![](https://dblp.uni-trier.de/img/logo.ua.320x120.png)
![](https://dblp.uni-trier.de/img/dropdown.dark.16x16.png)
![](https://dblp.uni-trier.de/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp.uni-trier.de/img/search.dark.16x16.png)
![search dblp](https://dblp.uni-trier.de/img/search.dark.16x16.png)
default search action
Ralf Schlüter
Person information
- affiliation: RWTH Aachen University, Germany
Refine list
![note](https://dblp.uni-trier.de/img/note-mark.dark.12x12.png)
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j17]Rohit Prabhavalkar
, Takaaki Hori
, Tara N. Sainath
, Ralf Schlüter
, Shinji Watanabe
:
End-to-End Speech Recognition: A Survey. IEEE ACM Trans. Audio Speech Lang. Process. 32: 325-351 (2024) - [c226]Mohammad Zeineldeen, Albert Zeyer, Ralf Schlüter, Hermann Ney:
Chunked Attention-Based Encoder-Decoder Model for Streaming Speech Recognition. ICASSP 2024: 11331-11335 - [c225]Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney:
On the Relation Between Internal Language Model and Sequence Discriminative Training for Neural Transducers. ICASSP 2024: 12627-12631 - [i64]Tina Raissi, Christoph Lüscher, Simon Berger, Ralf Schlüter, Hermann Ney:
Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality. CoRR abs/2407.11641 (2024) - [i63]Nick Rossenbach, Benedikt Hilmes, Ralf Schlüter:
On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures. CoRR abs/2407.17997 (2024) - [i62]Jingjing Xu, Wei Zhou, Zijian Yang, Eugen Beck, Ralf Schlüter:
Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition. CoRR abs/2407.18930 (2024) - [i61]Nick Rossenbach, Ralf Schlüter, Sakriani Sakti:
On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition. CoRR abs/2407.21476 (2024) - 2023
- [c224]Daniel Mann, Tina Raissi, Wilfried Michel, Ralf Schlüter, Hermann Ney:
End-To-End Training of a Neural HMM with Label and Transition Probabilities. ASRU 2023: 1-8 - [c223]Nick Rossenbach, Benedikt Hilmes, Ralf Schlüter:
On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition. ASRU 2023: 1-8 - [c222]Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney:
Investigating The Effect of Language Models in Sequence Discriminative Training For Neural Transducers. ASRU 2023: 1-8 - [c221]Peter Vieting, Christoph Lüscher, Julian Dierkes, Ralf Schlüter, Hermann Ney:
Efficient Utilization of Large Pre-Trained Models for Low Resource ASR. ICASSP Workshops 2023: 1-5 - [c220]Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney:
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers. ICASSP 2023: 1-5 - [c219]Wei Zhou, Haotian Wu, Jingjing Xu, Mohammad Zeineldeen, Christoph Lüscher, Ralf Schlüter, Hermann Ney:
Enhancing and Adversarial: Improve ASR with Speaker Labels. ICASSP 2023: 1-5 - [c218]Simon Berger, Peter Vieting, Christoph Böddeker, Ralf Schlüter, Reinhold Haeb-Umbach:
Mixture Encoder for Joint Speech Separation and Recognition. INTERSPEECH 2023: 3527-3531 - [c217]Wei Zhou, Eugen Beck, Simon Berger, Ralf Schlüter, Hermann Ney:
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition. INTERSPEECH 2023: 4094-4098 - [c216]Tina Raissi, Christoph Lüscher, Moritz Gunz, Ralf Schlüter, Hermann Ney:
Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think. INTERSPEECH 2023: 4938-4942 - [i60]Christoph Lüscher, Jingjing Xu, Mohammad Zeineldeen, Ralf Schlüter, Hermann Ney:
Improving And Analyzing Neural Speaker Embeddings for ASR. CoRR abs/2301.04571 (2023) - [i59]Rohit Prabhavalkar, Takaaki Hori, Tara N. Sainath, Ralf Schlüter, Shinji Watanabe:
End-to-End Speech Recognition: A Survey. CoRR abs/2303.03329 (2023) - [i58]Wei Zhou, Eugen Beck, Simon Berger, Ralf Schlüter, Hermann Ney:
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition. CoRR abs/2305.17782 (2023) - [i57]Tina Raissi, Christoph Lüscher, Moritz Gunz, Ralf Schlüter, Hermann Ney:
Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think. CoRR abs/2306.09517 (2023) - [i56]Simon Berger, Peter Vieting, Christoph Böddeker, Ralf Schlüter, Reinhold Haeb-Umbach:
Mixture Encoder for Joint Speech Separation and Recognition. CoRR abs/2306.12173 (2023) - [i55]Peter Vieting, Ralf Schlüter, Hermann Ney:
Comparative Analysis of the wav2vec 2.0 Feature Extractor. CoRR abs/2308.04286 (2023) - [i54]Mohammad Zeineldeen, Albert Zeyer, Ralf Schlüter, Hermann Ney:
Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition. CoRR abs/2309.08436 (2023) - [i53]Peter Vieting, Simon Berger, Thilo von Neumann, Christoph Böddeker, Ralf Schlüter, Reinhold Haeb-Umbach:
Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition. CoRR abs/2309.08454 (2023) - [i52]Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney:
On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers. CoRR abs/2309.14130 (2023) - [i51]Daniel Mann, Tina Raissi, Wilfried Michel, Ralf Schlüter, Hermann Ney:
End-to-End Training of a Neural HMM with Label and Transition Probabilities. CoRR abs/2310.02724 (2023) - [i50]Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney:
Investigating the Effect of Language Models in Sequence Discriminative Training for Neural Transducers. CoRR abs/2310.07345 (2023) - [i49]Nick Rossenbach, Benedikt Hilmes, Ralf Schlüter:
On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition. CoRR abs/2310.08132 (2023) - 2022
- [c215]Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter
, Hermann Ney:
Conformer-Based Hybrid ASR System For Switchboard Dataset. ICASSP 2022: 7437-7441 - [c214]Tina Raissi, Eugen Beck, Ralf Schlüter
, Hermann Ney:
Improving Factored Hybrid HMM Acoustic Modeling without State Tying. ICASSP 2022: 7442-7446 - [c213]Nils-Philipp Wynands, Wilfried Michel, Jan Rosendahl, Ralf Schlüter
, Hermann Ney:
Efficient Sequence Training of Attention Models Using Approximative Recombination. ICASSP 2022: 8002-8006 - [c212]Wei Zhou, Zuoyun Zheng, Ralf Schlüter
, Hermann Ney:
On Language Model Integration for RNN Transducer Based Speech Recognition. ICASSP 2022: 8407-8411 - [c211]Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Ralf Schlüter, Hermann Ney:
Improving the Training Recipe for a Robust Conformer-based Hybrid Model. INTERSPEECH 2022: 1036-1040 - [c210]Wei Zhou, Wilfried Michel, Ralf Schlüter, Hermann Ney:
Efficient Training of Neural Transducer for Speech Recognition. INTERSPEECH 2022: 2058-2062 - [c209]Zijian Yang, Yingbo Gao, Alexander Gerstenberger, Jintao Jiang, Ralf Schlüter, Hermann Ney:
Self-Normalized Importance Sampling for Neural Language Modeling. INTERSPEECH 2022: 3909-3913 - [c208]Felix Meyer, Wilfried Michel, Mohammad Zeineldeen, Ralf Schlüter, Hermann Ney:
Automatic Learning of Subword Dependent Model Scales. INTERSPEECH 2022: 4133-4136 - [c207]Michael Gansen, Jie Lou, Florian Freye
