Daniel Willett

发表

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

Gerhard Rigoll, Daniel Willett, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

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

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1997, EUROSPEECH.

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

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1999, EUROSPEECH.

Deep neural network training emphasizing central frames

Daniel Willett, Gakuto Kurata, 2015, INTERSPEECH.

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

Gerhard Rigoll, Daniel Willett, 1998, ESANN.

Improving Speech Recognition of Compound-Rich Languages

Daniel Willett, Simon Wiesler, Jahn Heymann, 2020, INTERSPEECH.

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

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

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

Gerhard Rigoll, Daniel Willett, 1997, EUROSPEECH.

Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio pdf

Daniel Willett, Manuel Giollo, Deniz Gunceler, 2020, ArXiv.

Language Identification in Vocal Music

Daniel Willett, Jochen Schwenninger, Marcus E. Hennecke, 2006, ISMIR.

Soft state-tying for HMM-based speech recognition

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1998, ICSLP.

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

Shigeru Katagiri, Daniel Willett, S. Katagiri, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

Gerhard Rigoll, Anja Brakensiek, Andreas Kosmala, 1999, DAGM-Symposium.

Confidence measures for HMM-based speech recognition

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1998, ICSLP.

Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed

Daniel Willett, Bogdan Mazoure, Atta Norouzian, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A new hybrid approach to large vocabulary cursive handwriting recognition

Gerhard Rigoll, Andreas Kosmala, Daniel Willett, 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

Workshop report: USP workshop on advancements in in vitro performance testing of drug products

Fernando J. Muzzio, Matthias G. Wacker, Changquan Calvin Sun, 2020 .

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

Christoph Neukirchen, Stefan Eickeler, Daniel Willett, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Deep Learning Based Mandarin Accent Identification for Accent Robust ASR

Puming Zhan, Yang Sun, Felix Weninger, 2019, INTERSPEECH.

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

Franz Gerl, Daniel Willett, Raymond Brueckner, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

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

Christoph Neukirchen, Daniel Willett, Jörg Rottland, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

Gerhard Rigoll, Daniel Willett, Stefan Müller, 1999, EUROSPEECH.

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

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1997, EUROSPEECH.

Language model adaptation using WFST-based speaking-style translation

Takaaki Hori, Daniel Willett, Yasuhiro Minami, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

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

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

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

Gerhard Rigoll, Daniel Willett, 1997, NIPS.

Experiments in topic indexing of broadcast news using neural networks

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Error - weighted discriminative training for HMM parameter estimation

Daniel Willett, 2004, INTERSPEECH.

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

Gerhard Rigoll, Daniel Willett, Jörg Rottland, 1998, ICSLP.

Discriminative training for complementariness in system combination

Daniel Willett, Chuang He, 2008, INTERSPEECH.

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

Shigeru Katagiri, Erik McDermott, Daniel Willett, 2001, INTERSPEECH.

DUcoder-the Duisburg University LVCSR stackdecoder

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

Advanced state clustering for very large vocabulary HMM-based on-line handwriting recognition

Gerhard Rigoll, Andreas Kosmala, Daniel Willett, 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

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

Martha Larson, Joachim Köhler, Gerhard Rigoll, 2000, INTERSPEECH.

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

Christoph Neukirchen, Daniel Willett, Jörg Rottland, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A SYSTEMATIC COMPARISON OF ADVANCED MODELING TECHNIQUES FOR VERY LARGE VOCABULARY ON-LINE CURSIVE HANDWRITING RECOGNITION

A. Kosmala, G. Rigoll, Daniel Willett, 1999 .

Pervasive unsupervised adaptation for lecture speech transcription

Shigeru Katagiri, Thomas Niesler, Erik McDermott, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Speech corpus recycling for acoustic cross-domain environments for automatic speech recognition

Osamu Ichikawa, Takashi Fukuda, Daniel Willett, 2016 .

Performance evaluation of a new hybrid modeling technique for handwriting recognition using identical on-line and off-line data

Gerhard Rigoll, Anja Brakensiek, Andreas Kosmala, 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

Smoothed language model incorporation for efficient time-synchronous beam search decoding in LVCSR

Shigeru Katagiri, Erik McDermott, Daniel Willett, 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

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

Björn W. Schuller, Zixing Zhang, Daniel Willett, 2014, IEEE Transactions on Consumer Electronics.

Frame-discriminative and confidence-driven adaptation for LVCSR

Gerhard Rigoll, Frank Wallhoff, Daniel Willett, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems pdf

Daniel Willett, Deniz Gunceler, Yulan Liu, 2020, ArXiv.

System for voice-controlled selection of an audio file and method thereof

Daniel Willett, Raymond Brueckner, Franz S Dr Gerl, 2006 .

AN INVESTIGATION OF CONTEXT-DEPENDENT AND HYBRID MODELING TECHNIQUES FOR VERY LARGE VOCABULARY ON-LINE CURSIVE HANDWRITING RECOGNITION

A. Kosmala, Gerhard Rigoll, Daniel Willett, 1998 .

Scaled likelihood linear regression for hidden Markov model adaptation

Gerhard Rigoll, Frank Wallhoff, Daniel Willett, 2001, INTERSPEECH.

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

Christoph Neukirchen, Gerhard Rigoll, Daniel Willett, 2001, IEEE Trans. Speech Audio Process..

Experiments on Chinese speech recognition with tonal models and pitch estimation using the Mandarin speecon data

Rainer Gruhn, Ying Sun, Dirk Bühler, 2006, INTERSPEECH.

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

Jianhua Lu, Paul Maergner, Daniel Willett, 2014, WOCCI.

Improved degraded document recognition with hybrid modeling techniques and character n-grams

Gerhard Rigoll, Anja Brakensiek, Daniel Willett, 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

Unsupervised language model adaptation for lecture speech transcription

Thomas Niesler, Daniel Willett, T. Niesler, 2002, INTERSPEECH.

Context-Dependent Duration Modeling

Daniel Willett, 2005, ICASSP.

Invariante Erkennung handskizzierter Piktogramme mit Anwendungsmöglichkeiten in der inhaltsorientierten Bilddatenbankabfrage

Gerhard Rigoll, Daniel Willett, Stefan Müller, 1998, DAGM-Symposium.

Unsupervised adaptation of statistical language models for speech recognition

Thomas Niesler, Daniel Willett, 2003, South Afr. Comput. J..

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

Ralf Schlüter, Daniel Willett, Joel Pinto, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Productive wastewater is not a contradiction

Daniel Willett, 2004 .

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

Yoshua Bengio, Daniel Willett, Marc Schönwiesner, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unlimited Vocabulary Script Recognition Using Character N-Grams

Gerhard Rigoll, Anja Brakensiek, Daniel Willett, 2000, DAGM-Symposium.

Beiträge zur statistischen Modellierung und effizienten Dekodierung in der automatischen Spracherkennung

Daniel Willett, 2000 .

Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio pdf

Daniel Willett, Manuel Giollo, Yulan Liu, 2021, Interspeech 2021.