Skip to main content

A Sequence Classification Framework for Human Language Technology

Pubblicazioni

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

Autori: Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes, Ralf Schlüter, Hermann Ney
Pubblicato in: ACL-IJCNLP 2021 Workshop on Document-grounded Dialogue and Conversational QA, 2021
Editore: arXiv

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

Autori: Beck, Eugen; Zhou, Wei; Schlüter, Ralf; Ney, Hermann
Pubblicato in: 32, 2019
Editore: arXiv

Towards a Better Evaluation of Metrics for Machine Translation

Autori: Peter Stanchev, Weiyue Wang, Hermann Ney
Pubblicato in: 5th Conference on Machine Translation (WMT), 2020
Editore: Association for Computational Linguistics

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Autori: Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
Pubblicato in: ACL-IJCNLP 2021 Workshop on Document-grounded Dialogue and Conversational QA, 2021
Editore: arXiv

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

Autori: Zeineldeen, Mohammad; Zeyer, Albert; Zhou, Wei; Ng, Thomas; Schlüter, Ralf; Ney, Hermann
Pubblicato in: 5, 2020
Editore: arXiv

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

Autori: Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney
Pubblicato in: International Workshop on Spoken Language Translation, IWSLT 2021, 2021
Editore: Association for Computational Linguistics

Investigation on Data Adaptation Techniques for Neural Named Entity Recognition

Autori: Evgeniia Tokarchuk, David Thulke, Weiyue Wang, Christian Dugast, Hermann Ney
Pubblicato in: ACL-IJCNLP 2021 Student Research Workshop, 2021
Editore: Association for Computational Linguistics

Feature Replacement and Combination for Hybrid ASR Systems

Autori: Peter Vieting, Christoph Lüscher, Wilfried Michel, Ralf Schlüter, Hermann Ney
Pubblicato in: 2021
Editore: arXiv

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

Autori: Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2021, 2021
Editore: arXiv

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Autori: Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
Pubblicato in: 2021
Editore: arXiv

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

Autori: Parnia Bahar, Nikita Makarov, Hermann Ney
Pubblicato in: 14th Biennial Conference of the Association for Machine Translation in the Americas, 2020
Editore: Contribution to a conference proceedings

On Sampling-Based Training Criteria for Neural Language Modeling

Autori: Yingbo Gao, David Thulke, Alexander Gerstenberger, Khoa Viet Tran, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2021, 2021
Editore: arXiv

Towards a Better Understanding of Label Smoothing in Neural Machine Translation

Autori: Yingbo Gao, Weiyue Wang, Christian Herold, Zijian Yang, Hermann Ney
Pubblicato 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
Editore: Association for Computational Linguistics

A study of latent monotonic attention variants

Autori: Zeyer, Albert; Schlüter, Ralf; Ney, Hermann
Pubblicato in: 11, 2021
Editore: arXiv

Transformer-Based Direct Hidden Markov Model for Machine Translation

Autori: Weiyue Wang, Zijian Yang, Yingbo Gao, Hermann Ney
Pubblicato in: ACL-IJCNLP 2021 Student Research Workshop, 2021
Editore: Association for Computational Linguistics

Towards Consistent Hybrid HMM Acoustic Modeling

Autori: Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney
Pubblicato in: 2021
Editore: arXiv

Two-Way Neural Machine Translation: A Proof of Concept for Bidirectional Translation Modeling using a Two-Dimensional Grid

Autori: Parnia Bahar; Christopher Brix; Hermann Ney
Pubblicato in: 6 Seiten (2020). doi:10.18154/RWTH-2021-02586, 10, 2020
Editore: IEEE
DOI: 10.18154/rwth-2021-02586

Diving Deep into Context-Aware Neural Machine Translation

Autori: Huo, Jingjing; Herold, Christian; Gao, Yingbo; Dahlmann, Leonard; Khadivi, Shahram; Ney, Hermann
Pubblicato in: 21, 2020
Editore: arXiv

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

Autori: Wei Zhou, Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2021, 2021
Editore: arXiv

Predicting and Using Target Length in Neural Machine Translation

Autori: Zijian Yang, Yingbo Gao, Weiyue Wang, Hermann Ney
Pubblicato 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
Editore: Association for Computational Linguistics

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention

Autori: Christoph Lüscher, Eugen Beck, Kazuki Irie, Markus Kitza, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2019, 2019, Page(s) 231-235
Editore: ISCA
DOI: 10.21437/interspeech.2019-1780

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

Autori: Wei Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7839-7843, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9053573

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

Autori: Wei Zhou, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7834-7838, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9053010

uniblock: Scoring and Filtering Corpus with Unicode Block Information.

Autori: Yingbo Gao; Weiyue Wang; Hermann Ney
Pubblicato in: EMNLP/IJCNLP (1), 11, 2019
Editore: Conference on Empirical Methods in Natural Language Processing
DOI: 10.18154/rwth-conv-240319

Investigation of Large-Margin Softmax in Neural Language Modeling

Autori: Jingjing Huo, Yingbo Gao, Weiyue Wang, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2020, 2020, Page(s) 3645-3649
Editore: ISCA
DOI: 10.21437/interspeech.2020-1849

EED: Extended Edit Distance Measure for Machine Translation

Autori: Peter Stanchev, Weiyue Wang, Hermann Ney
Pubblicato in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 514-520
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5359

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

Autori: Wei Zhou, Simon Berger, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, Page(s) 5644-5648, ISBN 978-1-7281-7605-5
Editore: IEEE
DOI: 10.1109/icassp39728.2021.9413648

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

Autori: Yunsu Kim, Jiahui Geng, Hermann Ney
Pubblicato in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, Page(s) 862-868
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/d18-1101

A Comparison of Transformer and LSTM Encoder Decoder Models for ASR

Autori: Albert Zeyer, Parnia Bahar, Kazuki Irie, Ralf Schluter, Hermann Ney
Pubblicato in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, Page(s) 8-15, ISBN 978-1-7281-0306-8
Editore: IEEE
DOI: 10.1109/asru46091.2019.9004025

Unifying Input and Output Smoothing in Neural Machine Translation

Autori: Yingbo Gao, Baohao Liao, Hermann Ney
Pubblicato in: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Page(s) 4361-4372
Editore: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.386

Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies

Autori: Yunsu Kim, Yingbo Gao, Hermann Ney
Pubblicato in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, Page(s) 1246-1257
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1120

A New Training Pipeline for an Improved Neural Transducer

Autori: Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2020, 2020, Page(s) 2812-2816
Editore: ISCA
DOI: 10.21437/interspeech.2020-1855

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

Autori: Wilfried Michel, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2020, 2020, Page(s) 3605-3609
Editore: ISCA
DOI: 10.21437/interspeech.2020-2675

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

Autori: Tobias Menne, Ilya Sklyar, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2019, 2019, Page(s) 2638-2642
Editore: ISCA
DOI: 10.21437/interspeech.2019-1728

On Using SpecAugment for End-to-End Speech Translation

Autori: Bahar, Parnia; Zeyer, Albert; Schlüter, Ralf; Ney, Hermann
Pubblicato in: 12, 2019
Editore: IWST
DOI: 10.5281/zenodo.3525010

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

Autori: Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter, Hermann Ney
Pubblicato in: 2021
Editore: arXiv

Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron

Autori: Yunsu Kim, Hendrik Rosendahl, Nick Rossenbach, Jan Rosendahl, Shahram Khadivi, Hermann Ney
Pubblicato in: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), 2019, Page(s) 61-71
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/w19-4309

Biasing Attention-Based Recurrent Neural Networks Using External Alignment Information

Autori: Tamer Alkhouli, Hermann Ney
Pubblicato in: Proceedings of the Second Conference on Machine Translation, 2017, Page(s) 108-117
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/w17-4711

Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture

Autori: Christopher Brix, Parnia Bahar, Hermann Ney
Pubblicato in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, Page(s) 3909-3915
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-main.360

Data Filtering using Cross-Lingual Word Embeddings

Autori: Christian Herold, Jan Rosendahl, Joris Vanvinckenroye, Hermann Ney
Pubblicato in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, Page(s) 162-172
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.15

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

Autori: Nick Rossenbach, Jan Rosendahl, Yunsu Kim, Miguel Graça, Aman Gokrani, Hermann Ney
Pubblicato in: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, 2018, Page(s) 946-954
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/w18-6487

Training Language Models for Long-Span Cross-Sentence Evaluation

Autori: Kazuki Irie, Albert Zeyer, Ralf Schluter, Hermann Ney
Pubblicato in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, Page(s) 419-426, ISBN 978-1-7281-0306-8
Editore: IEEE
DOI: 10.1109/asru46091.2019.9003788

Context-Dependent Acoustic Modeling Without Explicit Phone Clustering

Autori: Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2020, 2020, Page(s) 4377-4381
Editore: ISCA
DOI: 10.21437/interspeech.2020-1244

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

Autori: Parnia Bahar, Tobias Bieschke, Ralf Schluter, Hermann Ney
Pubblicato in: 2021 IEEE Spoken Language Technology Workshop (SLT), 2021, Page(s) 950-957, ISBN 978-1-7281-7066-4
Editore: IEEE
DOI: 10.1109/slt48900.2021.9383462

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

Autori: Wilfried Michel, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 6904-6908, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9053499

Language Modeling with Deep Transformers

Autori: Kazuki Irie, Albert Zeyer, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2019, 2019, Page(s) 3905-3909
Editore: ISCA
DOI: 10.21437/interspeech.2019-2225

Domain Robust, Fast, and Compact Neural Language Models

Autori: Alexander Gerstenberger, Kazuki Irie, Pavel Golik, Eugen Beck, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7954-7958, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9054399

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

Autori: Mohammad Zeineldeen, Albert Zeyer, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7679-7683, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9053635

Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages

Autori: Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
Pubblicato in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, Page(s) 866-876
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/d19-1080

When and Why is Document-level Context Useful in Neural Machine Translation?

Autori: Yunsu Kim, Duc Thanh Tran, Hermann Ney
Pubblicato in: Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), 2019, Page(s) 24-34
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/d19-6503

Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems

Autori: Nick Rossenbach, Albert Zeyer, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7069-7073, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9053008

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

Autori: Kazuki Irie, Alexander Gerstenberger, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 6154-6158, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9054324

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

Autori: Albert Zeyer, Tamer Alkhouli, Hermann Ney
Pubblicato in: Proceedings of ACL 2018, System Demonstrations, 2018, Page(s) 128-133
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/p18-4022

The RWTH Aachen Machine Translation Systems for IWSLT 2017

Autori: Parnia Bahar, Jan Rosendahl, Nick Rossenbach, and Hermann Ney
Pubblicato in: 14th IWSLT International Workshop on Spoken Language Translation, annual, 2017, Page(s) 29-34
Editore: In International Workshop on Spoken Language Translation
DOI: 10.18154/rwth-conv-220570

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

Autori: Kazuki Irie, Zhihong Lei, Ralf Schluter, Hermann Ney
Pubblicato in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, Page(s) 6104-6108, ISBN 978-1-5386-4658-8
Editore: IEEE
DOI: 10.1109/icassp.2018.8461743

Neural Hidden Markov Model for Machine Translation

Autori: Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan, Hermann Ney
Pubblicato in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2018, Page(s) 377-382
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/p18-2060

Improved Training of End-to-end Attention Models for Speech Recognition

Autori: Albert Zeyer, Kazuki Irie, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2018, 2018, Page(s) 7-11
Editore: ISCA
DOI: 10.21437/interspeech.2018-1616

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

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

 Biasing Attention-Based Recurrent Neural Networks Using External Alignment Information

Autori: Tamer Alkhouli, and Hermann Ney
Pubblicato in: Proceeding of the Second Conference on Machine Translation, annual, 2017, Page(s) 108-117, ISBN 978-1-945626-96-8
Editore: In EMNLP 2017 Second Conference on Machine Translation 

Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition

Autori: Tobias Menne, Ralf Schluter, Hermann Ney
Pubblicato in: 2018 IEEE Spoken Language Technology Workshop (SLT), 2018, Page(s) 535-541, ISBN 978-1-5386-4334-1
Editore: IEEE
DOI: 10.1109/slt.2018.8639547

A comprehensive analysis on attention models

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

Improving Neural Language Models with Weight Norm Initialization and Regularization

Autori: C. Herold, Y. Gao, H. Ney
Pubblicato in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), volume 1, annual, 2018, Page(s) 93-100
Editore: ACL (Association for Computational Linguistics)
DOI: 10.18653/v1/w18-64010

