Georg Heigold

发表

End-to-end text-dependent speaker verification

Georg Heigold, Samy Bengio, Noam Shazeer, 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The 2006 RWTH parliamentary speeches transcription system

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2006, INTERSPEECH.

Margin-Based Discriminative Training for String Recognition

Georg Heigold, Hermann Ney, Ralf Schlüter, 2010, IEEE Journal of Selected Topics in Signal Processing.

Speech recognition with state-based nearest neighbour classifiers

Georg Heigold, Hermann Ney, Thomas Deselaers, 2007, INTERSPEECH.

Investigations on an EM-Style Optimization Algorithm for Discriminative Training of HMMs

Georg Heigold, Hermann Ney, Ralf Schlüter, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Investigations on features for log-linear acoustic models in continuous speech recognition

Georg Heigold, Hermann Ney, Ralf Schlüter, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

Speech Recognition With Flat Direct Models

Geoffrey Zweig, Georg Heigold, Patrick Nguyen, 2010, IEEE Journal of Selected Topics in Signal Processing.

Development of the 2007 RWTH Mandarin LVCSR system

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Sequence discriminative distributed training of long short-term memory recurrent neural networks

Georg Heigold, Oriol Vinyals, Erik McDermott, 2014, INTERSPEECH.

Deep neural networks with auxiliary Gaussian mixture models for real-time speech recognition

Hui Lin, Georg Heigold, Xin Lei, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Confidence- and margin-based MMI/MPE discriminative training for off-line handwriting recognition

Georg Heigold, Hermann Ney, Philippe Dreuw, 2011, International Journal on Document Analysis and Recognition (IJDAR).

A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture

Georg Heigold, Erik McDermott, Ehsan Variani, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

GMM-Free DNN Training

Georg Heigold, Michiel Bacchiani, Andrew W. Senior, 2014 .

2009 IEEE Workshop on Automatic Speech Recognition & Understanding, ASRU 2009, Merano/Meran, Italy, December 13-17, 2009

Nobuaki Minematsu, Georg Heigold, Hermann Ney, 2009, ASRU.

Asynchronous stochastic optimization for sequence training of deep neural networks

Georg Heigold, Michiel Bacchiani, Erik McDermott, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

Exemplar-based speech recognition in a rescoring approach

Georg Heigold, 2012, MLSLP.

GMM-free DNN acoustic model training

Georg Heigold, Hank Liao, Michiel Bacchiani, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Development of the GALE 2008 Mandarin LVCSR system

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2009, INTERSPEECH.

The RWTH 2007 TC-STAR evaluation system for european English and Spanish

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2007, INTERSPEECH.

A discriminative splitting criterion for phonetic decision trees

Georg Heigold, Hermann Ney, Ralf Schlüter, 2010, INTERSPEECH.

Overview of large scale optimization for discriminative training in speech recognition

Stephen J. Wright, Georg Heigold, Hermann Ney, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

( Modeling, criteria, optimization, implementation, and performance )

Georg Heigold, Hermann Ney, Ralf Schlüter, 2012 .

Small-footprint keyword spotting using deep neural networks

Georg Heigold, Carolina Parada, Guoguo Chen, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cross-lingual Character-Level Neural Morphological Tagging pdf

Ryan Cotterell, Georg Heigold, G. Heigold, 2017, EMNLP.

On the equivalence of Gaussian and log-linear HMMs

Georg Heigold, Hermann Ney, Ralf Schlüter, 2008, INTERSPEECH.

Large Vocabulary Continuous Speech Recognition with Long Short-Term Recurrent Networks

Georg Heigold, Oriol Vinyals, Erik McDermott, 2014 .

Confidence-Based Discriminative Training for Model Adaptation in Offline Arabic Handwriting Recognition

Georg Heigold, Hermann Ney, Philippe Dreuw, 2009, 2009 10th International Conference on Document Analysis and Recognition.

Discriminative Training for Automatic Speech Recognition: Modeling, Criteria, Optimization, Implementation, and Performance

Georg Heigold, Hermann Ney, Ralf Schlüter, 2012, IEEE Signal Processing Magazine.

On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields

Georg Heigold, Hermann Ney, Ralf Schlüter, 2007, INTERSPEECH.

Introduction to the Special Section on Large-Scale Optimization for Audio, Speech, and Language Processing

Haizhou Li, Stephen J. Wright, Georg Heigold, 2013 .

