| 2026 | LREC | Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset. | Nick Rossenbach, Robin Schmitt, Tina Raissi, Simon Berger, Larissa Kleppel, Ralf Schlter |
| 2025 | ASRU | Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions. | Tina Raissi, Nick Rossenbach, Ralf Schlter |
| 2025 | ICASSP | Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression. | Jingjing Xu, Eugen Beck, Zijian Yang, Ralf Schlter |
| 2025 | ICASSP | Right Label Context in End-to-End Training of Time-Synchronous ASR Models. | Tina Raissi, Ralf Schlter, Hermann Ney |
| 2025 | ICASSP | The Conformer Encoder May Reverse the Time Dimension. | Robin Schmitt, Albert Zeyer, Mohammad Zeineldeen, Ralf Schlter, Hermann Ney |
| 2025 | ICASSP | Classification Error Bound for Low Bayes Error Conditions in Machine Learning. | Zijian Yang, Vahe Eminyan, Ralf Schlter, Hermann Ney |
| 2025 | Interspeech | Dynamic Acoustic Model Architecture Optimization in Training for ASR. | Jingjing Xu, Zijian Yang, Albert Zeyer, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2025 | Interspeech | Analyzing the Importance of Blank for CTC-Based Knowledge Distillation. | Benedikt Hilmes, Nick Rossenbach, Ralf Schlter |
| 2025 | Interspeech | Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach. | Nick Rossenbach, Benedikt Hilmes, Leon Brackmann, Moritz Gunz, Ralf Schlter |
| 2025 | Interspeech | Regularizing Learnable Feature Extraction for Automatic Speech Recognition. | Peter Vieting, Maximilian Kannen, Benedikt Hilmes, Ralf Schlter, Hermann Ney |
| 2025 | Interspeech | Label-Context-Dependent Internal Language Model Estimation for CTC. | Zijian Yang, Minh-Nghia Phan, Ralf Schlter, Hermann Ney |
| 2025 | NAACL | Medical Spoken Named Entity Recognition. | Khai Le-Duc, David Thulke, Hung-Phong Tran, Long Vo-Dang, Khai-Nguyen Nguyen, Truong-Son Hy, Ralf Schlter |
| 2024 | ICASSP | On the Relation Between Internal Language Model and Sequence Discriminative Training for Neural Transducers. | Zijian Yang, Wei Zhou, Ralf Schlter, Hermann Ney |
| 2024 | ICASSP | Chunked Attention-Based Encoder-Decoder Model for Streaming Speech Recognition. | Mohammad Zeineldeen, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2024 | Interspeech | Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition. | Jingjing Xu, Wei Zhou, Zijian Yang, Eugen Beck, Ralf Schlter |
| 2024 | Interspeech | Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality. | Tina Raissi, Christoph Lscher, Simon Berger, Ralf Schlter, Hermann Ney |
| 2024 | ITW | Refined Statistical Bounds for Classification Error Mismatches with Constrained Bayes Error. | Zijian Yang, Vahe Eminyan, Ralf Schlter, Hermann Ney |
| 2023 | ASRU | End-To-End Training of a Neural HMM with Label and Transition Probabilities. | Daniel Mann, Tina Raissi, Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2023 | ASRU | On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition. | Nick Rossenbach, Benedikt Hilmes, Ralf Schlter |
| 2023 | ASRU | Investigating The Effect of Language Models in Sequence Discriminative Training For Neural Transducers. | Zijian Yang, Wei Zhou, Ralf Schlter, Hermann Ney |
| 2023 | ICASSP | Efficient Utilization of Large Pre-Trained Models for Low Resource ASR. | Peter Vieting, Christoph Lscher, Julian Dierkes, Ralf Schlter, Hermann Ney |
| 2023 | ICASSP | Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers. | Zijian Yang, Wei Zhou, Ralf Schlter, Hermann Ney |
| 2023 | ICASSP | Enhancing and Adversarial: Improve ASR with Speaker Labels. | Wei Zhou, Haotian Wu, Jingjing Xu, Mohammad Zeineldeen, Christoph Lscher, Ralf Schlter, Hermann Ney |
| 2023 | Interspeech | RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition. | Wei Zhou, Eugen Beck, Simon Berger, Ralf Schlter, Hermann Ney |
| 2023 | Interspeech | Mixture Encoder for Joint Speech Separation and Recognition. | Simon Berger, Peter Vieting, Christoph Bddeker, Ralf Schlter, Reinhold Haeb-Umbach |
| 2023 | Interspeech | Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think. | Tina Raissi, Christoph Lscher, Moritz Gunz, Ralf Schlter, Hermann Ney |
| 2022 | ICASSP | Improving Factored Hybrid HMM Acoustic Modeling without State Tying. | Tina Raissi, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2022 | ICASSP | Efficient Sequence Training of Attention Models Using Approximative Recombination. | Nils-Philipp Wynands, Wilfried Michel, Jan Rosendahl, Ralf Schlter, Hermann Ney |
