Daniel Willett

According to our database, Daniel Willett authored at least 53 papers between 1990 and 2021.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of four.

2021

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

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

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

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Improving Speech Recognition of Compound-Rich Languages.

Prabhat Pandey, Volker Leutnant, Simon Wiesler, Jahn Heymann, Daniel Willett

Proceedings of the Interspeech 2020, 2020

2019

Deep Learning Based Mandarin Accent Identification for Accent Robust ASR.

Felix Weninger, Yang Sun, Junho Park, Daniel Willett, Puming Zhan

Proceedings of the Interspeech 2019, 2019

How Transferable Are Features in Convolutional Neural Network Acoustic Models across Languages?

Jessica A. F. Thompson, Marc Schönwiesner, Yoshua Bengio, Daniel Willett

Proceedings of the IEEE International Conference on Acoustics, 2019

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

Proceedings of the IEEE International Conference on Acoustics, 2019

2015

Deep neural network training emphasizing central frames.

Gakuto Kurata, Daniel Willett

Proceedings of the INTERSPEECH 2015, 2015

2014

Channel mapping using bidirectional long short-term memory for dereverberation in hands-free voice controlled devices.

Zixing Zhang, Joel Pinto, Christian Plahl, Björn W. Schuller, Daniel Willett

IEEE Trans. Consumer Electron., 2014

Child automatic speech recognition for US English: child interaction with living-room-electronic-devices.

Sharmistha S. Gray, Daniel Willett, Jianhua Lu, Joel Pinto, Paul Maergner, Nathan Bodenstab

Proceedings of the 4st Workshop on Child, Computer and Interaction, 2014

2013

Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions.

Zoltán Tüske, Joel Pinto, Daniel Willett, Ralf Schlüter

Proceedings of the IEEE International Conference on Acoustics, 2013

2008

Discriminative training for complementariness in system combination.

Daniel Willett, Chuang He

Proceedings of the INTERSPEECH 2008, 2008

2006

Language Identification in Vocal Music.

Jochen Schwenninger, Raymond Brueckner, Daniel Willett, Marcus E. Hennecke

Proceedings of the ISMIR 2006, 2006

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 Bühler

Proceedings of the INTERSPEECH 2006, 2006

Discriminatively Trained Context-Dependent Duration-Bigram Models for Korean Digit Recognition.

Daniel Willett, Franz Gerl, Raymond Brueckner

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

Context-Dependent Duration Modeling.

Daniel Willett

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Error - weighted discriminative training for HMM parameter estimation.

Daniel Willett

Proceedings of the INTERSPEECH 2004, 2004

2003

Unsupervised adaptation of statistical language models for speech recognition.

Thomas Niesler, Daniel Willett

South Afr. Comput. J., 2003

Pervasive unsupervised adaptation for lecture speech transcription.

Daniel Willett, Thomas Niesler, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

Language model adaptation using WFST-based speaking-style translation.

Takaaki Hori, Daniel Willett, Yasuhiro Minami

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Unsupervised language model adaptation for lecture speech transcription.

Thomas Niesler, Daniel Willett

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation.

Daniel Willett, Shigeru Katagiri

Proceedings of the IEEE International Conference on Acoustics, 2002

2001

A continuous density interpretation of discrete HMM systems and MMI-neural networks.

Christoph Neukirchen, Jörg Rottland, Daniel Willett, Gerhard Rigoll

IEEE Trans. Speech Audio Process., 2001

Time and memory efficient viterbi decoding for LVCSR using a precompiled search network.

Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Scaled likelihood linear regression for hidden Markov model adaptation.

Frank Wallhoff, Daniel Willett, Gerhard Rigoll

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

2000

Beiträge zur statistischen Modellierung und effizienten Dekodierung in der automatischen Spracherkennung.

Daniel Willett

PhD thesis, 2000

Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speeches.

Martha A. Larson, Daniel Willett, Joachim Köhler, Gerhard Rigoll

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Improved Degraded Document Recognition with Hybrid Modeling Techniques and Character N-Grams.

Anja Brakensiek, Daniel Willett, Gerhard Rigoll

Proceedings of the 15th International Conference on Pattern Recognition, 2000

DUcoder-the Duisburg University LVCSR stackdecoder.

