Skip to main content

A Sequence Classification Framework for Human Language Technology

Searching for OpenAIRE data...

Publications

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

Author(s): Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes, Ralf Schlüter, Hermann Ney
Published in: ACL-IJCNLP 2021 Workshop on Document-grounded Dialogue and Conversational QA, 2021

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

Author(s): Beck, Eugen; Zhou, Wei; Schlüter, Ralf; Ney, Hermann
Published in: Issue 32, 2019

Towards a Better Evaluation of Metrics for Machine Translation

Author(s): Peter Stanchev, Weiyue Wang, Hermann Ney
Published in: 5th Conference on Machine Translation (WMT), 2020

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Author(s): Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
Published in: ACL-IJCNLP 2021 Workshop on Document-grounded Dialogue and Conversational QA, 2021

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

Author(s): Zeineldeen, Mohammad; Zeyer, Albert; Zhou, Wei; Ng, Thomas; Schlüter, Ralf; Ney, Hermann
Published in: Issue 5, 2020

Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

Author(s): Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney
Published in: International Workshop on Spoken Language Translation, IWSLT 2021, 2021

Investigation on Data Adaptation Techniques for Neural Named Entity Recognition

Author(s): Evgeniia Tokarchuk, David Thulke, Weiyue Wang, Christian Dugast, Hermann Ney
Published in: ACL-IJCNLP 2021 Student Research Workshop, 2021

Feature Replacement and Combination for Hybrid ASR Systems

Author(s): Peter Vieting, Christoph Lüscher, Wilfried Michel, Ralf Schlüter, Hermann Ney
Published in: 2021

Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models

Author(s): Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2021, 2021

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Author(s): Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
Published in: 2021

Investigation of Transformer-based Latent Attention Models for Neural Machine Translation

Author(s): Parnia Bahar, Nikita Makarov, Hermann Ney
Published in: 14th Biennial Conference of the Association for Machine Translation in the Americas, 2020

On Sampling-Based Training Criteria for Neural Language Modeling

Author(s): Yingbo Gao, David Thulke, Alexander Gerstenberger, Khoa Viet Tran, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2021, 2021

Towards a Better Understanding of Label Smoothing in Neural Machine Translation

Author(s): Yingbo Gao, Weiyue Wang, Christian Herold, Zijian Yang, Hermann Ney
Published in: 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020

A study of latent monotonic attention variants

Author(s): Zeyer, Albert; Schlüter, Ralf; Ney, Hermann
Published in: Issue 11, 2021

Transformer-Based Direct Hidden Markov Model for Machine Translation

Author(s): Weiyue Wang, Zijian Yang, Yingbo Gao, Hermann Ney
Published in: ACL-IJCNLP 2021 Student Research Workshop, 2021

Towards Consistent Hybrid HMM Acoustic Modeling

Author(s): Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney
Published in: 2021

Diving Deep into Context-Aware Neural Machine Translation

Author(s): Huo, Jingjing; Herold, Christian; Gao, Yingbo; Dahlmann, Leonard; Khadivi, Shahram; Ney, Hermann
Published in: Issue 21, 2020

Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept

Author(s): Wei Zhou, Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2021, 2021

Predicting and Using Target Length in Neural Machine Translation

Author(s): Zijian Yang, Yingbo Gao, Weiyue Wang, Hermann Ney
Published in: 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 2020

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

Author(s): Wei Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7839-7843
DOI: 10.1109/icassp40776.2020.9053573

Full-Sum Decoding for Hybrid Hmm Based Speech Recognition Using LSTM Language Model

Author(s): Wei Zhou, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7834-7838
DOI: 10.1109/icassp40776.2020.9053010

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

Author(s): Wei Zhou, Simon Berger, Ralf Schluter, Hermann Ney
Published in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, Page(s) 5644-5648
DOI: 10.1109/icassp39728.2021.9413648