A GIS-like training algorithm for log-linear models with hidden variables

Georg Heigold, Hermann Ney, Thomas Deselaers, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

An empirical study of learning rates in deep neural networks for speech recognition

Georg Heigold, Marc'Aurelio Ranzato, Ke Yang, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Generalized likelihood ratio discriminant analysis

Georg Heigold, Hermann Ney, Ralf Schlüter, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale pdf

Georg Heigold, Lucas Beyer, Alexey Dosovitskiy, 2020, ArXiv.

Multiframe deep neural networks for acoustic modeling

Georg Heigold, Vincent Vanhoucke, Matthieu Devin, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Modified MPE/MMI in a transducer-based framework

Georg Heigold, Hermann Ney, Ralf Schlüter, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Common Round: Application of Language Technologies to Large-Scale Web Debates

Josef van Genabith, Georg Heigold, He Wang, 2017, EACL.

SVMs, Gaussian mixtures, and their generative/discriminative fusion

Georg Heigold, Hermann Ney, Thomas Deselaers, 2008, 2008 19th International Conference on Pattern Recognition.

Posterior-Scaled MPE: Novel Discriminative Training Criteria

Georg Heigold, Hermann Ney, Ralf Schlüter, 2012, INTERSPEECH.

Multilingual acoustic models using distributed deep neural networks

Georg Heigold, Marc'Aurelio Ranzato, Patrick Nguyen, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?

Josef van Genabith, Georg Heigold, Günter Neumann, 2017, AMTA.

A flat direct model for speech recognition

Geoffrey Zweig, Georg Heigold, Xiao Li, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

The RWTH aachen university open source speech recognition system

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2009, INTERSPEECH.

Neural Morphological Tagging from Characters for Morphologically Rich Languages pdf

Josef van Genabith, Georg Heigold, Günter Neumann, 2016, ArXiv.

Latent Log-Linear Models for Handwritten Digit Classification

Georg Heigold, Hermann Ney, Tobias Gass, 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

EM-style optimization of hidden conditional random fields for grapheme-to-phoneme conversion

Georg Heigold, Hermann Ney, Stefan Hahn, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Optimizing CRFs for SLU tasks in various languages using modified training criteria

Georg Heigold, Hermann Ney, Stefan Hahn, 2009, INTERSPEECH.

Equivalence of Generative and Log-Linear Models

Georg Heigold, Hermann Ney, Tobias Gass, 2011, IEEE Transactions on Audio, Speech, and Language Processing.

Modified MMI/MPE: a direct evaluation of the margin in speech recognition

Georg Heigold, Hermann Ney, Thomas Deselaers, 2008, ICML '08.

A log-linear discriminative modeling framework for speech recognition

Georg Heigold, G. Heigold, 2010 .

Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition

Georg Heigold, Michiel Bacchiani, Andrew W. Senior, 2014, INTERSPEECH.

Eine Formulierung für den log-linearen, diskriminativen Ansatz in der Spracherkennung

Georg Heigold, 2010, Ausgezeichnete Informatikdissertationen.

Investigations on convex optimization using log-linear HMMs for digit string recognition

Georg Heigold, Hermann Ney, Ralf Schlüter, 2009, INTERSPEECH.

Object classification by fusing SVMs and Gaussian mixtures

Georg Heigold, Hermann Ney, Thomas Deselaers, 2010, Pattern Recognit..

Discriminative HMMS, log-linear models, and CRFS: What is the difference?

Georg Heigold, Hermann Ney, Ralf Schlüter, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Recent improvements of the RWTH GALE Mandarin LVCSR system

Georg Heigold, Hermann Ney, Björn Hoffmeister, 2008, INTERSPEECH.

Word embeddings for speech recognition

Georg Heigold, Samy Bengio, Samy Bengio, 2014, INTERSPEECH.

Object-Centric Learning with Slot Attention pdf

Georg Heigold, Alexey Dosovitskiy, Jakob Uszkoreit, 2020, NeurIPS.

An Extensive Empirical Evaluation of Character-Based Morphological Tagging for 14 Languages

Josef van Genabith, Georg Heigold, Günter Neumann, 2017, EACL.

Investigations on exemplar-based features for speech recognition towards thousands of hours of unsupervised, noisy data

Mitch Weintraub, Georg Heigold, Patrick Nguyen, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Optimization Algorithms and Applications for Speech and Language Processing

Haizhou Li, Stephen J. Wright, Georg Heigold, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Conditional Object-Centric Learning from Video pdf

Georg Heigold, Klaus Greff, Alexey Dosovitskiy, 2021, ArXiv.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale pdf

Georg Heigold, Xiaohua Zhai, Lucas Beyer, 2021, ICLR.

ViViT: A Video Vision Transformer pdf

Cordelia Schmid, Georg Heigold, Chen Sun, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).