The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018

Autori: J. Schamper, J. Rosendahl, P. Bahar, Y. Kim, A. Nix, and H. Ney
Pubblicato in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), annual, 2018
Editore: Association for Computational Linguistics (ACL)
DOI: 10.18653/v1/w18-64053

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

Autori: N. Rossenbach, J. Rosendahl, Y. Kim, M. Graça, A. Gokrani, and H. Ney
Pubblicato in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), annual, 2018
Editore: Association for Computational Linguistics (ACL)
DOI: 10.18653/v1/w18-64115

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

Autori: T. Alkhouli, G. Bretschner, and H. Ney
Pubblicato in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), annual, 2018, Page(s) 177-185
Editore: Association for Computational Linguistics (ACL)
DOI: 10.18653/v1/w18-64018

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

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

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

Autori: M. Graça, Y. Kim, J. Schamper, J. Geng, and H. Ney
Pubblicato in: EMNLP 2018 Third Conference on Machine Translation (WMT 2018), annual, 2018
Editore: Association for Computational Linguistics (ACL)
DOI: 10.18653/v1/w18-64036

Deep fisher faces

Autori: Harald Hanselmann, Shen Yan, Hermann Ney
Pubblicato in: Procedings of the British Machine Vision Conference 2017, 2017, ISBN 1-901725-60-X
Editore: British Machine Vision Association
DOI: 10.5244/c.31.165

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

Autori: Jan-Thorsten Peter, Eugen Beck, Hermann Ney
Pubblicato in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2018, Page(s) 84-89
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/d18-2015

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

Autori: Jan-Thorsten Peter, Andreas Guta, Tamer Alkhouli, Parnia Bahar, Jan Rosendahl, Nick Rossenbach, Miguel Graça, Hermann Ney
Pubblicato in: Proceedings of the Second Conference on Machine Translation, 2017, Page(s) 358-365
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/w17-4735

The RWTH/UPB system combination for the CHiME 2018 Workshop

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

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

Autori: Markus Kitza, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2018, Interspeech, 2018, Page(s) 877-881
Editore: ISCA
DOI: 10.21437/interspeech.2018-2022

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

Autori: Parnia Bahar, Albert Zeyer, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 5671-5675, ISBN 978-1-4799-8131-1
Editore: IEEE
DOI: 10.1109/icassp.2019.8682155

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

Autori: Parnia Bahar, Christopher Brix, Hermann Ney
Pubblicato in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, Page(s) 3009-3015
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/d18-1335

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

Autori: Tobias Menne, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 6660-6664, ISBN 978-1-4799-8131-1
Editore: IEEE
DOI: 10.1109/icassp.2019.8682460

Parallel Neural Network Features for Improved Tandem Acoustic Modeling

Autori: Zoltán Tüske, Wilfried Michel, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2017, annual, 2017, Page(s) 1651-1655
Editore: ISCA
DOI: 10.21437/interspeech.2017-1747

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

Autori: Y. Kim, J. Geng, and H. Ney
Pubblicato in: Conference on Empirical Methods in Natural Language Processing (EMNLP), annual, 2018
Editore: Association for Computational Linguistics (ACL)

CTC in the Context of Generalized Full-Sum HMM Training

Autori: Albert Zeyer, Eugen Beck, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2017, annual, 2017, Page(s) 944-948
Editore: ISCA
DOI: 10.21437/interspeech.2017-1073

Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition

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

Learning Acoustic Features from the Raw Waveform for Automatic Speech Recognition

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

Sequence Modeling and Alignment for LVCSR-Systems

Autori: E. Beck, A. Zeyer, P. Doetsch, A. Merboldt, R. Schlüter, and H. Ney
Pubblicato in: ITG Conference on Speech Communication (ITG), annual, 2018
Editore: Informationstechnische Gesellschaft (ITG)

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

Autori: Zoltán Tüske, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2018, annual, 2018, Page(s) 3358-3362
Editore: ISCA
DOI: 10.21437/interspeech.2018-2476

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

Autori: Zoltan Tuske, Ralf Schluter, Hermann Ney
Pubblicato in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), annual, 2018, Page(s) 4859-4863, ISBN 978-1-5386-4658-8
Editore: IEEE
DOI: 10.1109/icassp.2018.8461871