A Comparison of Transformer and LSTM Encoder Decoder Models for ASR

Author(s): Albert Zeyer, Parnia Bahar, Kazuki Irie, Ralf Schluter, Hermann Ney
Published in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, Page(s) 8-15
DOI: 10.1109/asru46091.2019.9004025

Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition

Author(s): Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter, Hermann Ney
Published in: 2021

Training Language Models for Long-Span Cross-Sentence Evaluation

Author(s): Kazuki Irie, Albert Zeyer, Ralf Schluter, Hermann Ney
Published in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, Page(s) 419-426
DOI: 10.1109/asru46091.2019.9003788

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

Author(s): Parnia Bahar, Tobias Bieschke, Ralf Schluter, Hermann Ney
Published in: 2021 IEEE Spoken Language Technology Workshop (SLT), 2021, Page(s) 950-957
DOI: 10.1109/slt48900.2021.9383462

Frame-Level MMI as A Sequence Discriminative Training Criterion for LVCSR

Author(s): Wilfried Michel, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 6904-6908
DOI: 10.1109/icassp40776.2020.9053499

Domain Robust, Fast, and Compact Neural Language Models

Author(s): Alexander Gerstenberger, Kazuki Irie, Pavel Golik, Eugen Beck, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7954-7958
DOI: 10.1109/icassp40776.2020.9054399

Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR

Author(s): Mohammad Zeineldeen, Albert Zeyer, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7679-7683
DOI: 10.1109/icassp40776.2020.9053635

Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems

Author(s): Nick Rossenbach, Albert Zeyer, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7069-7073
DOI: 10.1109/icassp40776.2020.9053008

How Much Self-Attention Do We Needƒ Trading Attention for Feed-Forward Layers

Author(s): Kazuki Irie, Alexander Gerstenberger, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 6154-6158
DOI: 10.1109/icassp40776.2020.9054324

RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition

Author(s): Albert Zeyer, Tamer Alkhouli, and Hermann Ney
Published in: Annual Meeting of the Association for Computational Linguistics, Issue annual, 2018

The RWTH Aachen Machine Translation Systems for IWSLT 2017. In International Workshop on Spoken Language Translation

Author(s): Parnia Bahar, Jan Rosendahl, Nick Rossenbach, and Hermann Ney
Published in: 14th IWSLT International Workshop on Spoken Language Translation, Issue annual, 2017, Page(s) 29-34

Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward Language Models

Author(s): Kazuki Irie, Zhihong Lei, Ralf Schluter, Hermann Ney
Published in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, Page(s) 6104-6108
DOI: 10.1109/icassp.2018.8461743

Neural Hidden Markov Model for Machine Translation

Author(s): Weiyue Wang, D. Zhu, Tamer Alkhouli, Z. Gan, and Hermann Ney
Published in: Annual Meeting of the Association for Computational Linguistics, Issue annual, 2018

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

Author(s): Albert Zeyer, Kazuki Irie, Ralf Schlüter, and Hermann Ney
Published in: Interspeech 2018, Issue annual, 2018

Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation

Author(s): Weiyue Wang, Tamer Alkhouli, Derui Zhu, Hermann Ney
Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Issue annual, 2017, Page(s) 125-131
DOI: 10.18653/v1/P17-2020

 Biasing Attention-Based Recurrent Neural Networks Using External Alignment Information

Author(s): Tamer Alkhouli, and Hermann Ney
Published in: Proceeding of the Second Conference on Machine Translation, Issue annual, 2017, Page(s) 108-117

Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition

Author(s): Tobias Menne, Ralf Schluter, Hermann Ney
Published in: 2018 IEEE Spoken Language Technology Workshop (SLT), 2018, Page(s) 535-541
DOI: 10.1109/slt.2018.8639547