Daniel Willett, Christoph Neukirchen, Gerhard Rigoll

Proceedings of the IEEE International Conference on Acoustics, 2000

Frame-discriminative and confidence-driven adaptation for LVCSR.

Frank Wallhoff, Daniel Willett, Gerhard Rigoll

Proceedings of the IEEE International Conference on Acoustics, 2000

Unlimited Vocabulary Script Recognition Using Character N-Grams.

Anja Brakensiek, Daniel Willett, Gerhard Rigoll

Proceedings of the Mustererkennung 2000, 2000

1999

A discriminative training procedure based on language model and dictionary for LVCSR.

Daniel Willett, Stefan Müller, Gerhard Rigoll

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Speaker adaptation using regularization and network adaptation for hybrid MMI-NN/HMM speech recognition.

Jörg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Advanced State Clustering for Very Large Vocabulary HMM-based On-Line Handwriting Recognition.

Andreas Kosmala, Daniel Willett, Gerhard Rigoll

Proceedings of the Fifth International Conference on Document Analysis and Recognition, 1999

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

Proceedings of the Fifth International Conference on Document Analysis and Recognition, 1999

Refining tree-based state clustering by means of formal concept analysis, balanced decision trees and automatically generated model-sets.

Daniel Willett, Christoph Neukirchen, Jörg Rottland, Gerhard Rigoll

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Experiments in topic indexing of broadcast news using neural networks.

Christoph Neukirchen, Daniel Willett, Gerhard Rigoll

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Vergleich verschiedener statistischer Modellierungsverfahren für die On- und Off-line Handschriftenerkennung.

Anja Brakensiek, Andreas Kosmala, Daniel Willett, Gerhard Rigoll

Proceedings of the Mustererkennung 1999, 1999

1998

Confidence measures for HMM-based speech recognition.

Daniel Willett, Andreas Worm, Christoph Neukirchen, Gerhard Rigoll

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

A German dialogue system for scheduling dates and meetings by naturally spoken continuous speech.

Daniel Willett, Arno Romer, Jörg Rottland, Gerhard Rigoll

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Soft state-tying for HMM-based speech recognition.

Christoph Neukirchen, Daniel Willett, Gerhard Rigoll

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

A new hybrid approach to large vocabulary cursive handwriting recognition.

Gerhard Rigoll, Andreas Kosmala, Daniel Willett

Proceedings of the Fourteenth International Conference on Pattern Recognition, 1998

Efficient search with posterior probability estimates in HMM-based speech recognition.

Daniel Willett, Christoph Neukirchen, Gerhard Rigoll

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction.

Gerhard Rigoll, Daniel Willett

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Exploiting acoustic feature correlations by joint neural vector quantizer design in a discrete HMM system.

Christoph Neukirchen, Daniel Willett, Stefan Eickeler, Stefan Müller

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Speech recognition with a new hybrid architecture combining neural networks and continuous HMM.

Daniel Willett, Gerhard Rigoll

Proceedings of the 6th European Symposium on Artificial Neural Networks, 1998

Invariante Erkennung handskizzierter Piktogramme mit Anwendungsmöglichkeiten in der inhaltsorientierten Bilddatenbankabfrage.

Stefan Müller, Gerhard Rigoll, Denis Mazurenok, Daniel Willett

Proceedings of the Mustererkennung 1998, 20. DAGM-Symposium, Stuttgart, 29. September, 1998

1997

Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction.

Daniel Willett, Gerhard Rigoll

Proceedings of the Advances in Neural Information Processing Systems 10, 1997

A new approach to generalized mixture tying for continuous HMM-based speech recognition.

Daniel Willett, Gerhard Rigoll

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Large vocabulary speech recognition with context dependent MMI-connectionist / HMM systems using the WSJ database.

Jörg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Reduced lexicon trees for decoding in a MMIi-connectionist/HMM speech recognition system.

Christoph Neukirchen, Daniel Willett, Gerhard Rigoll

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Dictionary-based discriminative HMM parameter estimation for continuous speech recognition systems.

Daniel Willett, Christoph Neukirchen, Jörg Rottland

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

Performance of hybrid MMI-connectionist/HMM systems on the WSJ speech database.

Jörg Rottland, Christoph Neukirchen, Daniel Willett

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1990

Overview of the space station communications networks.

Joseph F. Smith, Daniel Willett, Sunil Paul

IEEE Netw., 1990