| 2022 | ICASSP | Conformer-Based Hybrid ASR System For Switchboard Dataset. | Mohammad Zeineldeen, Jingjing Xu, Christoph Lscher, Wilfried Michel, Alexander Gerstenberger, Ralf Schlter, Hermann Ney |
| 2022 | ICASSP | On Language Model Integration for RNN Transducer Based Speech Recognition. | Wei Zhou, Zuoyun Zheng, Ralf Schlter, Hermann Ney |
| 2022 | Interspeech | Automatic Learning of Subword Dependent Model Scales. | Felix Meyer, Wilfried Michel, Mohammad Zeineldeen, Ralf Schlter, Hermann Ney |
| 2022 | Interspeech | Self-Normalized Importance Sampling for Neural Language Modeling. | Zijian Yang, Yingbo Gao, Alexander Gerstenberger, Jintao Jiang, Ralf Schlter, Hermann Ney |
| 2022 | Interspeech | Improving the Training Recipe for a Robust Conformer-based Hybrid Model. | Mohammad Zeineldeen, Jingjing Xu, Christoph Lscher, Ralf Schlter, Hermann Ney |
| 2022 | Interspeech | Efficient Training of Neural Transducer for Speech Recognition. | Wei Zhou, Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2021 | ASRU | Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures. | Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes, Ralf Schlter, Hermann Ney |
| 2021 | ASRU | On Architectures and Training for Raw Waveform Feature Extraction in ASR. | Peter Vieting, Christoph Lscher, Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2021 | ICASSP | Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition. | Wei Zhou, Simon Berger, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | On Sampling-Based Training Criteria for Neural Language Modeling. | Yingbo Gao, David Thulke, Alexander Gerstenberger, Khoa Viet Tran, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech. | Yu Qiao, Wei Zhou, Elma Kerz, Ralf Schlter |
| 2021 | Interspeech | Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR Models. | Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | Librispeech Transducer Model with Internal Language Model Prior Correction. | Albert Zeyer, Andr Merboldt, Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept. | Wei Zhou, Albert Zeyer, Andr Merboldt, Ralf Schlter, Hermann Ney |
| 2021 | Interspeech | Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition. | Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition. | Parnia Bahar, Nikita Makarov, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | A Comprehensive Study of Residual CNNS for Acoustic Modeling in ASR. | Vitalii Bozheniuk, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | How Much Self-Attention Do We Need? Trading Attention for Feed-Forward Layers. | Kazuki Irie, Alexander Gerstenberger, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Frame-Level MMI as A Sequence Discriminative Training Criterion for LVCSR. | Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems. | Nick Rossenbach, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR. | Mohammad Zeineldeen, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment. | Wei Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schlter, Hermann Ney |
| 2020 | ICASSP | Full-Sum Decoding for Hybrid Hmm Based Speech Recognition Using LSTM Language Model. | Wei Zhou, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | LVCSR with Transformer Language Models. | Eugen Beck, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | Investigation of Large-Margin Softmax in Neural Language Modeling. | Jingjing Huo, Yingbo Gao, Weiyue Wang, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | Early Stage LM Integration Using Local and Global Log-Linear Combination. | Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | Context-Dependent Acoustic Modeling Without Explicit Phone Clustering. | Tina Raissi, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | A New Training Pipeline for an Improved Neural Transducer. | Albert Zeyer, Andr Merboldt, Ralf Schlter, Hermann Ney |
| 2020 | Interspeech | Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition Without Length Bias. | Wei Zhou, Ralf Schlter, Hermann Ney |
| 2019 | ASRU | Training Language Models for Long-Span Cross-Sentence Evaluation. | Kazuki Irie, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | ASRU | A Comparison of Transformer and LSTM Encoder Decoder Models for ASR. | Albert Zeyer, Parnia Bahar, Kazuki Irie, Ralf Schlter, Hermann Ney |