, Tobias Gemmeke
, Farhad Merchant, Albert Zeyer, Mohammad Zeineldeen, Ralf Schlüter
, Xin Fan:
Discrete Steps towards Approximate Computing. ISQED 2022: 1-6 - [c206]Albert Zeyer, Robin Schmitt, Wei Zhou, Ralf Schlüter, Hermann Ney:
Monotonic Segmental Attention for Automatic Speech Recognition. SLT 2022: 229-236 - [c205]Tina Raissi, Wei Zhou, Simon Berger, Ralf Schlüter, Hermann Ney:
HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch. SLT 2022: 287-294 - [i48]Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney:
Improving Factored Hybrid HMM Acoustic Modeling without State Tying. CoRR abs/2201.09692 (2022) - [i47]Wei Zhou, Wilfried Michel, Ralf Schlüter
, Hermann Ney:
Efficient Training of Neural Transducer for Speech Recognition. CoRR abs/2204.10586 (2022) - [i46]Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Ralf Schlüter
, Hermann Ney:
Improving the Training Recipe for a Robust Conformer-based Hybrid Model. CoRR abs/2206.12955 (2022) - [i45]Tina Raissi, Wei Zhou, Simon Berger, Ralf Schlüter, Hermann Ney:
HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch. CoRR abs/2210.09951 (2022) - [i44]Christoph Lüscher, Mohammad Zeineldeen, Zijian Yang, Peter Vieting, Khai Le-Duc, Weiyue Wang, Ralf Schlüter, Hermann Ney:
Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech. CoRR abs/2210.13397 (2022) - [i43]Albert Zeyer, Robin Schmitt, Wei Zhou, Ralf Schlüter, Hermann Ney:
Monotonic segmental attention for automatic speech recognition. CoRR abs/2210.14742 (2022) - [i42]Peter Vieting, Christoph Lüscher, Julian Dierkes, Ralf Schlüter, Hermann Ney:
Efficient Use of Large Pre-Trained Models for Low Resource ASR. CoRR abs/2210.15445 (2022) - [i41]Wei Zhou, Haotian Wu, Jingjing Xu, Mohammad Zeineldeen, Christoph Lüscher, Ralf Schlüter, Hermann Ney:
Enhancing and Adversarial: Improve ASR with Speaker Labels. CoRR abs/2211.06369 (2022) - [i40]Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney:
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers. CoRR abs/2212.04325 (2022) - 2021
- [c204]Peter Vieting, Christoph Lüscher, Wilfried Michel, Ralf Schlüter
, Hermann Ney:
On Architectures and Training for Raw Waveform Feature Extraction in ASR. ASRU 2021: 267-274 - [c203]Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes, Ralf Schlüter
, Hermann Ney:
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures. ASRU 2021: 788-795 - [c202]Wei Zhou, Simon Berger, Ralf Schlüter
, Hermann Ney:
Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition. ICASSP 2021: 5644-5648 - [c201]Yingbo Gao, David Thulke, Alexander Gerstenberger, Khoa Viet Tran, Ralf Schlüter
, Hermann Ney:
On Sampling-Based Training Criteria for Neural Language Modeling. Interspeech 2021: 1877-1881 - [c200]Albert Zeyer, André Merboldt, Wilfried Michel, Ralf Schlüter
, Hermann Ney:
Librispeech Transducer Model with Internal Language Model Prior Correction. Interspeech 2021: 2052-2056 - [c199]Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR Models. Interspeech 2021: 2856-2860 - [c198]Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter
, Hermann Ney:
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition. Interspeech 2021: 2886-2890 - [c197]Wei Zhou, Albert Zeyer, André Merboldt, Ralf Schlüter
, Hermann Ney:
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept. Interspeech 2021: 2891-2895 - [c196]Yu Qiao, Wei Zhou, Elma Kerz, Ralf Schlüter
:
The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech. Interspeech 2021: 4453-4457 - [c195]Parnia Bahar, Tobias Bieschke, Ralf Schlüter
, Hermann Ney:
Tight Integrated End-to-End Training for Cascaded Speech Translation. SLT 2021: 950-957 - [i39]Albert Zeyer, Ralf Schlüter, Hermann Ney:
A study of latent monotonic attention variants. CoRR abs/2103.16710 (2021) - [i38]Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney:
Towards Consistent Hybrid HMM Acoustic Modeling. CoRR abs/2104.02387 (2021) - [i37]Albert Zeyer, André Merboldt, Wilfried Michel, Ralf Schlüter, Hermann Ney:
Librispeech Transducer Model with Internal Language Model Prior Correction. CoRR abs/2104.03006 (2021) - [i36]Peter Vieting, Christoph Lüscher, Wilfried Michel, Ralf Schlüter, Hermann Ney:
Feature Replacement and Combination for Hybrid ASR Systems. CoRR abs/2104.04298 (2021) - [i35]Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes, Ralf Schlüter, Hermann Ney:
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures. CoRR abs/2104.05379 (2021) - [i34]Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney:
Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models. CoRR abs/2104.05544 (2021) - [i33]Wei Zhou, Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney:
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept. CoRR abs/2104.06104 (2021) - [i32]Yu Qiao, Zhou Wei, Elma Kerz, Ralf Schlüter:
The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech. CoRR abs/2104.08529 (2021) - [i31]Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter, Hermann Ney:
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition. CoRR abs/2104.09106 (2021) - [i30]Yingbo Gao, David Thulke, Alexander Gerstenberger, Khoa Viet Tran, Ralf Schlüter, Hermann Ney:
On Sampling-Based Training Criteria for Neural Language Modeling. CoRR abs/2104.10507 (2021) - [i29]Albert Zeyer, Ralf Schlüter, Hermann Ney:
Why does CTC result in peaky behavior? CoRR abs/2105.14849 (2021) - [i28]Wei Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney:
On Language Model Integration for RNN Transducer based Speech Recognition. CoRR abs/2110.06841 (2021) - [i27]Nils-Philipp Wynands, Wilfried Michel, Jan Rosendahl, Ralf Schlüter, Hermann Ney:
Efficient Sequence Training of Attention Models using Approximative Recombination. CoRR abs/2110.09245 (2021) - [i26]Felix Meyer, Wilfried Michel, Mohammad Zeineldeen, Ralf Schlüter, Hermann Ney:
Automatic Learning of Subword Dependent Model Scales. CoRR abs/2110.09324 (2021) - [i25]Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney:
Conformer-based Hybrid ASR System for Switchboard Dataset. CoRR abs/2111.03442 (2021) - [i24]Zijian Yang, Yingbo Gao, Alexander Gerstenberger, Jintao Jiang, Ralf Schlüter, Hermann Ney:
Self-Normalized Importance Sampling for Neural Language Modeling. CoRR abs/2111.06310 (2021) - [i23]Yu Qiao, Sourabh Zanwar, Rishab Bhattacharyya, Daniel Wiechmann, Wei Zhou, Elma Kerz, Ralf Schlüter:
Prediction of Listener Perception of Argumentative Speech in a Crowdsourced Dataset Using (Psycho-)Linguistic and Fluency Features. CoRR abs/2111.07130 (2021) - 2020
- [c194]Kazuki Irie, Alexander Gerstenberger, Ralf Schlüter
, Hermann Ney:
How Much Self-Attention Do We Need? Trading Attention for Feed-Forward Layers. ICASSP 2020: 6154-6158 - [c193]Wilfried Michel, Ralf Schlüter
, Hermann Ney:
Frame-Level MMI as A Sequence Discriminative Training Criterion for LVCSR. ICASSP 2020: 6904-6908 - [c192]Nick Rossenbach, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems. ICASSP 2020: 7069-7073 - [c191]Vitalii Bozheniuk, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
A Comprehensive Study of Residual CNNS for Acoustic Modeling in ASR. ICASSP 2020: 7674-7678 - [c190]Mohammad Zeineldeen, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR. ICASSP 2020: 7679-7683 - [c189]Wei Zhou, Ralf Schlüter
, Hermann Ney:
Full-Sum Decoding for Hybrid Hmm Based Speech Recognition Using LSTM Language Model. ICASSP 2020: 7834-7838 - [c188]Wei Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schlüter
, Hermann Ney:
The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment. ICASSP 2020: 7839-7843 - [c187]Parnia Bahar, Nikita Makarov, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition. ICASSP 2020: 7854-7858 - [c186]Wei Zhou, Ralf Schlüter
, Hermann Ney:
Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition Without Length Bias. INTERSPEECH 2020: 1768-1772 - [c185]Eugen Beck, Ralf Schlüter
, Hermann Ney:
LVCSR with Transformer Language Models. INTERSPEECH 2020: 1798-1802 - [c184]Albert Zeyer, André Merboldt, Ralf Schlüter
, Hermann Ney:
A New Training Pipeline for an Improved Neural Transducer. INTERSPEECH 2020: 2812-2816 - [c183]Wilfried Michel, Ralf Schlüter
, Hermann Ney:
Early Stage LM Integration Using Local and Global Log-Linear Combination. INTERSPEECH 2020: 3605-3609 - [c182]Jingjing Huo, Yingbo Gao, Weiyue Wang
, Ralf Schlüter
, Hermann Ney:
Investigation of Large-Margin Softmax in Neural Language Modeling. INTERSPEECH 2020: 3645-3649 - [c181]Tina Raissi, Eugen Beck, Ralf Schlüter
, Hermann Ney:
Context-Dependent Acoustic Modeling Without Explicit Phone Clustering. INTERSPEECH 2020: 4377-4381 - [i22]Wei Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schlüter, Hermann Ney:
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment. CoRR abs/2004.00960 (2020) - [i21]Wei Zhou, Ralf Schlüter, Hermann Ney:
Full-Sum Decoding for Hybrid HMM based Speech Recognition using LSTM Language Model. CoRR abs/2004.00967 (2020) - [i20]Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney:
Context-Dependent Acoustic Modeling without Explicit Phone Clustering. CoRR abs/2005.07578 (2020) - [i19]Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney:
A New Training Pipeline for an Improved Neural Transducer. CoRR abs/2005.09319 (2020) - [i18]Albert Zeyer, Wei Zhou, Thomas Ng, Ralf Schlüter, Hermann Ney:
Investigations on Phoneme-Based End-To-End Speech Recognition. CoRR abs/2005.09336 (2020) - [i17]Wilfried Michel, Ralf Schlüter, Hermann Ney:
Early Stage LM Integration Using Local and Global Log-Linear Combination. CoRR abs/2005.10049 (2020) - [i16]Jingjing Huo, Yingbo Gao, Weiyue Wang, Ralf Schlüter, Hermann Ney:
Investigation of Large-Margin Softmax in Neural Language Modeling. CoRR abs/2005.10089 (2020) - [i15]Wei Zhou, Simon Berger, Ralf Schlüter, Hermann Ney:
Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition. CoRR abs/2010.16368 (2020) - [i14]Parnia Bahar, Tobias Bieschke, Ralf Schlüter, Hermann Ney:
Tight Integrated End-to-End Training for Cascaded Speech Translation. CoRR abs/2011.12167 (2020)
2010 – 2019
- 2019
- [j16]Ralf Schlüter
, Eugen Beck
, Hermann Ney:
Upper and Lower Tight Error Bounds for Feature Omission with an Extension to Context Reduction. IEEE Trans. Pattern Anal. Mach. Intell. 41(2): 502-514 (2019) - [j15]Muhammad Ali Tahir, Heyun Huang, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Training of reduced-rank linear transformations for multi-layer polynomial acoustic features for speech recognition. Speech Commun. 110: 56-63 (2019) - [c180]Albert Zeyer
, Parnia Bahar, Kazuki Irie, Ralf Schlüter
, Hermann Ney:
A Comparison of Transformer and LSTM Encoder Decoder Models for ASR. ASRU 2019: 8-15 - [c179]Kazuki Irie, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Training Language Models for Long-Span Cross-Sentence Evaluation. ASRU 2019: 419-426 - [c178]Parnia Bahar, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
On Using 2D Sequence-to-sequence Models for Speech Recognition. ICASSP 2019: 5671-5675 - [c177]Tobias Menne, Ralf Schlüter
, Hermann Ney:
Investigation into Joint Optimization of Single Channel Speech Enhancement and Acoustic Modeling for Robust ASR. ICASSP 2019: 6660-6664 - [c176]Christoph Lüscher, Eugen Beck, Kazuki Irie, Markus Kitza, Wilfried Michel, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention. INTERSPEECH 2019: 231-235 - [c175]Markus Kitza, Pavel Golik, Ralf Schlüter
, Hermann Ney:
Cumulative Adaptation for BLSTM Acoustic Models. INTERSPEECH 2019: 754-758 - [c174]André Merboldt, Albert Zeyer, Ralf Schlüter
, Hermann Ney:
An Analysis of Local Monotonic Attention Variants. INTERSPEECH 2019: 1398-1402 - [c173]Wilfried Michel, Ralf Schlüter
, Hermann Ney:
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR. INTERSPEECH 2019: 1601-1605 - [c172]Tobias Menne, Ilya Sklyar, Ralf Schlüter
, Hermann Ney:
Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech. INTERSPEECH 2019: 2638-2642 - [c171]Kazuki Irie, Albert Zeyer
, Ralf Schlüter
, Hermann Ney:
Language Modeling with Deep Transformers. INTERSPEECH 2019: 3905-3909 - [c170]Anna Piunova, Eugen Beck, Ralf Schlüter
, Hermann Ney:
Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings. INTERSPEECH 2019: 4205-4209 - [c169]Ralf Schlüter:
Survey Talk: Modeling in Automatic Speech Recognition: Beyond Hidden Markov Models. INTERSPEECH 2019 - [c168]Parnia Bahar, Albert Zeyer, Ralf Schlüter, Hermann Ney:
On Using SpecAugment for End-to-End Speech Translation. IWSLT 2019 - [i13]Christoph Lüscher, Eugen Beck, Kazuki Irie, Markus Kitza, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney:
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation. CoRR abs/1905.03072 (2019) - [i12]Tobias Menne, Ilya Sklyar, Ralf Schlüter, Hermann Ney:
Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech. CoRR abs/1905.03500 (2019) - [i11]Kazuki Irie, Albert Zeyer, Ralf Schlüter, Hermann Ney:
Language Modeling with Deep Transformers. CoRR abs/1905.04226 (2019) - [i10]Markus Kitza, Pavel Golik, Ralf Schlüter, Hermann Ney:
Cumulative Adaptation for BLSTM Acoustic Models. CoRR abs/1906.06207 (2019) - [i9]Eugen Beck, Wei Zhou, Ralf Schlüter, Hermann Ney:
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring. CoRR abs/1907.01030 (2019) - [i8]Wilfried Michel, Ralf Schlüter, Hermann Ney:
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR. CoRR abs/1907.01409 (2019) - [i7]Parnia Bahar, Albert Zeyer, Ralf Schlüter, Hermann Ney:
On Using SpecAugment for End-to-End Speech Translation. CoRR abs/1911.08876 (2019) - [i6]Parnia Bahar, Albert Zeyer, Ralf Schlüter, Hermann Ney:
On using 2D sequence-to-sequence models for speech recognition. CoRR abs/1911.08888 (2019) - [i5]Nick Rossenbach, Albert Zeyer, Ralf Schlüter, Hermann Ney:
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems. CoRR abs/1912.09257 (2019) - 2018
- [c167]Eugen Beck, Albert Zeyer, Patrick Doetsch, André Merboldt, Ralf Schlüter, Hermann Ney:
Sequence Modeling and Alignment for LVCSR-Systems. ITG Symposium on Speech Communication 2018: 1-5 - [c166]Zoltán Tüske, Ralf Schlüter
, Hermann Ney:
Acoustic Modeling of Speech Waveform Based on Multi-Resolution, Neural Network Signal Processing. ICASSP 2018: 4859-4863 - [c165]Kazuki Irie, Zhihong Lei, Ralf Schlüter
, Hermann Ney:
Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward Language Models. ICASSP 2018: 6104-6108 - [c164]Albert Zeyer
, Kazuki Irie, Ralf Schlüter
, Hermann Ney:
Improved Training of End-to-end Attention Models for Speech Recognition. INTERSPEECH 2018: 7-11 - [c163]Kazuki Irie, Zhihong Lei, Liuhui Deng, Ralf Schlüter
, Hermann Ney:
Investigation on Estimation of Sentence Probability by Combining Forward, Backward and Bi-directional LSTM-RNNs. INTERSPEECH 2018: 392-395 - [c162]Eugen Beck, Mirko Hannemann, Patrick Dötsch, Ralf Schlüter
, Hermann Ney:
Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition. INTERSPEECH 2018: 766-770 - [c161]Markus Kitza, Ralf Schlüter
, Hermann Ney:
Comparison of BLSTM-Layer-Specific Affine Transformations for Speaker Adaptation. INTERSPEECH 2018: 877-881 - [c160]Zoltán Tüske, Ralf Schlüter
, Hermann Ney:
Investigation on LSTM Recurrent N-gram Language Models for Speech Recognition. INTERSPEECH 2018: 3358-3362 - [c159]Tobias Menne, Ralf Schlüter
, Hermann Ney:
Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition. SLT 2018: 535-541 - [i4]Albert Zeyer, Kazuki Irie, Ralf Schlüter, Hermann Ney:
Improved training of end-to-end attention models for speech recognition. CoRR abs/1805.03294 (2018) - [i3]Tobias Menne, Ralf Schlüter, Hermann Ney:
Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition. CoRR abs/1806.07407 (2018) - 2017
- [j14]Patrick Doetsch
, Mirko Hannemann, Ralf Schlüter
, Hermann Ney:
Inverted Alignments for End-to-End Automatic Speech Recognition. IEEE J. Sel. Top. Signal Process. 11(8): 1265-1273 (2017) - [c158]Markus Nußbaum-Thom, Ralf Schlüter
, Vaibhava Goel
, Hermann Ney:
Noisy objective functions based on the f-divergence. ICASSP 2017: 2327-2331 - [c157]Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlüter
, Hermann Ney:
A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition. ICASSP 2017: 2462-2466 - [c156]Albert Zeyer, Ilia Kulikov, Ralf Schlüter
, Hermann Ney:
Faster sequence training. ICASSP 2017: 5285-5289 - [c155]Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilia Kulikov, Ralf Schlüter
, Hermann Ney:
Returnn: The RWTH extensible training framework for universal recurrent neural networks. ICASSP 2017: 5345-5349 - [c154]Kazuki Irie, Pavel Golik, Ralf Schlüter
, Hermann Ney:
Investigations on byte-level convolutional neural networks for language modeling in low resource speech recognition. ICASSP 2017: 5740-5744 - [c153]Albert Zeyer, Eugen Beck, Ralf Schlüter
, Hermann Ney:
CTC in the Context of Generalized Full-Sum HMM Training. INTERSPEECH 2017: 944-948 - [c152]Zoltán Tüske, Wilfried Michel, Ralf Schlüter
, Hermann Ney:
Parallel Neural Network Features for Improved Tandem Acoustic Modeling. INTERSPEECH 2017: 1651-1655 - [c151]Pavel Golik, Zoltán Tüske, Kazuki Irie, Eugen Beck, Ralf Schlüter
, Hermann Ney:
The 2016 RWTH Keyword Search System for Low-Resource Languages. SPECOM 2017: 719-730 - 2016
- [c150]Markus Kitza, Albert Zeyer, Ralf Schlüter, Jahn Heymann, Reinhold Haeb-Umbach:
Robust Online Multi-Channel Speech Recognition. ITG Symposium on Speech Communication 2016: 1-5 - [c149]Zoltán Tüske, Kazuki Irie, Ralf Schlüter
, Hermann Ney:
Investigation on log-linear interpolation of multi-domain neural network language model. ICASSP 2016: 6005-6009 - [c148]Albert Zeyer, Ralf Schlüter
, Hermann Ney:
Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models. INTERSPEECH 2016: 3424-3428 - [c147]Kazuki Irie, Zoltán Tüske, Tamer Alkhouli, Ralf Schlüter
, Hermann Ney:
LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition. INTERSPEECH 2016: 3519-3523 - [c146]Wilfried Michel, Zoltán Tüske, M. Ali Basha Shaik, Ralf Schlüter, Hermann Ney:
The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task. IWSLT 2016 - [c145]Ralf Schlüter
, Patrick Doetsch, Pavel Golik, Markus Kitza, Tobias Menne, Kazuki Irie, Zoltán Tüske, Albert Zeyer:
Automatic Speech Recognition Based on Neural Networks. SPECOM 2016: 3-17 - [i2]Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlüter, Hermann Ney:
A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition. CoRR abs/1606.06871 (2016) - [i1]Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilya Kulikov, Ralf Schlüter, Hermann Ney:
RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks. CoRR abs/1608.00895 (2016) - 2015
- [j13]Martin Sundermeyer, Hermann Ney, Ralf Schlüter
:
From Feedforward to Recurrent LSTM Neural Networks for Language Modeling. IEEE ACM Trans. Audio Speech Lang. Process. 23(3): 517-529 (2015) - [c144]Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, Abhinav Sethy, Kartik Audhkhasi, Xiaodong Cui, Ellen Kislal, Lidia Mangu, Markus Nußbaum-Thom, Michael Picheny, Zoltán Tüske, Pavel Golik, Ralf Schlüter
, Hermann Ney, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang, Philip C. Woodland:
Multilingual representations for low resource speech recognition and keyword search. ASRU 2015: 259-266 - [c143]Zoltán Tüske, Pavel Golik, Ralf Schlüter
, Hermann Ney:
Speaker adaptive joint training of Gaussian mixture models and bottleneck features. ASRU 2015: 596-603 - [c142]Paul Voigtlaender, Patrick Doetsch, Simon Wiesler, Ralf Schlüter
, Hermann Ney:
Sequence-discriminative training of recurrent neural networks. ICASSP 2015: 2100-2104 - [c141]Zoltán Tüske, Muhammad Ali Tahir, Ralf Schlüter
, Hermann Ney:
Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables. ICASSP 2015: 4285-4289 - [c140]Simon Wiesler, Pavel Golik, Ralf Schlüter
, Hermann Ney:
Investigations on sequence training of neural networks. ICASSP 2015: 4565-4569 - [c139]Muhammad Ali Tahir, Simon Wiesler, Ralf Schlüter
, Hermann Ney:
Investigation of mixture splitting concept for training linear bottlenecks of deep neural network acoustic models. ICASSP 2015: 4614-4618 - [c138]M. Ali Basha Shaik, Amr El-Desoky Mousa, Stefan Hahn, Ralf Schlüter
, Hermann Ney:
Improved strategies for a zero oov rate LVCSR system. ICASSP 2015: 5048-5052 - [c137]Jahn Heymann, Reinhold Haeb-Umbach
, Pavel Golik, Ralf Schlüter
:
Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions. ICASSP 2015: 5053-5057 - [c136]Pavel Golik, Zoltán Tüske, Ralf Schlüter, Hermann Ney:
Convolutional neural networks for acoustic modeling of raw time signal in LVCSR. INTERSPEECH 2015: 26-30 - [c135]Pavel Golik, Zoltán Tüske, Ralf Schlüter, Hermann Ney:
Multilingual features based keyword search for very low-resource languages. INTERSPEECH 2015: 1260-1264 - [c134]Eugen Beck, Ralf Schlüter, Hermann Ney:
Error bounds for context reduction and feature omission. INTERSPEECH 2015: 1280-1284 - [c133]Kazuki Irie, Ralf Schlüter, Hermann Ney:
Bag-of-words input for long history representation in neural network-based language models for speech recognition. INTERSPEECH 2015: 2371-2375 - [c132]M. Ali Basha Shaik, Zoltán Tüske, Muhammad Ali Tahir, Markus Nußbaum-Thom, Ralf Schlüter, Hermann Ney:
Improvements in RWTH LVCSR evaluation systems for Polish, Portuguese, English, urdu, and Arabic. INTERSPEECH 2015: 3154-3158 - 2014
- [c131]Simon Wiesler, Alexander Richard, Ralf Schlüter
, Hermann Ney:
Mean-normalized stochastic gradient for large-scale deep learning. ICASSP 2014: 180-184 - [c130]Simon Wiesler, Alexander Richard, Pavel Golik, Ralf Schlüter
, Hermann Ney:
RASR/NN: The RWTH neural network toolkit for speech recognition. ICASSP 2014: 3281-3285 - [c129]Simon Wiesler, Kazuki Irie, Zoltán Tüske, Ralf Schlüter
, Hermann Ney:
The RWTH English lecture recognition system. ICASSP 2014: 3286-3290 - [c128]Markus Nußbaum-Thom, Xiaodong Cui, Ralf Schlüter
, Vaibhava Goel
, Hermann Ney:
A family of discriminative training criteria based on the F-divergence for deep neural networks. ICASSP 2014: 5612-5616 - [c127]Zoltán Tüske, David Nolden, Ralf Schlüter
, Hermann Ney:
Multilingual MRASTA features for low-resource keyword search and speech recognition systems. ICASSP 2014: 7854-7858 - [c126]Michal Kozielski, Martin Matysiak, Patrick Doetsch, Ralf Schlüter, Hermann Ney:
Open-Lexicon Language Modeling Combining Word and Character Levels. ICFHR 2014: 343-348 - [c125]David Nolden, Ralf Schlüter, Hermann Ney:
Word pair approximation for more efficient decoding with high-order language models. INTERSPEECH 2014: 646-650 - [c124]Martin Sundermeyer, Zoltán Tüske, Ralf Schlüter, Hermann Ney:
Lattice decoding and rescoring with long-Span neural network language models. INTERSPEECH 2014: 661-665 - [c123]Zoltán Tüske, Pavel Golik, Ralf Schlüter, Hermann Ney:
Acoustic modeling with deep neural networks using raw time signal for LVCSR. INTERSPEECH 2014: 890-894 - [c122]M. Ali Basha Shaik, Zoltán Tüske, Muhammad Ali Tahir, Markus Nußbaum-Thom, Ralf Schlüter, Hermann Ney:
RWTH LVCSR systems for quaero and EU-bridge: German, Polish, Spanish and Portuguese. INTERSPEECH 2014: 973-977 - [c121]Zoltán Tüske, Pavel Golik, David Nolden, Ralf Schlüter, Hermann Ney:
Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages. INTERSPEECH 2014: 1420-1424 - [c120]Martin Sundermeyer, Ralf Schlüter, Hermann Ney:
rwthlm - the RWTH aachen university neural network language modeling toolkit. INTERSPEECH 2014: 2093-2097 - 2013
- [j12]David Rybach, Hermann Ney, Ralf Schlüter:
Lexical Prefix Tree and WFST: A Comparison of Two Dynamic Search Concepts for LVCSR. IEEE Trans. Speech Audio Process. 21(6): 1295-1307 (2013) - [j11]Georg Heigold, Hermann Ney, Ralf Schlüter
:
Investigations on an EM-Style Optimization Algorithm for Discriminative Training of HMMs. IEEE ACM Trans. Audio Speech Lang. Process. 21(12): 2616-2626 (2013) - [c119]David Nolden, Ralf Schlüter
, Hermann Ney:
Efficient nearly error-less LVCSR decoding based on incremental forward and backward passes. ASRU 2013: 66-71 - [c118]Christian Plahl, Michal Kozielski, Ralf Schlüter
, Hermann Ney:
Feature combination and stacking of recurrent and non-recurrent neural networks for LVCSR. ICASSP 2013: 6714-6718 - [c117]David Nolden, Ralf Schlüter
, Hermann Ney:
Advanced search space pruning with acoustic look-ahead for WFST based LVCSR. ICASSP 2013: 6734-6738 - [c116]Simon Wiesler, Alexander Richard, Ralf Schlüter
, Hermann Ney:
A critical evaluation of stochastic algorithms for convex optimization. ICASSP 2013: 6955-6959 - [c115]Zoltán Tüske, Ralf Schlüter
, Hermann Ney:
Deep hierarchical bottleneck MRASTA features for LVCSR. ICASSP 2013: 6970-6974 - [c114]Zoltán Tüske, Joel Pinto, Daniel Willett, Ralf Schlüter
:
Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions. ICASSP 2013: 7349-7353 - [c113]Michal Kozielski, David Rybach, Stefan Hahn, Ralf Schlüter
, Hermann Ney:
Open vocabulary handwriting recognition using combined word-level and character-level language models. ICASSP 2013: 8257-8261 - [c112]Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Brian Kingsbury, Kate M. Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter
, Abhinav Sethy, Philip C. Woodland:
System combination and score normalization for spoken term detection. ICASSP 2013: 8272-8276 - [c111]Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Kate M. Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter
, Abhinav Sethy, Philip C. Woodland:
A high-performance Cantonese keyword search system. ICASSP 2013: 8277-8281 - [c110]Martin Sundermeyer, Ilya Oparin, Jean-Luc Gauvain, B. Freiberg, Ralf Schlüter
, Hermann Ney:
Comparison of feedforward and recurrent neural network language models. ICASSP 2013: 8430-8434 - [c109]Stefan Hahn, Patrick Lehnen, Simon Wiesler, Ralf Schlüter, Hermann Ney:
Improving LVCSR with hidden conditional random fields for grapheme-to-phoneme conversion. INTERSPEECH 2013: 495-499 - [c108]Markus Nußbaum-Thom, Eugen Beck, Tamer Alkhouli, Ralf Schlüter, Hermann Ney:
Relative error bounds for statistical classifiers based on the f-divergence. INTERSPEECH 2013: 2197-2201 - [c107]Zoltán Tüske, Ralf Schlüter, Hermann Ney:
Multilingual hierarchical MRASTA features for ASR. INTERSPEECH 2013: 2222-2226 - [c106]Pavel Golik, Zoltán Tüske, Ralf Schlüter, Hermann Ney:
Development of the RWTH transcription system for slovenian. INTERSPEECH 2013: 3107-3111 - [c105]Muhammad Ali Tahir, Heyun Huang, Ralf Schlüter, Hermann Ney, Louis ten Bosch, Bert Cranen, Lou Boves:
Training log-linear acoustic models in higher-order polynomial feature space for speech recognition. INTERSPEECH 2013: 3352-3355 - [c104]M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlüter, Hermann Ney:
