Daniel Willett

Publication Activity (10 Years)

Years Active: 1990-2021
Publications (10 Years): 10

Top Venues

ICASSP

CoRR

INTERSPEECH

IEEE Trans. Consumer Electron.

University of Duisburg-Essen, Germany (PHD)

Education History

University of Duisburg-Essen, Germany

PHD

Publications

Xianrui Zheng, Yulan Liu, Deniz Gunceler, Daniel Willett
Using Synthetic Audio to Improve the Recognition of Out-of-Vocabulary Words in End-to-End Asr Systems. ICASSP (2021)
Manuel Giollo, Deniz Gunceler, Yulan Liu, Daniel Willett
Bootstrap an End-to-End ASR System by Multilingual Training, Transfer Learning, Text-to-Text Mapping and Synthetic Audio. Interspeech (2021)
Manuel Giollo, Deniz Gunceler, Yulan Liu, Daniel Willett
Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio. CoRR (2020)
Prabhat Pandey, Volker Leutnant, Simon Wiesler, Jahn Heymann, Daniel Willett
Improving Speech Recognition of Compound-Rich Languages. INTERSPEECH (2020)
Xianrui Zheng, Yulan Liu, Deniz Gunceler, Daniel Willett
Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems. CoRR (2020)
Jessica A. F. Thompson, Marc Schönwiesner, Yoshua Bengio, Daniel Willett
How Transferable Are Features in Convolutional Neural Network Acoustic Models across Languages? ICASSP (2019)
Atta Norouzian, Bogdan Mazoure, Dermot Connolly, Daniel Willett
Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed. ICASSP (2019)
Atta Norouzian, Bogdan Mazoure, Dermot Connolly, Daniel Willett
Exploring attention mechanism for acoustic-based classification of speech utterances into system-directed and non-system-directed. CoRR (2019)
Felix Weninger, Yang Sun, Junho Park, Daniel Willett, Puming Zhan
Deep Learning Based Mandarin Accent Identification for Accent Robust ASR. INTERSPEECH (2019)
Gakuto Kurata, Daniel Willett
Deep neural network training emphasizing central frames. INTERSPEECH (2015)
Zixing Zhang, Joel Pinto, Christian Plahl, Björn W. Schuller, Daniel Willett
Channel mapping using bidirectional long short-term memory for dereverberation in hands-free voice controlled devices. IEEE Trans. Consumer Electron. 60 (3) (2014)
Sharmistha S. Gray, Daniel Willett, Jianhua Lu, Joel Pinto, Paul Maergner, Nathan Bodenstab
Child automatic speech recognition for US English: child interaction with living-room-electronic-devices. WOCCI (2014)
Zoltán Tüske, Joel Pinto, Daniel Willett, Ralf Schlüter
Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions. ICASSP (2013)
Daniel Willett, Chuang He
Discriminative training for complementariness in system combination. INTERSPEECH (2008)
Ying Sun, Daniel Willett, Raymond Brueckner, Rainer Gruhn, Dirk Bühler
Experiments on Chinese speech recognition with tonal models and pitch estimation using the Mandarin speecon data. INTERSPEECH (2006)
Jochen Schwenninger, Raymond Brueckner, Daniel Willett, Marcus E. Hennecke
Language Identification in Vocal Music. ISMIR (2006)
Daniel Willett, Franz Gerl, Raymond Brueckner
Discriminatively Trained Context-Dependent Duration-Bigram Models for Korean Digit Recognition. ICASSP (1) (2006)
Daniel Willett
Context-Dependent Duration Modeling. ICASSP (1) (2005)
Daniel Willett
Error - weighted discriminative training for HMM parameter estimation. INTERSPEECH (2004)
Thomas Niesler, Daniel Willett
Unsupervised adaptation of statistical language models for speech recognition. South Afr. Comput. J. 30 (2003)
Daniel Willett, Thomas Niesler, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri
Pervasive unsupervised adaptation for lecture speech transcription. ICASSP (1) (2003)
Takaaki Hori, Daniel Willett, Yasuhiro Minami
Language model adaptation using WFST-based speaking-style translation. ICASSP (1) (2003)
Daniel Willett, Shigeru Katagiri
Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation. ICASSP (2002)
Thomas Niesler, Daniel Willett
Unsupervised language model adaptation for lecture speech transcription. INTERSPEECH (2002)
Frank Wallhoff, Daniel Willett, Gerhard Rigoll
Scaled likelihood linear regression for hidden Markov model adaptation. INTERSPEECH (2001)
Christoph Neukirchen, Jörg Rottland, Daniel Willett, Gerhard Rigoll
A continuous density interpretation of discrete HMM systems and MMI-neural networks. IEEE Trans. Speech Audio Process. 9 (4) (2001)
Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri
Time and memory efficient viterbi decoding for LVCSR using a precompiled search network. INTERSPEECH (2001)
Martha A. Larson, Daniel Willett, Joachim Köhler, Gerhard Rigoll
Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speeches. INTERSPEECH (2000)
Daniel Willett, Christoph Neukirchen, Gerhard Rigoll
DUcoder-the Duisburg University LVCSR stackdecoder. ICASSP (2000)
Frank Wallhoff, Daniel Willett, Gerhard Rigoll
Frame-discriminative and confidence-driven adaptation for LVCSR. ICASSP (2000)
Anja Brakensiek, Daniel Willett, Gerhard Rigoll
Improved Degraded Document Recognition with Hybrid Modeling Techniques and Character N-Grams. ICPR (2000)
Anja Brakensiek, Daniel Willett, Gerhard Rigoll
Unlimited Vocabulary Script Recognition Using Character N-Grams. DAGM-Symposium (2000)
Daniel Willett, Stefan Müller, Gerhard Rigoll
A discriminative training procedure based on language model and dictionary for LVCSR. EUROSPEECH (1999)
Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
Experiments in topic indexing of broadcast news using neural networks. ICASSP (1999)
Anja Brakensiek, Andreas Kosmala, Daniel Willett, Wenwei Wang, Gerhard Rigoll
Performance Evaluation of a New Hybrid Modeling Technique for Handwriting Recognition using On-Line and Off-Line Data. ICDAR (1999)
Daniel Willett, Christoph Neukirchen, Jörg Rottland, Gerhard Rigoll
Refining tree-based state clustering by means of formal concept analysis, balanced decision trees and automatically generated model-sets. ICASSP (1999)
Andreas Kosmala, Daniel Willett, Gerhard Rigoll
Advanced State Clustering for Very Large Vocabulary HMM-based On-Line Handwriting Recognition. ICDAR (1999)
Anja Brakensiek, Andreas Kosmala, Daniel Willett, Gerhard Rigoll
Vergleich verschiedener statistischer Modellierungsverfahren für die On- und Off-line Handschriftenerkennung. DAGM-Symposium (1999)
Jörg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
Speaker adaptation using regularization and network adaptation for hybrid MMI-NN/HMM speech recognition. EUROSPEECH (1999)
Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
Soft state-tying for HMM-based speech recognition. ICSLP (1998)
Daniel Willett, Andreas Worm, Christoph Neukirchen, Gerhard Rigoll
Confidence measures for HMM-based speech recognition. ICSLP (1998)
Christoph Neukirchen, Daniel Willett, Stefan Eickeler, Stefan Müller
Exploiting acoustic feature correlations by joint neural vector quantizer design in a discrete HMM system. ICASSP (1998)
Daniel Willett, Christoph Neukirchen, Gerhard Rigoll
Efficient search with posterior probability estimates in HMM-based speech recognition. ICASSP (1998)
Gerhard Rigoll, Daniel Willett
A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction. ICASSP (1998)
Stefan Müller, Gerhard Rigoll, Denis Mazurenok, Daniel Willett
Invariante Erkennung handskizzierter Piktogramme mit Anwendungsmöglichkeiten in der inhaltsorientierten Bilddatenbankabfrage. DAGM-Symposium (1998)
Daniel Willett, Gerhard Rigoll
Speech recognition with a new hybrid architecture combining neural networks and continuous HMM. ESANN (1998)
Daniel Willett, Arno Romer, Jörg Rottland, Gerhard Rigoll
A German dialogue system for scheduling dates and meetings by naturally spoken continuous speech. ICSLP (1998)
Gerhard Rigoll, Andreas Kosmala, Daniel Willett
A new hybrid approach to large vocabulary cursive handwriting recognition. ICPR (1998)
Daniel Willett, Gerhard Rigoll
Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction. NIPS (1997)
Daniel Willett, Christoph Neukirchen, Jörg Rottland
Dictionary-based discriminative HMM parameter estimation for continuous speech recognition systems. ICASSP (1997)
Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
Reduced lexicon trees for decoding in a MMIi-connectionist/HMM speech recognition system. EUROSPEECH (1997)
Jörg Rottland, Christoph Neukirchen, Daniel Willett
Performance of hybrid MMI-connectionist/HMM systems on the WSJ speech database. ICASSP (1997)
Jörg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
Large vocabulary speech recognition with context dependent MMI-connectionist / HMM systems using the WSJ database. EUROSPEECH (1997)
Daniel Willett, Gerhard Rigoll
A new approach to generalized mixture tying for continuous HMM-based speech recognition. EUROSPEECH (1997)
Joseph F. Smith, Daniel Willett, Sunil Paul
Overview of the space station communications networks. IEEE Netw. 4 (5) (1990)

Daniel Willett.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Daniel Willett