| 2019 | ICASSP | On Using 2D Sequence-to-sequence Models for Speech Recognition. | Parnia Bahar, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | ICASSP | Investigation into Joint Optimization of Single Channel Speech Enhancement and Acoustic Modeling for Robust ASR. | Tobias Menne, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Language Modeling with Deep Transformers. | Kazuki Irie, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Cumulative Adaptation for BLSTM Acoustic Models. | Markus Kitza, Pavel Golik, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | RWTH ASR Systems for LibriSpeech: Hybrid vs Attention. | Christoph Lscher, Eugen Beck, Kazuki Irie, Markus Kitza, Wilfried Michel, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech. | Tobias Menne, Ilya Sklyar, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | An Analysis of Local Monotonic Attention Variants. | Andr Merboldt, Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR. | Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings. | Anna Piunova, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2019 | Interspeech | Survey Talk: Modeling in Automatic Speech Recognition: Beyond Hidden Markov Models. | Ralf Schlter |
| 2018 | ICASSP | Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward Language Models. | Kazuki Irie, Zhihong Lei, Ralf Schlter, Hermann Ney |
| 2018 | ICASSP | Acoustic Modeling of Speech Waveform Based on Multi-Resolution, Neural Network Signal Processing. | Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2018 | Interspeech | Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition. | Eugen Beck, Mirko Hannemann, Patrick Dtsch, Ralf Schlter, Hermann Ney |
| 2018 | Interspeech | Investigation on Estimation of Sentence Probability by Combining Forward, Backward and Bi-directional LSTM-RNNs. | Kazuki Irie, Zhihong Lei, Liuhui Deng, Ralf Schlter, Hermann Ney |
| 2018 | Interspeech | Comparison of BLSTM-Layer-Specific Affine Transformations for Speaker Adaptation. | Markus Kitza, Ralf Schlter, Hermann Ney |
| 2018 | Interspeech | Investigation on LSTM Recurrent N-gram Language Models for Speech Recognition. | Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2018 | Interspeech | Improved Training of End-to-end Attention Models for Speech Recognition. | Albert Zeyer, Kazuki Irie, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | Returnn: The RWTH extensible training framework for universal recurrent neural networks. | Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilia Kulikov, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | Investigations on byte-level convolutional neural networks for language modeling in low resource speech recognition. | Kazuki Irie, Pavel Golik, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | Noisy objective functions based on the f-divergence. | Markus Nubaum-Thom, Ralf Schlter, Vaibhava Goel, Hermann Ney |
| 2017 | ICASSP | A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition. | Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlter, Hermann Ney |
| 2017 | ICASSP | Faster sequence training. | Albert Zeyer, Ilia Kulikov, Ralf Schlter, Hermann Ney |
| 2017 | Interspeech | Parallel Neural Network Features for Improved Tandem Acoustic Modeling. | Zoltn Tske, Wilfried Michel, Ralf Schlter, Hermann Ney |
| 2017 | Interspeech | CTC in the Context of Generalized Full-Sum HMM Training. | Albert Zeyer, Eugen Beck, Ralf Schlter, Hermann Ney |
| 2016 | ICASSP | Investigation on log-linear interpolation of multi-domain neural network language model. | Zoltn Tske, Kazuki Irie, Ralf Schlter, Hermann Ney |
| 2016 | Interspeech | LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition. | Kazuki Irie, Zoltn Tske, Tamer Alkhouli, Ralf Schlter, Hermann Ney |
| 2016 | Interspeech | Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models. | Albert Zeyer, Ralf Schlter, Hermann Ney |
| 2015 | ASRU | Multilingual representations for low resource speech recognition and keyword search. | Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, Abhinav Sethy, Kartik Audhkhasi, Xiaodong Cui, Ellen Kislal, Lidia Mangu, Markus Nubaum-Thom, Michael Picheny, Zoltn Tske, Pavel Golik, Ralf Schlter, Hermann Ney, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang, Philip C. Woodland |