Feature-rich sub-lexical language models using a maximum entropy approach for German LVCSR. INTERSPEECH 2013: 3404-3408 - [c103]Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlüter, Hermann Ney:
Morpheme level hierarchical pitman-yor class-based language models for LVCSR of morphologically rich languages. INTERSPEECH 2013: 3409-3413 - [c102]Ralf Schlüter
, Markus Nußbaum-Thom, Eugen Beck, Tamer Alkhouli, Hermann Ney:
Novel tight classification error bounds under mismatch conditions based on f-Divergence. ITW 2013: 1-5 - [c101]M. Ali Basha Shaik, Zoltán Tüske, Simon Wiesler, Markus Nußbaum-Thom, Stephan Peitz, Ralf Schlüter, Hermann Ney:
The RWTH Aachen German and English LVCSR systems for IWSLT-2013. IWSLT (Evaluation Campaign) 2013 - 2012
- [j10]Ralf Schlüter
, Markus Nußbaum-Thom, Hermann Ney:
Does the Cost Function Matter in Bayes Decision Rule? IEEE Trans. Pattern Anal. Mach. Intell. 34(2): 292-301 (2012) - [j9]Georg Heigold, Hermann Ney, Ralf Schlüter
, Simon Wiesler:
Discriminative Training for Automatic Speech Recognition: Modeling, Criteria, Optimization, Implementation, and Performance. IEEE Signal Process. Mag. 29(6): 58-69 (2012) - [j8]Björn Hoffmeister, Georg Heigold, David Rybach, Ralf Schlüter
, Hermann Ney:
WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding. IEEE Trans. Speech Audio Process. 20(2): 551-564 (2012) - [c100]Yotaro Kubo, Shinji Watanabe
, Atsushi Nakamura, Simon Wiesler, Ralf Schlüter
, Hermann Ney:
Basis vector orthogonalization for an improved kernel gradient matching pursuit method. ICASSP 2012: 1909-1912 - [c99]Zoltán Tüske, Ralf Schlüter
, Hermann Ney:
Comparison and combination of different CRBE based MLP features for LVCSR. ICASSP 2012: 4081-4084 - [c98]David Rybach, Ralf Schlüter
, Hermann Ney:
Silence is golden: Modeling non-speech events in WFST-based dynamic network decoders. ICASSP 2012: 4205-4208 - [c97]David Nolden, David Rybach, Ralf Schlüter
, Hermann Ney:
Joining advantages of word-conditioned and token-passing decoding. ICASSP 2012: 4425-4428 - [c96]David Nolden, Ralf Schlüter
, Hermann Ney:
Extended search space pruning in LVCSR. ICASSP 2012: 4429-4432 - [c95]Amr El-Desoky Mousa, Ralf Schlüter
, Hermann Ney:
Investigations on the use of morpheme level features in Language Models for Arabic LVCSR. ICASSP 2012: 5021-5024 - [c94]Zoltán Tüske, Ralf Schlüter, Hermann Ney, Martin Sundermeyer:
Context-Dependent MLPs for LVCSR: TANDEM, Hybrid or Both? INTERSPEECH 2012: 18-21 - [c93]Zoltán Tüske, Friedhelm R. Drepper, Ralf Schlüter:
Non-stationary signal processing and its application in speech recognition. SAPA@INTERSPEECH 2012: 34-39 - [c92]M. Ali Basha Shaik, David Rybach, Stefan Hahn, Ralf Schlüter, Hermann Ney:
Hierarchical hybrid language models for open vocabulary continuous speech recognition using WFST. SAPA@INTERSPEECH 2012: 46-51 - [c91]Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlüter, Hermann Ney:
Morpheme Level Feature-based Language Models for German LVCSR. INTERSPEECH 2012: 170-173 - [c90]Martin Sundermeyer, Ralf Schlüter, Hermann Ney:
LSTM Neural Networks for Language Modeling. INTERSPEECH 2012: 194-197 - [c89]Muhammad Ali Tahir, Markus Nußbaum-Thom, Ralf Schlüter, Hermann Ney:
Simultaneous Discriminative Training and Mixture Splitting of HMMs for Speech Recognition. INTERSPEECH 2012: 571-574 - [c88]David Nolden, Ralf Schlüter, Hermann Ney:
Search Space Pruning Based on Anticipated Path Recombination in LVCSR. INTERSPEECH 2012: 1015-1018 - [c87]M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlüter, Hermann Ney:
Investigation of Maximum Entropy Hybrid Language Models for Open Vocabulary German and Polish LVCSR. INTERSPEECH 2012: 1071-1074 - [c86]Simon Wiesler, Ralf Schlüter, Hermann Ney:
Accelerated Batch Learning of Convex Log-linear Models for LVCSR. INTERSPEECH 2012: 1207-1210 - [c85]Markus Nußbaum-Thom, Zoltán Tüske, Georg Heigold, Ralf Schlüter, Hermann Ney:
Posterior-Scaled MPE: Novel Discriminative Training Criteria. INTERSPEECH 2012: 2614-2617 - [c84]Zoltán Tüske, Friedhelm R. Drepper, Ralf Schlüter
:
Phase difference of filter-stable part-tones as acoustic feature. SSP 2012: 365-368 - 2011
- [j7]Ralf Schlüter
, Markus Nußbaum-Thom, Hermann Ney:
On the Relationship Between Bayes Risk and Word Error Rate in ASR. IEEE Trans. Speech Audio Process. 19(5): 1103-1112 (2011) - [j6]Georg Heigold, Hermann Ney, Patrick Lehnen, Tobias Gass, Ralf Schlüter
:
Equivalence of Generative and Log-Linear Models. IEEE Trans. Speech Audio Process. 19(5): 1138-1148 (2011) - [c83]Simon Wiesler, Ralf Schlüter
, Hermann Ney:
A convergence analysis of log-linear training and its application to speech recognition. ASRU 2011: 1-6 - [c82]Muhammad Ali Tahir, Ralf Schlüter
, Hermann Ney:
Discriminative splitting of Gaussian/log-linear mixture HMMs for speech recognition. ASRU 2011: 7-11 - [c81]Christian Plahl, Ralf Schlüter
, Hermann Ney:
Cross-lingual portability of Chinese and english neural network features for French and German LVCSR. ASRU 2011: 371-376 - [c80]Martin Sundermeyer, Markus Nußbaum-Thom, Simon Wiesler, Christian Plahl, Amr El-Desoky Mousa, Stefan Hahn, David Nolden, Ralf Schlüter
, Hermann Ney:
The RWTH 2010 Quaero ASR evaluation system for English, French, and German. ICASSP 2011: 2212-2215 - [c79]Yotaro Kubo, Simon Wiesler, Ralf Schlüter
, Hermann Ney, Shinji Watanabe
, Atsushi Nakamura, Tetsunori Kobayashi:
Subspace pursuit method for kernel-log-linear models. ICASSP 2011: 4500-4503 - [c78]M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlüter
, Hermann Ney:
Using morpheme and syllable based sub-words for polish LVCSR. ICASSP 2011: 4680-4683 - [c77]David Nolden, Hermann Ney, Ralf Schlüter
:
Exploiting sparseness of backing-off language models for efficient look-ahead in LVCSR. ICASSP 2011: 4684-4687 - [c76]David Rybach, Ralf Schlüter
, Hermann Ney:
A comparative analysis of dynamic network decoding. ICASSP 2011: 5184-5187 - [c75]Zoltán Tüske, Pavel Golik, Ralf Schlüter
, Friedhelm R. Drepper:
Non-stationary feature extraction for automatic speech recognition. ICASSP 2011: 5204-5207 - [c74]Simon Wiesler, Alexander Richard, Yotaro Kubo, Ralf Schlüter
, Hermann Ney:
Feature selection for log-linear acoustic models. ICASSP 2011: 5324-5327 - [c73]David Nolden, Ralf Schlüter, Hermann Ney:
Acoustic Look-Ahead for More Efficient Decoding in LVCSR. INTERSPEECH 2011: 893-896 - [c72]Zoltán Tüske, Christian Plahl, Ralf Schlüter:
A Study on Speaker Normalized MLP Features in LVCSR. INTERSPEECH 2011: 1089-1092 - [c71]Christian Plahl, Ralf Schlüter, Hermann Ney:
Improved Acoustic Feature Combination for LVCSR by Neural Networks. INTERSPEECH 2011: 1237-1240 - [c70]Martin Sundermeyer, Ralf Schlüter, Hermann Ney:
