R. Schlüter

发表

Mean-normalized stochastic gradient for large-scale deep learning

Hermann Ney, Ralf Schlüter, Simon Wiesler, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

INTERDEPENDENCE OF LANGUAGE MODELS AND DISCRIMINATIVE TRAINING

H. Ney, R. Schlüter, Boris Müller, 2007 .

Model-based MCE bound to the true Bayes' error

H. Ney, R. Schlüter, Ralf Schlüter, 2001, IEEE Signal Processing Letters.

LSTM Neural Networks for Language Modeling

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2012, INTERSPEECH.

Development of the SRI/nightingale Arabic ASR system

Andreas Stolcke, Wen Wang, Arindam Mandal, 2008, INTERSPEECH.

The RWTH 2010 Quaero ASR evaluation system for English, French, and German

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

RASR/NN: The RWTH neural network toolkit for speech recognition

Hermann Ney, Ralf Schlüter, Simon Wiesler, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

AUTOMATIC TRANSCRIPTION VERIFICATION OF BROADCAST NEWS AND SIMILAR SPEECH CORPORA

H. Ney, R. Schlüter, M. Pitz, 1999 .

Comparison of discriminative training criteria and optimization methods for speech recognition

Hermann Ney, Boris Müller, Wolfgang Macherey, 2001, Speech Commun..

The RWTH aachen university open source speech recognition system

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

Investigations on discriminative training criteria

Ralf Schlüter, R. Schlüter, Oliver Bender, 2000 .

LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition

Hermann Ney, Ralf Schlüter, Kazuki Irie, 2016, INTERSPEECH.

Investigations on error minimizing training criteria for discriminative training in automatic speech recognition

Hermann Ney, Wolfgang Macherey, Ralf Schlüter, 2005, INTERSPEECH.

Comparison of optimization methods for discriminative training criteria

Hermann Ney, Wolfgang Macherey, Ralf Schlüter, 1997, EUROSPEECH.

Confidence measures for large vocabulary continuous speech recognition

Hermann Ney, Ralf Schlüter, Klaus Macherey, 2001, IEEE Trans. Speech Audio Process..

Comparison of feedforward and recurrent neural network language models

Hermann Ney, Jean-Luc Gauvain, Ralf Schlüter, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Acoustic modeling with deep neural networks using raw time signal for LVCSR

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2014, INTERSPEECH.

Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition

Hermann Ney, Ralf Schlüter, Ilja Bezrukov, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Neural Networks for Language Modeling

H. Ney, R. Schlüter, M. Sundermeyer, 2012 .

The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task

H. Ney, R. Schlüter, Zoltán Tüske, 2016, IWSLT.

Non-stationary acoustic objects as atoms of voiced speech

R. Schlüter, F. Drepper, 2008 .

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

Georg Heigold, Hermann Ney, Ralf Schlüter, 2012 .

Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2016, INTERSPEECH.

Tight Integrated End-to-End Training for Cascaded Speech Translation pdf

Hermann Ney, Ralf Schlüter, Tobias Bieschke, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

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.

Does the Cost Function Matter in Bayes Decision Rule?

Hermann Ney, Ralf Schlüter, Markus Nußbaum-Thom, 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Simulation of Fixed Length Word String Probability Distributions

H. Ney, R. Schlüter, M. Nußbaum-Thom, 2012 .

Towards Consistent Hybrid HMM Acoustic Modeling pdf

Hermann Ney, Ralf Schlüter, Tina Raissi, 2021, ArXiv.

Self-Normalized Importance Sampling for Neural Language Modeling

H. Ney, R. Schlüter, Jintao Jiang, 2021, INTERSPEECH.

Efficient Sequence Training of Attention Models Using Approximative Recombination

H. Ney, R. Schlüter, Wilfried Michel, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Discrete Steps towards Approximate Computing

R. Schlüter, Albert Zeyer, Farhad Merchant, 2022, 2022 23rd International Symposium on Quality Electronic Design (ISQED).

Survey Talk: Modeling in Automatic Speech Recognition: Beyond Hidden Markov Models

Ralf Schlüter, R. Schlüter, 2019, INTERSPEECH.

Automatic Speech Recognition Based on Neural Networks

Ralf Schlüter, Patrick Doetsch, Albert Zeyer, 2016, SPECOM.

Investigation on LSTM Recurrent N-gram Language Models for Speech Recognition

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2018, INTERSPEECH.

A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition

Hermann Ney, Ralf Schlüter, Patrick Doetsch, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On Sampling-Based Training Criteria for Neural Language Modeling

H. Ney, R. Schlüter, Yingbo Gao, 2021, Interspeech.

Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2016, INTERSPEECH.

Inverted Alignments for End-to-End Automatic Speech Recognition

Hermann Ney, Ralf Schlüter, Mirko Hannemann, 2017, IEEE Journal of Selected Topics in Signal Processing.

CTC in the Context of Generalized Full-Sum HMM Training

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2017, INTERSPEECH.

Error bounds for context reduction and feature omission

Hermann Ney, Ralf Schlüter, Eugen Beck, 2015, INTERSPEECH.

Investigation on log-linear interpolation of multi-domain neural network language model

Hermann Ney, Ralf Schlüter, Kazuki Irie, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multilingual MRASTA features for low-resource keyword search and speech recognition systems

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Investigation into Joint Optimization of Single Channel Speech Enhancement and Acoustic Modeling for Robust ASR

Hermann Ney, Ralf Schlüter, Tobias Menne, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Language Modeling with Deep Transformers

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, INTERSPEECH.

On Using SpecAugment for End-to-End Speech Translation pdf

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, IWSLT.

A Comparison of Transformer and LSTM Encoder Decoder Models for ASR

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation

Hermann Ney, Athanasios Mouchtaris, Reinhold Haeb-Umbach, 2016 .

Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech pdf

Hermann Ney, Ralf Schlüter, Tobias Menne, 2019, INTERSPEECH.

Improved training of end-to-end attention models for speech recognition pdf

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2018, INTERSPEECH.

Computing Mel-frequency cepstral coefficients on the power spectrum

Hermann Ney, Ralf Schlüter, Sirko Molau, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Improving the Training Recipe for a Robust Conformer-based Hybrid Model

H. Ney, R. Schlüter, Jingjing Xu, 2022, INTERSPEECH.

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, INTERSPEECH.

Conformer-Based Hybrid ASR System For Switchboard Dataset

H. Ney, R. Schlüter, Wilfried Michel, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On Language Model Integration for RNN Transducer Based Speech Recognition

H. Ney, R. Schlüter, Wei Zhou, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multilingual hierarchical MRASTA features for ASR

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2013, INTERSPEECH.

An Analysis of Local Monotonic Attention Variants

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, INTERSPEECH.

Improving And Analyzing Neural Speaker Embeddings for ASR

H. Ney, R. Schlüter, Jingjing Xu, 2023, ArXiv.

Enhancing and Adversarial: Improve ASR with Speaker Labels

H. Ney, R. Schlüter, Wei Zhou, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment

Hermann Ney, Ralf Schlüter, Wei Zhou, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring pdf

Hermann Ney, Wei Zhou, Ralf Schlüter, 2019, ArXiv.

Cumulative Adaptation for BLSTM Acoustic Models pdf

Hermann Ney, Ralf Schlüter, Markus Kitza, 2019, INTERSPEECH.

Comparison of BLSTM-Layer-Specific Affine Transformations for Speaker Adaptation

Hermann Ney, Ralf Schlüter, Markus Kitza, 2018, INTERSPEECH.

Hierarchical hybrid language models for open vocabulary continuous speech recognition using WFST

Hermann Ney, Ralf Schlüter, M. Ali Basha Shaik, 2012, SAPA@INTERSPEECH.

Training of reduced-rank linear transformations for multi-layer polynomial acoustic features for speech recognition

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, Speech Commun..

Early Stage LM Integration Using Local and Global Log-Linear Combination pdf

Hermann Ney, Ralf Schlüter, Wilfried Michel, 2020, INTERSPEECH.

Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition

Hermann Ney, Ralf Schlüter, Mirko Hannemann, 2018, INTERSPEECH.

Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition Without Length Bias

Hermann Ney, Ralf Schlüter, Wei Zhou, 2020, INTERSPEECH.

Multilingual representations for low resource speech recognition and keyword search

Brian Kingsbury, Bhuvana Ramabhadran, Michael Picheny, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Training Language Models for Long-Span Cross-Sentence Evaluation

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

On the Estimation of Discount Parameters for Language Model Smoothing

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2011, INTERSPEECH.

RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2011 .

A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models.

H. Ney, R. Schlüter, Wei Zhou, 2020 .

A comprehensive analysis on attention models

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2019, NeurIPS 2019.

C L ] 8 M ay 2 01 8 Improved training of end-to-end attention models for speech recognition

H. Ney, R. Schlüter, Kazuki Irie, 2018 .

Context-Dependent MLPs for LVCSR: TANDEM, Hybrid or Both?

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2012, INTERSPEECH.

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

Hermann Ney, Ralf Schlüter, Wei Zhou, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sequence Modeling and Alignment for LVCSR-Systems

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2018, ITG Symposium on Speech Communication.

From Feedforward to Recurrent LSTM Neural Networks for Language Modeling

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Returnn: The RWTH extensible training framework for universal recurrent neural networks

Hermann Ney, Ralf Schlüter, Patrick Doetsch, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Comparison of discriminative training criteria

Wolfgang Macherey, Ralf Schlüter, R. Schlüter, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech pdf

Ralf Schlüter, Elma Kerz, Yu Qiao, 2021, Interspeech.

The RWTH/UPB system combination for the CHiME 2018 Workshop

Hermann Ney, Reinhold Haeb-Umbach, Ralf Schlüter, 2018, 5th International Workshop on Speech Processing in Everyday Environments (CHiME 2018).

Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Equivalence of Generative and Log-Linear Models

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

Inverted HMM - a Proof of Concept

Hermann Ney, Ralf Schlüter, Stefan Hegselmann, 2016, NIPS 2016.

Sequence-discriminative training of recurrent neural networks

Hermann Ney, Ralf Schlüter, Patrick Doetsch, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition

Hermann Ney, Ralf Schlüter, Albert Zeyer, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Using posterior word probabilities for improved speech recognition

Hermann Ney, Ralf Schlüter, Frank Wessel, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

Using word probabilities as confidence measures

Ralf Schlüter, Klaus Macherey, Frank Wessel, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

A critical evaluation of stochastic algorithms for convex optimization

Hermann Ney, Ralf Schlüter, Simon Wiesler, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Investigations on sequence training of neural networks

Hermann Ney, Ralf Schlüter, Simon Wiesler, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2014, INTERSPEECH.

Compound Word Recombination for German LVCSR

Hermann Ney, Ralf Schlüter, Amr El-Desoky Mousa, 2011, INTERSPEECH.

iROVER: Improving System Combination with Classification

Hermann Ney, Mari Ostendorf, Björn Hoffmeister, 2007, NAACL.

A convergence analysis of log-linear training and its application to speech recognition

Hermann Ney, Ralf Schlüter, Simon Wiesler, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

End-to-End Training of a Neural HMM with Label and Transition Probabilities

R. Schlüter, Wilfried Michel, Tina Raissi, 2023, ArXiv.

Convolutional neural networks for acoustic modeling of raw time signal in LVCSR

Hermann Ney, Ralf Schlüter, Zoltán Tüske, 2015, INTERSPEECH.

Investigations on byte-level convolutional neural networks for language modeling in low resource speech recognition

Hermann Ney, Ralf Schlüter, Kazuki Irie, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On the equivalence of Gaussian and log-linear HMMs

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

Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures

H. Ney, R. Schlüter, Mohammad Zeineldeen, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Margin-Based Discriminative Training for String Recognition

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

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.

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.

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

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

Advances in Arabic broadcast news transcription at RWTH

Hermann Ney, Ralf Schlüter, Stefan Hahn, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

The RWTH 2009 quaero ASR evaluation system for English and German

Hermann Ney, Ralf Schlüter, Martin Sundermeyer, 2010, INTERSPEECH.

Recent improvements of the RWTH GALE Mandarin LVCSR system

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

Hierarchical neural networks feature extraction for LVCSR system

Fabio Valente, Hynek Hermansky, Jithendra Vepa, 2007, INTERSPEECH.

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

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

Efficient estimation of speaker-specific projecting feature transforms

Hermann Ney, Ralf Schlüter, Jonas Lööf, 2007, INTERSPEECH.

System combination and score normalization for spoken term detection

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Cross domain automatic transcription on the TC-STAR EPPS corpus

Hermann Ney, Ralf Schlüter, Christian Gollan, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

The RWTH Large Vocabulary Speech Recognition System for Spontaneous Speech

Hermann Ney, Ralf Schlüter, Sirko Molau, 2000, KONVENS.

Fast Search for Large Vocabulary Speech Recognition

Hermann Ney, Ralf Schlüter, Sirko Molau, 2000 .

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.

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.

Open-Lexicon Language Modeling Combining Word and Character Levels

Hermann Ney, Michal Kozielski, Ralf Schlüter, 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

Log-linear model combination with word-dependent scaling factors

Hermann Ney, Björn Hoffmeister, Ralf Schlüter, 2009, INTERSPEECH.