A comprehensive analysis on attention models

Author(s): A. Zeyer, A. Merboldt, R. Schlüter, H. Ney
Published in: Interpretability and Robustness in Audio, Speech, and Language (IRASL) Workshop, Conference on Neural Information Processing Systems (NeurIPS), Montreal, Canada, December 2018, Issue annual, 2018

Improving Neural Language Models with Weight Norm Initialization and Regularization

Author(s): C. Herold, Y. Gao, H. Ney
Published in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), volume 1, Issue annual, 2018, Page(s) 93-100
DOI: 10.18653/v1/w18-64010

The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018

Author(s): J. Schamper, J. Rosendahl, P. Bahar, Y. Kim, A. Nix, and H. Ney
Published in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), Issue annual, 2018
DOI: 10.18653/v1/w18-64053

The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task

Author(s): N. Rossenbach, J. Rosendahl, Y. Kim, M. Graça, A. Gokrani, and H. Ney
Published in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), Issue annual, 2018
DOI: 10.18653/v1/w18-64115

On The Alignment Problem in Multi-Head Attention-Based Neural Machine Translation

Author(s): T. Alkhouli, G. Bretschner, and H. Ney
Published in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), Issue annual, 2018, Page(s) 177-185
DOI: 10.18653/v1/w18-64018

Investigation on Estimation of Sentence Probability by Combining Forward, Backward and Bi-directional LSTM-RNNs

Author(s): Kazuki Irie, Zhihong Lei, Liuhui Deng, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2018, Issue annual, 2018, Page(s) 392-395
DOI: 10.21437/interspeech.2018-1766

The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018

Author(s): M. Graça, Y. Kim, J. Schamper, J. Geng, and H. Ney
Published in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), Issue annual, 2018
DOI: 10.18653/v1/w18-64036

Deep fisher faces

Author(s): Harald Hanselmann, Shen Yan, Hermann Ney
Published in: Procedings of the British Machine Vision Conference 2017, 2017
DOI: 10.5244/c.31.165

Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition

Author(s): J. Peter, E. Beck, and H. Ney
Published in: Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018, Page(s) 84-89

The RWTH Aachen University English-German and German-English Machine Translation System for WMT 2017

Author(s): J. Peter, A. Guta, T. Alkhouli, P. Bahar, J. Rosendahl, N. Rossenbach, M. Graça, and H. Ney
Published in: EMNLP 2017 Second Conference on Machine Translation (WMT 2017), Issue annual, 2017, Page(s) 358-365

The RWTH/UPB system combination for the CHiME 2018 Workshop

Author(s): Markus Kitza, Wilfried Michel, Christoph Boeddeker, Jens Heitkaemper, Tobias Menne, Ralf Schlüter, Hermann Ney, Joerg Schmalenstroeer, Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach
Published in: CHiME 2018 Workshop on Speech Processing in Everyday Environments, 2018, Page(s) 53-57
DOI: 10.21437/chime.2018-12

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

Author(s): Markus Kitza, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2018, Issue Interspeech, 2018, Page(s) 877-881
DOI: 10.21437/interspeech.2018-2022

On Using 2D Sequence-to-sequence Models for Speech Recognition

Author(s): Parnia Bahar, Albert Zeyer, Ralf Schluter, Hermann Ney
Published in: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 5671-5675
DOI: 10.1109/icassp.2019.8682155

Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation

Author(s): P. Bahar, C. Brix, and H. Ney
Published in: Conference on Empirical Methods in Natural Language Processing (EMNLP), Issue annual, 2018

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

Author(s): Tobias Menne, Ralf Schluter, Hermann Ney
Published in: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 6660-6664
DOI: 10.1109/icassp.2019.8682460

Parallel Neural Network Features for Improved Tandem Acoustic Modeling

Author(s): Zoltán Tüske, Wilfried Michel, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2017, Issue annual, 2017, Page(s) 1651-1655
DOI: 10.21437/interspeech.2017-1747

Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder

Author(s): Y. Kim, J. Geng, and H. Ney
Published in: Conference on Empirical Methods in Natural Language Processing (EMNLP), Issue annual, 2018

CTC in the Context of Generalized Full-Sum HMM Training

Author(s): Albert Zeyer, Eugen Beck, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2017, Issue annual, 2017, Page(s) 944-948
DOI: 10.21437/interspeech.2017-1073

Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition

Author(s): Eugen Beck, Mirko Hannemann, Patrick Dötsch, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2018, Issue annual, 2018, Page(s) 766-770
DOI: 10.21437/interspeech.2018-1212

Learning Acoustic Features from the Raw Waveform for Automatic Speech Recognition

Author(s): T. Menne, Z. Tüske, R. Schlüter, and H. Ney
Published in: 44. Jahrestagung für Akustik der Deutschen Gesellschaft für Akustik, Issue annual, 2018, Page(s) 1533-1536

Sequence Modeling and Alignment for LVCSR-Systems

Author(s): E. Beck, A. Zeyer, P. Doetsch, A. Merboldt, R. Schlüter, and H. Ney
Published in: ITG Conference on Speech Communication (ITG), Issue annual, 2018

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

Author(s): Zoltán Tüske, Ralf Schlüter, Hermann Ney
Published in: Interspeech 2018, Issue annual, 2018, Page(s) 3358-3362
DOI: 10.21437/interspeech.2018-2476

Acoustic Modeling of Speech Waveform Based on Multi-Resolution, Neural Network Signal Processing

Author(s): Zoltan Tuske, Ralf Schluter, Hermann Ney
Published in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Issue annual, 2018, Page(s) 4859-4863
DOI: 10.1109/icassp.2018.8461871

A Comparative Study on End-to-End Speech to Text Translation

Author(s): Parnia Bahar, Tobias Bieschke, Hermann Ney
Published in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, Page(s) 792-799
DOI: 10.1109/asru46091.2019.9003774

A Comprehensive Study of Residual CNNS for Acoustic Modeling in ASR

Author(s): Vitalii Bozheniuk, Albert Zeyer, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7674-7678
DOI: 10.1109/icassp40776.2020.9052931

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

Author(s): Parnia Bahar, Nikita Makarov, Albert Zeyer, Ralf Schluter, Hermann Ney
Published in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7854-7858
DOI: 10.1109/icassp40776.2020.9054545

Analysis of Positional Encodings for Neural Machine Translation

Author(s): Jan Rosendahl, Viet Anh Khoa Tran, Weiyue Wang, Hermann Ney
Published in: International Workshop on Spoken Language Translation, 2019

Generating Alignments Using Target Foresight in Attention-Based Neural Machine Translation

Author(s): Jan-Thorsten Peter, Arne Nix, Hermann Ney
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 108/1, 2017, ISSN 1804-0462
DOI: 10.1515/pralin-2017-0006

Empirical Investigation of Optimization Algorithms in Neural Machine Translation

Author(s): Parnia Bahar, Tamer Alkhouli, Jan-Thorsten Peter, Christopher Jan-Steffen Brix, Hermann Ney
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 108/1, 2017, Page(s) 13-26, ISSN 1804-0462
DOI: 10.1515/pralin-2017-0005

Upper and Lower Tight Error Bounds for Feature Omission with an Extension to Context Reduction

Author(s): Ralf Schluter, Eugen Beck, Hermann Ney
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Issue 41/2, 2019, Page(s) 502-514, ISSN 0162-8828
DOI: 10.1109/tpami.2017.2788434

Inverted Alignments for End-to-End Automatic Speech Recognition

Author(s): Patrick Doetsch, Mirko Hannemann, Ralf Schluter, Hermann Ney
Published in: IEEE Journal of Selected Topics in Signal Processing, Issue 11/8, 2017, Page(s) 1265-1273, ISSN 1932-4553
DOI: 10.1109/jstsp.2017.2752691