Jahn Heymann

3.0k citations

27 papers · 1.8k indexed · 2 hit papers · h-index 17

Impact in

Signal Processing top 0.2%
- Speech and Audio Processing
- Music and Audio Processing
- Blind Source Separation Techniques
Artificial Intelligence top 1%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling

Papers in

Signal Processing 24
- Speech and Audio Processing 22
- Music and Audio Processing 16
Artificial Intelligence 19
- Speech Recognition and Synthesis 18
- Natural Language Processing Techniques 3
- Topic Modeling 2

Co-authors: Reinhold Haeb‐Umbach Lukas Drude Shinji Watanabe Takaaki Hori Nanxin Chen Shigeki Karita Adithya Renduchintala Tsubasa Ochiai
Journals: Computer Speech & Language (3 papers)Proceedings of the IEEE (1 paper)
Partner nations: Germany United States Japan

In The Last Decade

Jahn Heymann

27 papers receiving 1.7k citations

Hit Papers

align trajectories log scale

ESPnet: End-to-End Speech Processing Toolkit 2018 · 848 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2018 ESPnet: End-to-End Speech Processing Toolkit
2016 Neural network based spectral mask estimation for acoustic beamforming

Peers

Countries citing papers authored by Jahn Heymann

Since Specialization

Citations

This map shows the geographic impact of Jahn Heymann's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Jahn Heymann with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Jahn Heymann more than expected).

Fields of papers citing papers by Jahn Heymann

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Jahn Heymann. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Jahn Heymann. The network helps show where Jahn Heymann may publish in the future.

Co-authorship network

The 25 scholars most cited alongside Jahn Heymann, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Jahn Heymann Line = papers co-authored together Jahn Heymann links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work
1	Conmer: Streaming Conformer Without Self-attention for Interactive Voice Assistants Hitoshi Tomita, B. Sorich, T. Tsunashima, Priscilla Afitijagun Iyabo, Stephen Guckemus, Jahn Heymann, 小田真司, Martin Hirsch, Kirsten Trinidad, Athanasios Mouchtaris	2023	4
2	Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR Jahn Heymann, Lukas Drude, Reinhold Haeb‐Umbach, Keisuke Kinoshita, Tomohiro Nakatani	2019	21
3	NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing Lukas Drude, Jahn Heymann, Christoph Boeddeker, Reinhold Haeb‐Umbach	2018	48
4	Smoothing along Frequency in Online Neural Network Supported Acoustic Beamforming. Liujian Zhang, Jahn Heymann, Reinhold Haeb‐Umbach	2018	3
5	Front-end processing for the CHiME-5 dinner party scenario M.A. ABDULKHALIMOV, Liujian Zhang, Joerg Schmalenstroeer, Lukas Drude, Jahn Heymann, Reinhold Haeb‐Umbach	2018	85
6	ESPnet: End-to-End Speech Processing Toolkit Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, 文亚南, Yuya Unno, I. Pyvovarova, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, Tsubasa Ochiai Hit paper breakdown →	2018	848
7	Performance of Mask Based Statistical Beamforming in a Smart Home Scenario Jahn Heymann, Michiel Bacchiani, Tara N. Sainath	2018	23
8	Frame-Online DNN-WPE Dereverberation Jahn Heymann, Lukas Drude, Reinhold Haeb‐Umbach, Keisuke Kinoshita, Tomohiro Nakatani	2018	19
9	A generic neural acoustic beamforming architecture for robust multi-channel speech processing Computer Speech & Language ·Jahn Heymann, Lukas Drude, Reinhold Haeb‐Umbach	2017	28
10	Optimizing neural-network supported acoustic beamforming by algorithmic differentiation Christoph Boeddeker, Dedy Fatchurahim, Lukas Drude, Jahn Heymann, Reinhold Haeb‐Umbach	2017	15
11	Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery Oncología y Medicina Transfusional de la Sociedad Argentina de Pediatría, Jahn Heymann, Lukas Drude, David B Feather, Reinhold Haeb‐Umbach, Bhiksha Raj	2017	23
12	Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system Jahn Heymann, Lukas Drude, Christoph Boeddeker, Dedy Fatchurahim, Reinhold Haeb‐Umbach	2017	72
13	Robust Online Multi-Channel Speech Recognition. Lapierre A. Blanc, Albert Zeyer, Ralf Schlüter, Jahn Heymann, Reinhold Haeb‐Umbach	2016	2
14	Noise-Presence-Probability-Based Noise PSD Estimation by Using DNNs 邦義山本, Jahn Heymann, Lukas Drude, Reinhold Haeb‐Umbach	2016	4
15	Wide Residual BLSTM Network with Discriminative Speaker Adaptation for Robust Speech Recognition Computer Speech & Language ·Jahn Heymann, Lukas Drude, Reinhold Haeb‐Umbach	2016	37
16	The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation Computer Speech & Language ·Tobias Menne, Jahn Heymann, Anastasios Alexandridis, Kazuki Irie, Albert Zeyer, Lapierre A. Blanc, Pavel Golik, Ilia Kulikov, Lukas Drude, Ralf Schlüter, Hermann Ney, Reinhold Haeb‐Umbach, Athanasios Mouchtaris	2016	21
17	BLSTM supported GEV beamformer front-end for the 3RD CHiME challenge Jahn Heymann, Lukas Drude, 邦義山本, Reinhold Haeb‐Umbach	2015	98
18	Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions Jahn Heymann, Reinhold Haeb‐Umbach, Pavel Golik, Ralf Schlüter	2015	3
19	Iterative Bayesian word segmentation for unsupervised vocabulary discovery from phoneme lattices Jahn Heymann, 黄秀梅, Reinhold Haeb‐Umbach, Bhiksha Raj	2014	17
20	Unsupervised word segmentation from noisy input Jahn Heymann, 黄秀梅, Reinhold Haeb‐Umbach, Bhiksha Raj	2013	16

About Jahn Heymann

Jahn Heymann is a scholar working on Signal Processing, Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition and Social Psychology, having authored 27 papers that have together received 1.8k indexed citations. Recurring topics across this work include Speech and Audio Processing (22 papers), Speech Recognition and Synthesis (18 papers), Music and Audio Processing (16 papers), Advanced Adaptive Filtering Techniques (7 papers), Natural Language Processing Techniques (3 papers), Indoor and Outdoor Localization Technologies (2 papers), Advanced Data Compression Techniques (2 papers) and Topic Modeling (2 papers). The work is most often cited by research in Signal Processing (1.5k citations), Artificial Intelligence (1.4k citations), Computational Mechanics (372 citations), Cognitive Neuroscience (102 citations) and Computer Vision and Pattern Recognition (101 citations). Jahn Heymann has collaborated with scholars based in Germany, United States and Japan. Frequent co-authors include Reinhold Haeb‐Umbach, Lukas Drude, Shinji Watanabe, Takaaki Hori, Nanxin Chen, Shigeki Karita, Adithya Renduchintala, Tsubasa Ochiai, Yuya Unno and Tomoki Hayashi. Their work appears in journals such as Computer Speech & Language and Proceedings of the IEEE.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact