Daniel Willett

56 papers A 13B 3Misc 14Journal 7Unranked 18

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