| 2015 | ASRU | Speaker adaptive joint training of Gaussian mixture models and bottleneck features. | Zoltn Tske, Pavel Golik, Ralf Schlter, Hermann Ney |
| 2015 | ICASSP | Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions. | Jahn Heymann, Reinhold Haeb-Umbach, Pavel Golik, Ralf Schlter |
| 2015 | ICASSP | Improved strategies for a zero oov rate LVCSR system. | M. Ali Basha Shaik, Amr El-Desoky Mousa, Stefan Hahn, Ralf Schlter, Hermann Ney |
| 2015 | ICASSP | Investigation of mixture splitting concept for training linear bottlenecks of deep neural network acoustic models. | Muhammad Ali Tahir, Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2015 | ICASSP | Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables. | Zoltn Tske, Muhammad Ali Tahir, Ralf Schlter, Hermann Ney |
| 2015 | ICASSP | Sequence-discriminative training of recurrent neural networks. | Paul Voigtlaender, Patrick Doetsch, Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2015 | ICASSP | Investigations on sequence training of neural networks. | Simon Wiesler, Pavel Golik, Ralf Schlter, Hermann Ney |
| 2015 | Interspeech | Error bounds for context reduction and feature omission. | Eugen Beck, Ralf Schlter, Hermann Ney |
| 2015 | Interspeech | Convolutional neural networks for acoustic modeling of raw time signal in LVCSR. | Pavel Golik, Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2015 | Interspeech | Multilingual features based keyword search for very low-resource languages. | Pavel Golik, Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2015 | Interspeech | Bag-of-words input for long history representation in neural network-based language models for speech recognition. | Kazuki Irie, Ralf Schlter, Hermann Ney |
| 2015 | Interspeech | Improvements in RWTH LVCSR evaluation systems for Polish, Portuguese, English, urdu, and Arabic. | M. Ali Basha Shaik, Zoltn Tske, Muhammad Ali Tahir, Markus Nubaum-Thom, Ralf Schlter, Hermann Ney |
| 2014 | ICASSP | A family of discriminative training criteria based on the F-divergence for deep neural networks. | Markus Nubaum-Thom, Xiaodong Cui, Ralf Schlter, Vaibhava Goel, Hermann Ney |
| 2014 | ICASSP | Multilingual MRASTA features for low-resource keyword search and speech recognition systems. | Zoltn Tske, David Nolden, Ralf Schlter, Hermann Ney |
| 2014 | ICASSP | The RWTH English lecture recognition system. | Simon Wiesler, Kazuki Irie, Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2014 | ICASSP | RASR/NN: The RWTH neural network toolkit for speech recognition. | Simon Wiesler, Alexander Richard, Pavel Golik, Ralf Schlter, Hermann Ney |
| 2014 | ICASSP | Mean-normalized stochastic gradient for large-scale deep learning. | Simon Wiesler, Alexander Richard, Ralf Schlter, Hermann Ney |
| 2014 | ICFHR | Open-Lexicon Language Modeling Combining Word and Character Levels. | Michal Kozielski, Martin Matysiak, Patrick Doetsch, Ralf Schlter, Hermann Ney |
| 2014 | Interspeech | Word pair approximation for more efficient decoding with high-order language models. | David Nolden, Ralf Schlter, Hermann Ney |
| 2014 | Interspeech | RWTH LVCSR systems for quaero and EU-bridge: German, Polish, Spanish and Portuguese. | M. Ali Basha Shaik, Zoltn Tske, Muhammad Ali Tahir, Markus Nubaum-Thom, Ralf Schlter, Hermann Ney |
| 2014 | Interspeech | rwthlm - the RWTH aachen university neural network language modeling toolkit. | Martin Sundermeyer, Ralf Schlter, Hermann Ney |
| 2014 | Interspeech | Lattice decoding and rescoring with long-Span neural network language models. | Martin Sundermeyer, Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2014 | Interspeech | Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages. | Zoltn Tske, Pavel Golik, David Nolden, Ralf Schlter, Hermann Ney |
| 2014 | Interspeech | Acoustic modeling with deep neural networks using raw time signal for LVCSR. | Zoltn Tske, Pavel Golik, Ralf Schlter, Hermann Ney |
| 2013 | ASRU | Efficient nearly error-less LVCSR decoding based on incremental forward and backward passes. | David Nolden, Ralf Schlter, Hermann Ney |
| 2013 | ICASSP | A high-performance Cantonese keyword search system. | Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Kate M. Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlter, Abhinav Sethy, Philip C. Woodland |