On the Estimation of Discount Parameters for Language Model Smoothing. INTERSPEECH 2011: 1433-1436 - [c69]M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlüter, Hermann Ney:
Hybrid Language Models Using Mixed Types of Sub-Lexical Units for Open Vocabulary German LVCSR. INTERSPEECH 2011: 1441-1444 - [c68]Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlüter, Hermann Ney:
Morpheme Based Factored Language Models for German LVCSR. INTERSPEECH 2011: 1445-1448 - [c67]Markus Nußbaum-Thom, Amr El-Desoky Mousa, Ralf Schlüter, Hermann Ney:
Compound Word Recombination for German LVCSR. INTERSPEECH 2011: 1449-1452 - [c66]Muhammad Ali Tahir, Ralf Schlüter, Hermann Ney:
Log-Linear Optimization of Second-Order Polynomial Features with Subsequent Dimension Reduction for Speech Recognition. INTERSPEECH 2011: 1705-1708 - [c65]Lori Lamel, Sandrine Courcinous, Julien Despres, Jean-Luc Gauvain, Yvan Josse, Kevin Kilgour, Florian Kraft, Viet Bac Le, Hermann Ney, Markus Nußbaum-Thom, Ilya Oparin, Tim Schlippe, Ralf Schlüter, Tanja Schultz, Thiago Fraga-Silva, Sebastian Stüker, Martin Sundermeyer, Bianca Vieru, Ngoc Thang Vu, Alex Waibel, Cécile Woehrling:
Speech recognition for machine translation in Quaero. IWSLT 2011: 121-128 - 2010
- [j5]Georg Heigold, Philippe Dreuw, Stefan Hahn, Ralf Schlüter
, Hermann Ney:
Margin-Based Discriminative Training for String Recognition. IEEE J. Sel. Top. Signal Process. 4(6): 917-925 (2010) - [c64]Georg Heigold, Simon Wiesler, Markus Nußbaum-Thom, Patrick Lehnen, Ralf Schlüter
, Hermann Ney:
Discriminative HMMS, log-linear models, and CRFS: What is the difference? ICASSP 2010: 5546-5549 - [c63]Simon Wiesler, Georg Heigold, Markus Nußbaum-Thom, Ralf Schlüter, Hermann Ney:
A discriminative splitting criterion for phonetic decision trees. INTERSPEECH 2010: 54-57 - [c62]Ralf Schlüter, Markus Nußbaum-Thom, Hermann Ney:
On the relation of Bayes risk, word error, and word posteriors in ASR. INTERSPEECH 2010: 230-233 - [c61]David Nolden, Hermann Ney, Ralf Schlüter:
Time conditioned search in automatic speech recognition reconsidered. INTERSPEECH 2010: 234-237 - [c60]Doddipatla Rama Sanand, Ralf Schlüter, Hermann Ney:
Revisiting VTLN using linear transformation on conventional MFCC. INTERSPEECH 2010: 538-541 - [c59]Christian Plahl, Ralf Schlüter, Hermann Ney:
Hierarchical bottle neck features for LVCSR. INTERSPEECH 2010: 1197-1200 - [c58]Naveen Parihar, Ralf Schlüter, David Rybach, Eric A. Hansen:
Parallel lexical-tree based LVCSR on multi-core processors. INTERSPEECH 2010: 1485-1488 - [c57]Markus Nußbaum-Thom, Simon Wiesler, Martin Sundermeyer, Christian Plahl, Stefan Hahn, Ralf Schlüter, Hermann Ney:
The RWTH 2009 quaero ASR evaluation system for English and German. INTERSPEECH 2010: 1517-1520 - [c56]Jonas Lööf, Ralf Schlüter, Hermann Ney:
Discriminative adaptation for log-linear acoustic models. INTERSPEECH 2010: 1648-1651 - [c55]Amr El-Desoky, Ralf Schlüter, Hermann Ney:
A Hybrid Morphologically Decomposed Factored Language Models for Arabic LVCSR. HLT-NAACL 2010: 701-704 - [c54]Amr El-Desoky Mousa, M. Ali Basha Shaik, Ralf Schlüter
, Hermann Ney:
Sub-lexical language models for German LVCSR. SLT 2010: 171-176 - [c53]Jonas Lööf, Daniele Falavigna, Ralf Schlüter
, Diego Giuliani, Roberto Gretter, Hermann Ney:
Evaluation of automatic transcription systems for the judicial domain. SLT 2010: 206-211
2000 – 2009
- 2009
- [c52]Simon Wiesler, Markus Nußbaum-Thom, Georg Heigold, Ralf Schlüter
, Hermann Ney:
Investigations on features for log-linear acoustic models in continuous speech recognition. ASRU 2009: 52-57 - [c51]Muhammad Ali Tahir, Georg Heigold, Christian Plahl, Ralf Schlüter
, Hermann Ney:
Generalized likelihood ratio discriminant analysis. ASRU 2009: 76-81 - [c50]Georg Heigold, Ralf Schlüter
, Hermann Ney:
Modified MPE/MMI in a transducer-based framework. ICASSP 2009: 3749-3752 - [c49]David Rybach, Christian Gollan, Ralf Schlüter
, Hermann Ney:
Audio segmentation for speech recognition using segment features. ICASSP 2009: 4197-4200 - [c48]Daniele Falavigna, Diego Giuliani, Roberto Gretter, Jonas Lööf, Christian Gollan, Ralf Schlüter, Hermann Ney:
Automatic Transcription of Courtroom Recordings in the JUMAS project. ICT4Justice 2009: 65-72 - [c47]Georg Heigold, David Rybach, Ralf Schlüter, Hermann Ney:
Investigations on convex optimization using log-linear HMMs for digit string recognition. INTERSPEECH 2009: 216-219 - [c46]Björn Hoffmeister, Ruoying Liang, Ralf Schlüter, Hermann Ney:
Log-linear model combination with word-dependent scaling factors. INTERSPEECH 2009: 248-251 - [c45]Björn Hoffmeister, Ralf Schlüter, Hermann Ney:
Bayes risk approximations using time overlap with an application to system combination. INTERSPEECH 2009: 1191-1194 - [c44]Christian Plahl, Björn Hoffmeister, Georg Heigold, Jonas Lööf, Ralf Schlüter, Hermann Ney:
Development of the GALE 2008 Mandarin LVCSR system. INTERSPEECH 2009: 2107-2110 - [c43]David Rybach, Christian Gollan, Georg Heigold, Björn Hoffmeister, Jonas Lööf, Ralf Schlüter, Hermann Ney:
The RWTH aachen university open source speech recognition system. INTERSPEECH 2009: 2111-2114 - [c42]Amr El-Desoky, Christian Gollan, David Rybach, Ralf Schlüter, Hermann Ney:
Investigating the use of morphological decomposition and diacritization for improving Arabic LVCSR. INTERSPEECH 2009: 2679-2682 - [c41]Naveen Parihar, Ralf Schlüter, David Rybach, Eric A. Hansen:
Parallel fast likelihood computation for LVCSR using mixture decomposition. INTERSPEECH 2009: 3047-3050 - 2008
- [c40]Georg Heigold, Thomas Deselaers, Ralf Schlüter
, Hermann Ney:
A GIS-like training algorithm for log-linear models with hidden variables. ICASSP 2008: 4045-4048 - [c39]Georg Heigold, Thomas Deselaers, Ralf Schlüter, Hermann Ney:
Modified MMI/MPE: a direct evaluation of the margin in speech recognition. ICML 2008: 384-391 - [c38]Björn Hoffmeister, Ralf Schlüter, Hermann Ney:
iCNC and iROVER: the limits of improving system combination with classification? INTERSPEECH 2008: 232-235 - [c37]Georg Heigold, Patrick Lehnen, Ralf Schlüter, Hermann Ney:
On the equivalence of Gaussian and log-linear HMMs. INTERSPEECH 2008: 273-276 - [c36]Dimitra Vergyri, Arindam Mandal, Wen Wang, Andreas Stolcke, Jing Zheng, Martin Graciarena, David Rybach, Christian Gollan, Ralf Schlüter, Katrin Kirchhoff, Arlo Faria, Nelson Morgan:
Development of the SRI/nightingale Arabic ASR system. INTERSPEECH 2008: 1437-1440 - [c35]Christian Plahl, Björn Hoffmeister, Mei-Yuh Hwang, Danju Lu, Georg Heigold, Jonas Lööf, Ralf Schlüter, Hermann Ney:
Recent improvements of the RWTH GALE Mandarin LVCSR system. INTERSPEECH 2008: 2426-2429 - 2007