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

Autori: Parnia Bahar, Tobias Bieschke, Hermann Ney
Pubblicato in: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019, Page(s) 792-799, ISBN 978-1-7281-0306-8
Editore: IEEE
DOI: 10.1109/asru46091.2019.9003774

Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification

Autori: Gao, Yingbo; Herold, Christian; Wang, Weiyue; Ney, Hermann
Pubblicato in: 16th International Workshop on Spoken Language Translation 2019<br/>16th International Workshop on Spoken Language Translation, IWSLT 2019, Hong Kong, Peoples R China, on November 02 and 03, 2019-11-02 - 2019-11-03, 11, 2019
Editore: IWSLT
DOI: 10.5281/zenodo.3524999

A Comprehensive Study of Residual CNNS for Acoustic Modeling in ASR

Autori: Vitalii Bozheniuk, Albert Zeyer, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7674-7678, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9052931

Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation

Autori: Baohao Liao, Yingbo Gao, Hermann Ney
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Page(s) 1715-1724
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.155

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

Autori: Wei Zhou, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2020, 2020, Page(s) 1768-1772
Editore: ISCA
DOI: 10.21437/interspeech.2020-1958

Neural Language Modeling for Named Entity Recognition

Autori: Zhihong Lei, Weiyue Wang, Christian Dugast, Hermann Ney
Pubblicato in: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Page(s) 6937-6941
Editore: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.612

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

Autori: Parnia Bahar, Nikita Makarov, Albert Zeyer, Ralf Schluter, Hermann Ney
Pubblicato in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7854-7858, ISBN 978-1-5090-6631-5
Editore: IEEE
DOI: 10.1109/icassp40776.2020.9054545

Cumulative Adaptation for BLSTM Acoustic Models

Autori: Markus Kitza, Pavel Golik, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2019, 2019, Page(s) 754-758
Editore: ISCA
DOI: 10.21437/interspeech.2019-2162

Generalizing Back-Translation in Neural Machine Translation

Autori: Miguel Graça, Yunsu Kim, Julian Schamper, Shahram Khadivi, Hermann Ney
Pubblicato in: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), 2019, Page(s) 45-52
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5205

Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR

Autori: Wilfried Michel, Ralf Schlüter, Hermann Ney
Pubblicato in: Interspeech 2019, 2019, Page(s) 1601-1605
Editore: ISCA
DOI: 10.21437/interspeech.2019-2254

A comprehensive analysis on attention models

Autori: Zeyer, Albert; Merboldt, André; Schlüter, Ralf; Ney, Hermann
Pubblicato in: 1, 2019
Editore: NeurIPS
DOI: 10.18154/rwth-2019-03648

Analysis of Positional Encodings for Neural Machine Translation

Autori: Jan Rosendahl, Viet Anh Khoa Tran, Weiyue Wang, Hermann Ney
Pubblicato in: International Workshop on Spoken Language Translation, 2019
Editore: IWSLT

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

Autori: Jan-Thorsten Peter, Arne Nix, Hermann Ney
Pubblicato in: The Prague Bulletin of Mathematical Linguistics, 108/1, 2017, ISSN 1804-0462
Editore: In Conference of the European Association for Machine Translation
DOI: 10.1515/pralin-2017-0006

Empirical Investigation of Optimization Algorithms in Neural Machine Translation

Autori: Parnia Bahar, Tamer Alkhouli, Jan-Thorsten Peter, Christopher Jan-Steffen Brix, Hermann Ney
Pubblicato in: The Prague Bulletin of Mathematical Linguistics, 108/1, 2017, Page(s) 13-26, ISSN 1804-0462
Editore: In Conference of the European Association for Machine Translation
DOI: 10.1515/pralin-2017-0005

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

Autori: Ralf Schluter, Eugen Beck, Hermann Ney
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 41/2, 2019, Page(s) 502-514, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2017.2788434

Inverted Alignments for End-to-End Automatic Speech Recognition

Autori: Patrick Doetsch, Mirko Hannemann, Ralf Schluter, Hermann Ney
Pubblicato in: IEEE Journal of Selected Topics in Signal Processing, 11/8, 2017, Page(s) 1265-1273, ISSN 1932-4553
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/jstsp.2017.2752691