| 2013 | ICASSP | Open vocabulary handwriting recognition using combined word-level and character-level language models. | Michal Kozielski, David Rybach, Stefan Hahn, Ralf Schlter, Hermann Ney |
| 2013 | ICASSP | System combination and score normalization for spoken term detection. | Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Brian Kingsbury, Kate M. Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlter, Abhinav Sethy, Philip C. Woodland |
| 2013 | ICASSP | Advanced search space pruning with acoustic look-ahead for WFST based LVCSR. | David Nolden, Ralf Schlter, Hermann Ney |
| 2013 | ICASSP | Feature combination and stacking of recurrent and non-recurrent neural networks for LVCSR. | Christian Plahl, Michal Kozielski, Ralf Schlter, Hermann Ney |
| 2013 | ICASSP | Comparison of feedforward and recurrent neural network language models. | Martin Sundermeyer, Ilya Oparin, Jean-Luc Gauvain, B. Freiberg, Ralf Schlter, Hermann Ney |
| 2013 | ICASSP | Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions. | Zoltn Tske, Joel Pinto, Daniel Willett, Ralf Schlter |
| 2013 | ICASSP | Deep hierarchical bottleneck MRASTA features for LVCSR. | Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2013 | ICASSP | A critical evaluation of stochastic algorithms for convex optimization. | Simon Wiesler, Alexander Richard, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Development of the RWTH transcription system for slovenian. | Pavel Golik, Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Improving LVCSR with hidden conditional random fields for grapheme-to-phoneme conversion. | Stefan Hahn, Patrick Lehnen, Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Morpheme level hierarchical pitman-yor class-based language models for LVCSR of morphologically rich languages. | Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Relative error bounds for statistical classifiers based on the f-divergence. | Markus Nubaum-Thom, Eugen Beck, Tamer Alkhouli, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Feature-rich sub-lexical language models using a maximum entropy approach for German LVCSR. | M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlter, Hermann Ney |
| 2013 | Interspeech | Training log-linear acoustic models in higher-order polynomial feature space for speech recognition. | Muhammad Ali Tahir, Heyun Huang, Ralf Schlter, Hermann Ney, Louis ten Bosch, Bert Cranen, Lou Boves |
| 2013 | Interspeech | Multilingual hierarchical MRASTA features for ASR. | Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2013 | ITW | Novel tight classification error bounds under mismatch conditions based on f-Divergence. | Ralf Schlter, Markus Nubaum-Thom, Eugen Beck, Tamer Alkhouli, Hermann Ney |
| 2012 | ICASSP | Basis vector orthogonalization for an improved kernel gradient matching pursuit method. | Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura, Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2012 | ICASSP | Investigations on the use of morpheme level features in Language Models for Arabic LVCSR. | Amr El-Desoky Mousa, Ralf Schlter, Hermann Ney |
| 2012 | ICASSP | Joining advantages of word-conditioned and token-passing decoding. | David Nolden, David Rybach, Ralf Schlter, Hermann Ney |
| 2012 | ICASSP | Extended search space pruning in LVCSR. | David Nolden, Ralf Schlter, Hermann Ney |
| 2012 | ICASSP | Silence is golden: Modeling non-speech events in WFST-based dynamic network decoders. | David Rybach, Ralf Schlter, Hermann Ney |
| 2012 | ICASSP | Comparison and combination of different CRBE based MLP features for LVCSR. | Zoltn Tske, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Morpheme Level Feature-based Language Models for German LVCSR. | Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Search Space Pruning Based on Anticipated Path Recombination in LVCSR. | David Nolden, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Posterior-Scaled MPE: Novel Discriminative Training Criteria. | Markus Nubaum-Thom, Zoltn Tske, Georg Heigold, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Investigation of Maximum Entropy Hybrid Language Models for Open Vocabulary German and Polish LVCSR. | M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Hierarchical hybrid language models for open vocabulary continuous speech recognition using WFST. | M. Ali Basha Shaik, David Rybach, Stefan Hahn, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | LSTM Neural Networks for Language Modeling. | Martin Sundermeyer, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Simultaneous Discriminative Training and Mixture Splitting of HMMs for Speech Recognition. | Muhammad Ali Tahir, Markus Nubaum-Thom, Ralf Schlter, Hermann Ney |
| 2012 | Interspeech | Non-stationary signal processing and its application in speech recognition. | Zoltn Tske, Friedhelm R. Drepper, Ralf Schlter |
| 2012 | Interspeech | Context-Dependent MLPs for LVCSR: TANDEM, Hybrid or Both? | Zoltn Tske, Ralf Schlter, Hermann Ney, Martin Sundermeyer |
| 2012 | Interspeech | Accelerated Batch Learning of Convex Log-linear Models for LVCSR. | Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2011 | ASRU | Cross-lingual portability of Chinese and english neural network features for French and German LVCSR. | Christian Plahl, Ralf Schlter, Hermann Ney |
| 2011 | ASRU | Discriminative splitting of Gaussian/log-linear mixture HMMs for speech recognition. | Muhammad Ali Tahir, Ralf Schlter, Hermann Ney |
| 2011 | ASRU | A convergence analysis of log-linear training and its application to speech recognition. | Simon Wiesler, Ralf Schlter, Hermann Ney |
| 2011 | ICASSP | Subspace pursuit method for kernel-log-linear models. | Yotaro Kubo, Simon Wiesler, Ralf Schlter, Hermann Ney, Shinji Watanabe, Atsushi Nakamura, Tetsunori Kobayashi |
| 2011 | ICASSP | Exploiting sparseness of backing-off language models for efficient look-ahead in LVCSR. | David Nolden, Hermann Ney, Ralf Schlter |
| 2011 | ICASSP | A comparative analysis of dynamic network decoding. | David Rybach, Ralf Schlter, Hermann Ney |
| 2011 | ICASSP | Using morpheme and syllable based sub-words for polish LVCSR. | M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlter, Hermann Ney |
| 2011 | ICASSP | The RWTH 2010 Quaero ASR evaluation system for English, French, and German. | Martin Sundermeyer, Markus Nubaum-Thom, Simon Wiesler, Christian Plahl, Amr El-Desoky Mousa, Stefan Hahn, David Nolden, Ralf Schlter, Hermann Ney |
| 2011 | ICASSP | Non-stationary feature extraction for automatic speech recognition. | Zoltn Tske, Pavel Golik, Ralf Schlter, Friedhelm R. Drepper |
| 2011 | ICASSP | Feature selection for log-linear acoustic models. | Simon Wiesler, Alexander Richard, Yotaro Kubo, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | Morpheme Based Factored Language Models for German LVCSR. | Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | Acoustic Look-Ahead for More Efficient Decoding in LVCSR. | David Nolden, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | Compound Word Recombination for German LVCSR. | Markus Nubaum-Thom, Amr El-Desoky Mousa, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | Improved Acoustic Feature Combination for LVCSR by Neural Networks. | Christian Plahl, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | Hybrid Language Models Using Mixed Types of Sub-Lexical Units for Open Vocabulary German LVCSR. | M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | On the Estimation of Discount Parameters for Language Model Smoothing. | Martin Sundermeyer, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | Log-Linear Optimization of Second-Order Polynomial Features with Subsequent Dimension Reduction for Speech Recognition. | Muhammad Ali Tahir, Ralf Schlter, Hermann Ney |
| 2011 | Interspeech | A Study on Speaker Normalized MLP Features in LVCSR. | Zoltn Tske, Christian Plahl, Ralf Schlter |
| 2010 | ICASSP | Discriminative HMMS, log-linear models, and CRFS: What is the difference? | Georg Heigold, Simon Wiesler, Markus Nubaum-Thom, Patrick Lehnen, Ralf Schlter, Hermann Ney |
| 2010 | Interspeech | Discriminative adaptation for log-linear acoustic models. | Jonas Lf, Ralf Schlter, Hermann Ney |
| 2010 | Interspeech | Time conditioned search in automatic speech recognition reconsidered. | David Nolden, Hermann Ney, Ralf Schlter |
| 2010 | Interspeech | The RWTH 2009 quaero ASR evaluation system for English and German. | Markus Nubaum-Thom, Simon Wiesler, Martin Sundermeyer, Christian Plahl, Stefan Hahn, Ralf Schlter, Hermann Ney |
| 2010 | Interspeech | Parallel lexical-tree based LVCSR on multi-core processors. | Naveen Parihar, Ralf Schlter, David Rybach, Eric A. Hansen |
| 2010 | Interspeech | Hierarchical bottle neck features for LVCSR. | Christian Plahl, Ralf Schlter, Hermann Ney |
| 2010 | Interspeech | Revisiting VTLN using linear transformation on conventional MFCC. | Doddipatla Rama Sanand, Ralf Schlter, Hermann Ney |
| 2010 | Interspeech | On the relation of Bayes risk, word error, and word posteriors in ASR. | Ralf Schlter, Markus Nubaum-Thom, Hermann Ney |
| 2010 | Interspeech | A discriminative splitting criterion for phonetic decision trees. | Simon Wiesler, Georg Heigold, Markus Nubaum-Thom, Ralf Schlter, Hermann Ney |
| 2010 | NAACL | A Hybrid Morphologically Decomposed Factored Language Models for Arabic LVCSR. | Amr El-Desoky, Ralf Schlter, Hermann Ney |
| 2009 | ASRU | Generalized likelihood ratio discriminant analysis. | Muhammad Ali Tahir, Georg Heigold, Christian Plahl, Ralf Schlter, Hermann Ney |
| 2009 | ASRU | Investigations on features for log-linear acoustic models in continuous speech recognition. | Simon Wiesler, Markus Nubaum-Thom, Georg Heigold, Ralf Schlter, Hermann Ney |
| 2009 | ICASSP | Modified MPE/MMI in a transducer-based framework. | Georg Heigold, Ralf Schlter, Hermann Ney |
| 2009 | ICASSP | Audio segmentation for speech recognition using segment features. | David Rybach, Christian Gollan, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | Investigating the use of morphological decomposition and diacritization for improving Arabic LVCSR. | Amr El-Desoky, Christian Gollan, David Rybach, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | Investigations on convex optimization using log-linear HMMs for digit string recognition. | Georg Heigold, David Rybach, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | Log-linear model combination with word-dependent scaling factors. | Bjrn Hoffmeister, Ruoying Liang, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | Bayes risk approximations using time overlap with an application to system combination. | Bjrn Hoffmeister, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | Parallel fast likelihood computation for LVCSR using mixture decomposition. | Naveen Parihar, Ralf Schlter, David Rybach, Eric A. Hansen |
| 2009 | Interspeech | Development of the GALE 2008 Mandarin LVCSR system. | Christian Plahl, Bjrn Hoffmeister, Georg Heigold, Jonas Lf, Ralf Schlter, Hermann Ney |
| 2009 | Interspeech | The RWTH aachen university open source speech recognition system. | David Rybach, Christian Gollan, Georg Heigold, Bjrn Hoffmeister, Jonas Lf, Ralf Schlter, Hermann Ney |
| 2008 | ICASSP | A GIS-like training algorithm for log-linear models with hidden variables. | Georg Heigold, Thomas Deselaers, Ralf Schlter, Hermann Ney |
| 2008 | ICML | Modified MMI/MPE: a direct evaluation of the margin in speech recognition. | Georg Heigold, Thomas Deselaers, Ralf Schlter, Hermann Ney |
| 2008 | Interspeech | On the equivalence of Gaussian and log-linear HMMs. | Georg Heigold, Patrick Lehnen, Ralf Schlter, Hermann Ney |
| 2008 | Interspeech | iCNC and iROVER: the limits of improving system combination with classification? | Bjrn Hoffmeister, Ralf Schlter, Hermann Ney |
| 2008 | Interspeech | Recent improvements of the RWTH GALE Mandarin LVCSR system. | Christian Plahl, Bjrn Hoffmeister, Mei-Yuh Hwang, Danju Lu, Georg Heigold, Jonas Lf, Ralf Schlter, Hermann Ney |
| 2008 | Interspeech | Development of the SRI/nightingale Arabic ASR system. | Dimitra Vergyri, Arindam Mandal, Wen Wang, Andreas Stolcke, Jing Zheng, Martin Graciarena, David Rybach, Christian Gollan, Ralf Schlter, Katrin Kirchhoff, Arlo Faria, Nelson Morgan |
| 2007 | ASRU | Development of the 2007 RWTH Mandarin LVCSR system. | Bjrn Hoffmeister, Christian Plahl, Peter Fritz, Georg Heigold, Jonas Lf, Ralf Schlter, Hermann Ney |
| 2007 | ASRU | Advances in Arabic broadcast news transcription at RWTH. | David Rybach, Stefan Hahn, Christian Gollan, Ralf Schlter, Hermann Ney |
| 2007 | ICASSP | Cross-Site and Intra-Site ASR System Combination: Comparisons on Lattice and 1-Best Methods. | Bjrn Hoffmeister, Dustin Hillard, Stefan Hahn, Ralf Schlter, Mari Ostendorf, Hermann Ney |
| 2007 | ICASSP | Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition. | Ralf Schlter, Ilja Bezrukov, Hermann Wagner, Hermann Ney |
| 2007 | Interspeech | An improved method for unsupervised training of LVCSR systems. | Christian Gollan, Stefan Hahn, Ralf Schlter, Hermann Ney |
| 2007 | Interspeech | On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields. | Georg Heigold, Ralf Schlter, Hermann Ney |
| 2007 | Interspeech | The RWTH 2007 TC-STAR evaluation system for european English and Spanish. | Jonas Lf, Christian Gollan, Stefan Hahn, Georg Heigold, Bjrn Hoffmeister, Christian Plahl, David Rybach, Ralf Schlter, Hermann Ney |
| 2007 | Interspeech | Efficient estimation of speaker-specific projecting feature transforms. | Jonas Lf, Ralf Schlter, Hermann Ney |
| 2007 | Interspeech | Hierarchical neural networks feature extraction for LVCSR system. | Fabio Valente, Jithendra Vepa, Christian Plahl, Christian Gollan, Hynek Hermansky, Ralf Schlter |
| 2007 | NAACL | iROVER: Improving System Combination with Classification. | Dustin Hillard, Bjrn Hoffmeister, Mari Ostendorf, Ralf Schlter, Hermann Ney |
| 2006 | Interspeech | Frame based system combination and a comparison with weighted ROVER and CNC. | Bjrn Hoffmeister, Tobias Klein, Ralf Schlter, Hermann Ney |
| 2006 | Interspeech | The 2006 RWTH parliamentary speeches transcription system. | Jonas Lf, Maximilian Bisani, Christian Gollan, Georg Heigold, Bjrn Hoffmeister, Christian Plahl, Ralf Schlter, Hermann Ney |
| 2006 | Interspeech | Feature combination using linear discriminant analysis and its pitfalls. | Ralf Schlter, Andrs Zolnay, Hermann Ney |
| 2005 | ICASSP | Cross Domain Automatic Transcription on the TC-STAR EPPS Corpus. | Christian Gollan, Maximilian Bisani, Stephan Kanthak, Ralf Schlter, Hermann Ney |
| 2005 | ICASSP | Acoustic Feature Combination for Robust Speech Recognition. | Andrs Zolnay, Ralf Schlter, Hermann Ney |
| 2005 | Interspeech | Articulatory motivated acoustic features for speech recognition. | Daniil Kocharov, Andrs Zolnay, Ralf Schlter, Hermann Ney |
| 2005 | Interspeech | Investigations on error minimizing training criteria for discriminative training in automatic speech recognition. | Wolfgang Macherey, Lars Haferkamp, Ralf Schlter, Hermann Ney |
| 2005 | Interspeech | Bayes risk minimization using metric loss functions. | Ralf Schlter, T. Scharrenbach, Volker Steinbiss, Hermann Ney |
| 2004 | Interspeech | Discriminative training with tied covariance matrices. | Wolfgang Macherey, Ralf Schlter, Hermann Ney |
| 2003 | Interspeech | Extraction methods of voicing feature for robust speech recognition. | Andrs Zolnay, Ralf Schlter, Hermann Ney |
| 2002 | Interspeech | Robust speech recognition using a voiced-unvoiced feature. | Andrs Zolnay, Ralf Schlter, Hermann Ney |
| 2001 | ICASSP | Computing Mel-frequency cepstral coefficients on the power spectrum. | Sirko Molau, Michael Pitz, Ralf Schlter, Hermann Ney |
| 2001 | ICASSP | Using phase spectrum information for improved speech recognition performance. | Ralf Schlter, Hermann Ney |
| 2001 | ICASSP | Explicit word error minimization using word hypothesis posterior probabilities. | Frank Wessel, Ralf Schlter, Hermann Ney |
| 2001 | Interspeech | Vocal tract normalization equals linear transformation in cepstral space. | Michael Pitz, Sirko Molau, Ralf Schlter, Hermann Ney |
| 2000 | ICASSP | Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech. | Achim Sixtus, Sirko Molau, Stephan Kanthak, Ralf Schlter, Hermann Ney |
| 2000 | ICASSP | Using posterior word probabilities for improved speech recognition. | Frank Wessel, Ralf Schlter, Hermann Ney |
| 2000 | Interspeech | Speech recognition using context conditional word posterior probabilities. | Ralf Schlter, Frank Wessel, Hermann Ney |
| 1999 | Interspeech | A combined maximum mutual information and maximum likelihood approach for mixture density splitting. | Ralf Schlter, Wolfgang Macherey, Boris Mller, Hermann Ney |
| 1998 | ICASSP | Comparison of discriminative training criteria. | Ralf Schlter, Wolfgang Macherey |
| 1998 | ICASSP | Using word probabilities as confidence measures. | Frank Wessel, Klaus Macherey, Ralf Schlter |
| 1997 | Interspeech | Comparison of optimization methods for discriminative training criteria. | Ralf Schlter, Wolfgang Macherey, Stephan Kanthak, Hermann Ney, Lutz Welling |