manuel Giollo, Deniz Gunceler, Yulan Liu, Daniel Willett |
| 2020 | Interspeech | Improving Speech Recognition of Compound-Rich Languages. | Prabhat Pandey, Volker Leutnant, Simon Wiesler, Jahn Heymann, Daniel Willett |
| 2019 | ICASSP | Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed. | Atta Norouzian, Bogdan Mazoure, Dermot Connolly, Daniel Willett |
| 2019 | ICASSP | How Transferable Are Features in Convolutional Neural Network Acoustic Models across Languages? | Jessica A. F. Thompson, Marc Schnwiesner, Yoshua Bengio, Daniel Willett |
| 2019 | Interspeech | Deep Learning Based Mandarin Accent Identification for Accent Robust ASR. | Felix Weninger, Yang Sun, Junho Park, Daniel Willett, Puming Zhan |
| 2015 | Interspeech | Deep neural network training emphasizing central frames. | Gakuto Kurata, Daniel Willett |
| 2013 | ICASSP | Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions. | Zoltn Tske, Joel Pinto, Daniel Willett, Ralf Schlter |
| 2008 | Interspeech | Discriminative training for complementariness in system combination. | Daniel Willett, Chuang He |
| 2006 | ICASSP | Discriminatively Trained Context-Dependent Duration-Bigram Models for Korean Digit Recognition. | Daniel Willett, Franz Gerl, Raymond Brueckner |
| 2006 | Interspeech | Experiments on Chinese speech recognition with tonal models and pitch estimation using the Mandarin speecon data. | Ying Sun, Daniel Willett, Raymond Brueckner, Rainer Gruhn, Dirk Bhler |
| 2005 | ICASSP | Context-Dependent Duration Modeling. | Daniel Willett |
| 2004 | Interspeech | Error - weighted discriminative training for HMM parameter estimation. | Daniel Willett |
| 2003 | ICASSP | Language model adaptation using WFST-based speaking-style translation. | Takaaki Hori, Daniel Willett, Yasuhiro Minami |
| 2003 | ICASSP | Pervasive unsupervised adaptation for lecture speech transcription. | Daniel Willett, Thomas Niesler, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri |
| 2002 | ICASSP | Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation. | Daniel Willett, Shigeru Katagiri |
| 2002 | Interspeech | Unsupervised language model adaptation for lecture speech transcription. | Thomas Niesler, Daniel Willett |
| 2001 | Interspeech | Scaled likelihood linear regression for hidden Markov model adaptation. | Frank Wallhoff, Daniel Willett, Gerhard Rigoll |
| 2001 | Interspeech | Time and memory efficient viterbi decoding for LVCSR using a precompiled search network. | Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri |
| 2000 | ICASSP | Frame-discriminative and confidence-driven adaptation for LVCSR. | Frank Wallhoff, Daniel Willett, Gerhard Rigoll |
| 2000 | ICASSP | DUcoder-the Duisburg University LVCSR stackdecoder. | Daniel Willett, Christoph Neukirchen, Gerhard Rigoll |
| 2000 | ICPR | Improved Degraded Document Recognition with Hybrid Modeling Techniques and Character N-Grams. | Anja Brakensiek, Daniel Willett, Gerhard Rigoll |
| 2000 | Interspeech | Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speeches. | Martha A. Larson, Daniel Willett, Joachim Khler, Gerhard Rigoll |
| 1999 | ICASSP | Experiments in topic indexing of broadcast news using neural networks. | Christoph Neukirchen, Daniel Willett, Gerhard Rigoll |
| 1999 | ICASSP | Refining tree-based state clustering by means of formal concept analysis, balanced decision trees and automatically generated model-sets. | Daniel Willett, Christoph Neukirchen, Jrg Rottland, Gerhard Rigoll |
| 1999 | ICDAR | Performance Evaluation of a New Hybrid Modeling Technique for Handwriting Recognition using On-Line and Off-Line Data. | Anja Brakensiek, Andreas Kosmala, Daniel Willett, Wenwei Wang, Gerhard Rigoll |
| 1999 | ICDAR | Advanced State Clustering for Very Large Vocabulary HMM-based On-Line Handwriting Recognition. | Andreas Kosmala, Daniel Willett, Gerhard Rigoll |
| 1999 | Interspeech | Speaker adaptation using regularization and network adaptation for hybrid MMI-NN/HMM speech recognition. | Jrg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll |
| 1999 | Interspeech | A discriminative training procedure based on language model and dictionary for LVCSR. | Daniel Willett, Stefan Mller, Gerhard Rigoll |
| 1998 | ESANN | Speech recognition with a new hybrid architecture combining neural networks and continuous HMM. | Daniel Willett, Gerhard Rigoll |
| 1998 | ICASSP | Exploiting acoustic feature correlations by joint neural vector quantizer design in a discrete HMM system. | Christoph Neukirchen, Daniel Willett, Stefan Eickeler, Stefan Mller |
| 1998 | ICASSP | A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction. | Gerhard Rigoll, Daniel Willett |
| 1998 | ICASSP | Efficient search with posterior probability estimates in HMM-based speech recognition. | Daniel Willett, Christoph Neukirchen, Gerhard Rigoll |
| 1998 | ICPR | A new hybrid approach to large vocabulary cursive handwriting recognition. | Gerhard Rigoll, Andreas Kosmala, Daniel Willett |
| 1998 | Interspeech | Soft state-tying for HMM-based speech recognition. | Christoph Neukirchen, Daniel Willett, Gerhard Rigoll |
| 1998 | Interspeech | A German dialogue system for scheduling dates and meetings by naturally spoken continuous speech. | Daniel Willett, Arno Romer, Jrg Rottland, Gerhard Rigoll |
| 1998 | Interspeech | Confidence measures for HMM-based speech recognition. | Daniel Willett, Andreas Worm, Christoph Neukirchen, Gerhard Rigoll |
| 1997 | ICASSP | Performance of hybrid MMI-connectionist/HMM systems on the WSJ speech database. | Jrg Rottland, Christoph Neukirchen, Daniel Willett |
| 1997 | ICASSP | Dictionary-based discriminative HMM parameter estimation for continuous speech recognition systems. | Daniel Willett, Christoph Neukirchen, Jrg Rottland |
| 1997 | Interspeech | Reduced lexicon trees for decoding in a MMIi-connectionist/HMM speech recognition system. | Christoph Neukirchen, Daniel Willett, Gerhard Rigoll |
| 1997 | Interspeech | Large vocabulary speech recognition with context dependent MMI-connectionist / HMM systems using the WSJ database. | Jrg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll |
| 1997 | Interspeech | A new approach to generalized mixture tying for continuous HMM-based speech recognition. | Daniel Willett, Gerhard Rigoll |