From

Institution

Field

Type

Open access only Cited by patents (Lens) Include non-Aachen papers (citing/cited)

Reset

Papers matching “hybrid speech recognition” 26

Sort: Relevance Cited Newest Oldest Fwci Patents ⇩ CSV

Not finding it? Sign in to also search OpenAlex live.

Full-Sum Decoding for Hybrid HMM based Speech Recognition using LSTM Language Model
2020 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Wei Guo Zhou, Ralf Schlüter, Hermann Ney

1

citations
Discriminative feature modeling for statistical speech recognition
2020 RWTH Publications (RWTH Aachen) dissertation Computer Science Speech Recognition and Synthesis Open access

Zoltán Tüske

1

citations
AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
2025 IEEE Biomedical Circuits and Systems Conference (BioCAS) conference-paper Computer Science Speech Recognition and Synthesis Open access

Chuanbing Huo, Qinyu Chen, Chang Gao

3

citations
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) conference-paper Computer Science Speech Recognition and Synthesis Open access

Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes, Ralf Schlüter, Hermann Ney

4

citations
HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
2022 RWTH Publications (RWTH Aachen) conference-paper Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Wei Guo Zhou, Simon Berger, Ralf Schlüter, Hermann Ney

1

citations
Conformer-based Hybrid ASR System for Switchboard Dataset
2021 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Mohammad Zeineldeen, Jingjing Xu, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney

0

citations
On Language Model Integration for RNN Transducer Based Speech Recognition
2022 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access cited by 1 patent

Wei Guo Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

18

citations
On Language Model Integration for RNN Transducer based Speech Recognition
2021 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Wei Guo Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

4

citations
Conformer-Based Hybrid ASR System For Switchboard Dataset
2022 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access

Mohammad Zeineldeen, Jingjing Xu, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney

22

citations
Towards Consistent Hybrid HMM Acoustic Modeling
2021 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney

4

citations
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
2022 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Mohammad Zeineldeen, Jingjing Xu, Ralf Schlüter, Hermann Ney

0

citations
Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think
2023 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Christoph Lüscher, Moritz Gunz, Ralf Schlüter, Hermann Ney

0

citations
Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR
2023 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Jintao Jiang, Yingbo Gao, Zoltán Tüske

0

citations
Improving Factored Hybrid HMM Acoustic Modeling without State Tying
2022 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney

0

citations
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment
2020 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Wei Guo Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schlüter, Hermann Ney

1

citations
Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR
2024 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Jintao Jiang, Yingbo Gao, Mohammad Zeineldeen, Zoltán Tüske

0

citations
Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021
2021 International Conference on Spoken Language Translation (IWSLT) conference-paper Computer Science Speech Recognition and Synthesis Open access

Parnia Bahar, Patrick Wilken, Mattia Antonino Di Gangi, Evgeny Matusov

7

citations
Language model integration into acoustic model training
2026 RWTH Publications (RWTH Aachen) dissertation Computer Science Speech Recognition and Synthesis Open access

Wilfried Michel

0

citations
Context-Dependent Acoustic Modeling Without Explicit Phone Clustering
2020 Interspeech (USB) conference-paper Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Eugen Beck, Ralf Schlüter, Hermann Ney

9

citations
Early Stage LM Integration Using Local and Global Log-Linear Combination
2020 Interspeech (USB) conference-paper Computer Science Speech Recognition and Synthesis Open access

Wilfried Michel, Ralf Schlüter, Hermann Ney

10

citations
Analyzing And Improving Neural Speaker Embeddings for ASR
2023 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Christoph Lüscher, Jingjing Xu, Mohammad Zeineldeen, Ralf Schlüter, Hermann Ney

0

citations
Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR Models
2021 Interspeech (USB) conference-paper Computer Science Speech Recognition and Synthesis Open access cited by 1 patent

Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel, Albert Zeyer, Ralf Schlüter, Hermann Ney

38

citations
On Architectures and Training for Raw Waveform Feature Extraction in ASR
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) conference-paper Computer Science Speech Recognition and Synthesis Open access

Peter Vieting, Wilfried Michel, Ralf Schlüter, Hermann Ney

3

citations
Right Label Context in End-to-End Training of Time-Synchronous ASR Models
2025 IEEE International Conference on Acoustics Speech and Signal Processing conference-paper Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Ralf Schlüter, Hermann Ney

1

citations
Right Label Context in End-to-End Training of Time-Synchronous ASR Models
2025 arXiv (Cornell University) preprint Computer Science Speech Recognition and Synthesis Open access

Tina Raissi, Ralf Schlüter, Hermann Ney

0

citations