- [j4]András Zolnay, Daniil Kocharov
, Ralf Schlüter
, Hermann Ney:
Using multiple acoustic feature sets for speech recognition. Speech Commun. 49(6): 514-525 (2007) - [c34]David Rybach, Stefan Hahn, Christian Gollan, Ralf Schlüter
, Hermann Ney:
Advances in Arabic broadcast news transcription at RWTH. ASRU 2007: 449-454 - [c33]Björn Hoffmeister, Christian Plahl, Peter Fritz, Georg Heigold, Jonas Lööf, Ralf Schlüter
, Hermann Ney:
Development of the 2007 RWTH Mandarin LVCSR system. ASRU 2007: 455-460 - [c32]Ralf Schlüter
, Ilja Bezrukov, Hermann Wagner, Hermann Ney:
Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition. ICASSP (4) 2007: 649-652 - [c31]Björn Hoffmeister, Dustin Hillard, Stefan Hahn, Ralf Schlüter
, Mari Ostendorf, Hermann Ney:
Cross-Site and Intra-Site ASR System Combination: Comparisons on Lattice and 1-Best Methods. ICASSP (4) 2007: 1145-1148 - [c30]Fabio Valente, Jithendra Vepa, Christian Plahl, Christian Gollan, Hynek Hermansky, Ralf Schlüter:
Hierarchical neural networks feature extraction for LVCSR system. INTERSPEECH 2007: 42-45 - [c29]Jonas Lööf, Ralf Schlüter, Hermann Ney:
Efficient estimation of speaker-specific projecting feature transforms. INTERSPEECH 2007: 1557-1560 - [c28]Georg Heigold, Ralf Schlüter, Hermann Ney:
On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields. INTERSPEECH 2007: 1721-1724 - [c27]Christian Gollan, Stefan Hahn, Ralf Schlüter, Hermann Ney:
An improved method for unsupervised training of LVCSR systems. INTERSPEECH 2007: 2101-2104 - [c26]Jonas Lööf, Christian Gollan, Stefan Hahn, Georg Heigold, Björn Hoffmeister, Christian Plahl, David Rybach, Ralf Schlüter, Hermann Ney:
The RWTH 2007 TC-STAR evaluation system for european English and Spanish. INTERSPEECH 2007: 2145-2148 - [c25]Dustin Hillard, Björn Hoffmeister, Mari Ostendorf, Ralf Schlüter, Hermann Ney:
iROVER: Improving System Combination with Classification. HLT-NAACL (Short Papers) 2007: 65-68 - 2006
- [c24]Björn Hoffmeister, Tobias Klein, Ralf Schlüter, Hermann Ney:
Frame based system combination and a comparison with weighted ROVER and CNC. INTERSPEECH 2006 - [c23]Jonas Lööf, Maximilian Bisani, Christian Gollan, Georg Heigold, Björn Hoffmeister, Christian Plahl, Ralf Schlüter, Hermann Ney:
The 2006 RWTH parliamentary speeches transcription system. INTERSPEECH 2006 - [c22]Ralf Schlüter, András Zolnay, Hermann Ney:
Feature combination using linear discriminant analysis and its pitfalls. INTERSPEECH 2006 - 2005
- [c21]András Zolnay, Ralf Schlüter
, Hermann Ney:
Acoustic Feature Combination for Robust Speech Recognition. ICASSP (1) 2005: 457-460 - [c20]Christian Gollan, Maximilian Bisani, Stephan Kanthak, Ralf Schlüter
, Hermann Ney:
Cross Domain Automatic Transcription on the TC-STAR EPPS Corpus. ICASSP (1) 2005: 825-828 - [c19]Daniil Kocharov, András Zolnay, Ralf Schlüter, Hermann Ney:
Articulatory motivated acoustic features for speech recognition. INTERSPEECH 2005: 1101-1104 - [c18]Ralf Schlüter, T. Scharrenbach, Volker Steinbiss, Hermann Ney:
Bayes risk minimization using metric loss functions. INTERSPEECH 2005: 1449-1452 - [c17]Wolfgang Macherey, Lars Haferkamp, Ralf Schlüter, Hermann Ney:
Investigations on error minimizing training criteria for discriminative training in automatic speech recognition. INTERSPEECH 2005: 2133-2136 - 2004
- [c16]Wolfgang Macherey, Ralf Schlüter, Hermann Ney:
Discriminative training with tied covariance matrices. INTERSPEECH 2004: 705-708 - 2003
- [c15]András Zolnay, Ralf Schlüter, Hermann Ney:
Extraction methods of voicing feature for robust speech recognition. INTERSPEECH 2003: 497-500 - 2002
- [c14]András Zolnay, Ralf Schlüter, Hermann Ney:
Robust speech recognition using a voiced-unvoiced feature. INTERSPEECH 2002: 1065-1068 - 2001
- [j3]Ralf Schlüter
, Wolfgang Macherey, Boris Müller, Hermann Ney:
Comparison of discriminative training criteria and optimization methods for speech recognition. Speech Commun. 34(3): 287-310 (2001) - [j2]Ralf Schlüter
, Hermann Ney:
Model-based MCE bound to the true Bayes' error. IEEE Signal Process. Lett. 8(5): 131-133 (2001) - [j1]Frank Wessel, Ralf Schlüter
, Klaus Macherey, Hermann Ney:
Confidence measures for large vocabulary continuous speech recognition. IEEE Trans. Speech Audio Process. 9(3): 288-298 (2001) - [c13]Frank Wessel, Ralf Schlüter, Hermann Ney:
Explicit word error minimization using word hypothesis posterior probabilities. ICASSP 2001: 33-36 - [c12]Sirko Molau, Michael Pitz, Ralf Schlüter, Hermann Ney:
Computing Mel-frequency cepstral coefficients on the power spectrum. ICASSP 2001: 73-76 - [c11]Ralf Schlüter, Hermann Ney:
Using phase spectrum information for improved speech recognition performance. ICASSP 2001: 133-136 - [c10]Michael Pitz, Sirko Molau, Ralf Schlüter, Hermann Ney:
Vocal tract normalization equals linear transformation in cepstral space. INTERSPEECH 2001: 2653-2656 - 2000
- [b1]Ralf Schlüter:
Investigations on discriminative training criteria. RWTH Aachen University, Germany, 2000, pp. 1-138 - [c9]Frank Wessel, Ralf Schlüter
, Hermann Ney:
Using posterior word probabilities for improved speech recognition. ICASSP 2000: 1587-1590 - [c8]Achim Sixtus, Sirko Molau, Stephan Kanthak, Ralf Schlüter
, Hermann Ney:
Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech. ICASSP 2000: 1671-1674 - [c7]Ralf Schlüter, Frank Wessel, Hermann Ney:
Speech recognition using context conditional word posterior probabilities. INTERSPEECH 2000: 923-926 - [c6]Stephan Kanthak, Sirko Molau, Achim Sixtus, Ralf Schlüter, Hermann Ney:
The RWTH Large Vocabulary Speech Recognition System for Spontaneous Speech. KONVENS 2000: 249-254
1990 – 1999
- 1999
- [c5]Jörg Dahmen, Ralf Schlüter, Hermann Ney:
Discriminative Training of Gaussian Mixtures for Image Object Recognition. DAGM-Symposium 1999: 205-212 - [c4]Ralf Schlüter, Wolfgang Macherey, Boris Müller, Hermann Ney:
A combined maximum mutual information and maximum likelihood approach for mixture density splitting. EUROSPEECH 1999: 1715-1718 - 1998
- [c3]Frank Wessel, Klaus Macherey, Ralf Schlüter
:
Using word probabilities as confidence measures. ICASSP 1998: 225-228 - [c2]Ralf Schlüter
, Wolfgang Macherey:
Comparison of discriminative training criteria. ICASSP 1998: 493-496 - 1997
- [c1]Ralf Schlüter, Wolfgang Macherey, Stephan Kanthak, Hermann Ney, Lutz Welling:
Comparison of optimization methods for discriminative training criteria. EUROSPEECH 1997: 15-18
Coauthor Index
aka: Patrick Dötsch
aka: Amr El-Desoky
![](https://dblp.uni-trier.de/img/cog.dark.24x24.png)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-08-27 23:00 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint