Jahn Heymann

Amazon (United States) — United States

Computer Science · Physical Sciences

21h-index2.9kcitations39works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech and Audio Processing(30), Speech Recognition and Synthesis(27), Music and Audio Processing(22), Advanced Adaptive Filtering Techniques(10), Natural Language Processing Techniques(7)

Publications39 total

Conmer: Streaming Conformer Without Self-attention for Interactive Voice Assistants
2023· 5 cited
Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition
2023· 1 cited
Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition
arXiv (Cornell University)·2023Open Access
Towards Accurate and Real-Time End-of-Speech Estimation
2023
Being Greedy Does Not Hurt: Sampling Strategies for End-To-End Speech Recognition
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022
Multi-Channel Opus Compression for Far-Field Automatic Speech Recognition with a Fixed Bitrate Budget
2021Open Access
Multi-channel Opus compression for far-field automatic speech\n recognition with a fixed bitrate budget
arXiv (Cornell University)·2021· 1 citedOpen Access
Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition
2020Open Access
Improving Speech Recognition of Compound-Rich Languages
2020
Far-Field Automatic Speech Recognition
arXiv (Cornell University)·2020Open Access
Far-Field Automatic Speech Recognition
Proceedings of the IEEE·2020· 108 cited
Subword Regularization: An Analysis of Scalability and Generalization\n for End-to-End Automatic Speech Recognition
arXiv (Cornell University)·2020Open Access
Unsupervised Training of Neural Mask-Based Beamforming
2019· 7 citedOpen Access
Improving CTC Using Stimulated Learning for Sequence Modeling
2019· 5 cited
Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR
2019· 31 cited
The RWTH/UPB system combination for the CHiME 2018 Workshop
2018· 8 cited
Front-end processing for the CHiME-5 dinner party scenario
2018· 136 cited
Frame-Online DNN-WPE Dereverberation
2018· 29 cited
ESPnet: End-to-End Speech Processing Toolkit
2018· 1.3k cited
Integrating Neural Network Based Beamforming and Weighted Prediction Error Dereverberation
2018· 43 cited
page 1 of 2Next →

Frequent Co-authors

Reinhold Haeb‐Umbach(25), Lukas Drude(24), Christoph Boeddeker(6), Tomohiro Nakatani(5), Simon Wiesler(5), Shinji Watanabe(4), Ralf Schlüter(4), Jens Heitkaemper(3), Joerg Schmalenstroeer(3), Patrick Hanebrink(3), Marc Delcroix(3), Bhiksha Raj(3), Keisuke Kinoshita(3), Markus Kitza(3), Egor Lakomkin(3), Takaaki Hori(2), Shigeki Karita(2), Tomoki Hayashi(2), Jiro Nishitoba(2), Yuya Unno(2)