Jahn Heymann

3.0k total citations · 2 hit papers
27 papers, 1.8k citations indexed

About

Jahn Heymann is a scholar working on Signal Processing, Artificial Intelligence and Computational Mechanics. According to data from OpenAlex, Jahn Heymann has authored 27 papers receiving a total of 1.8k indexed citations (citations by other indexed papers that have themselves been cited), including 24 papers in Signal Processing, 19 papers in Artificial Intelligence and 7 papers in Computational Mechanics. Recurrent topics in Jahn Heymann's work include Speech and Audio Processing (22 papers), Speech Recognition and Synthesis (18 papers) and Music and Audio Processing (16 papers). Jahn Heymann is often cited by papers focused on Speech and Audio Processing (22 papers), Speech Recognition and Synthesis (18 papers) and Music and Audio Processing (16 papers). Jahn Heymann collaborates with scholars based in Germany, United States and Japan. Jahn Heymann's 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 and has published in prestigious journals such as Proceedings of the IEEE and Computer Speech & Language.

In The Last Decade

Jahn Heymann

27 papers receiving 1.7k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

ESPnet: End-to-End Speech Processing Toolkit

2018 848 citations Shinji Watanabe, Takaaki Hori et al. profile →
Neural network based spectral mask estimation for acoustic beamforming

2016 321 citations Jahn Heymann, Lukas Drude et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Jahn Heymann Germany	17	1.5k	1.4k	372	102	101	27	1.8k
Xiao-Lei Zhang China	16	838 0.6×	816 0.6×	173 0.5×	92 0.9×	176 1.7×	83	1.2k
Rahim Saeidi Finland	21	1.1k 0.8×	848 0.6×	234 0.6×	81 0.8×	127 1.3×	65	1.2k
Chanwoo Kim United States	15	757 0.5×	644 0.5×	150 0.4×	71 0.7×	61 0.6×	42	980
Roland Maas Germany	15	873 0.6×	603 0.4×	301 0.8×	145 1.4×	52 0.5×	39	1.0k
Arun Narayanan United States	19	2.1k 1.4×	1.6k 1.1×	640 1.7×	361 3.5×	98 1.0×	69	2.4k
Ashutosh Pandey United States	14	908 0.6×	603 0.4×	387 1.0×	178 1.7×	60 0.6×	43	1.1k
Frédéric Bimbot France	24	1.6k 1.1×	1.3k 0.9×	320 0.9×	61 0.6×	461 4.6×	116	2.1k
Hans‐Günter Hirsch Germany	10	1.7k 1.1×	1.3k 0.9×	382 1.0×	156 1.5×	218 2.2×	21	1.8k
Atsunori Ogawa Japan	20	1.0k 0.7×	1.1k 0.8×	141 0.4×	63 0.6×	81 0.8×	136	1.5k
Jitong Chen United States	14	1.7k 1.2×	924 0.7×	649 1.7×	506 5.0×	137 1.4×	21	1.9k

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 of co-authors of Jahn Heymann

This figure shows the co-authorship network connecting the top 25 collaborators of Jahn Heymann. A scholar is included among the top collaborators of Jahn Heymann based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Jahn Heymann. Jahn Heymann is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

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

20 of 20 papers shown

1.

Heymann, Jahn, et al.. (2023). Conmer: Streaming Conformer Without Self-attention for Interactive Voice Assistants. 2198–2202. 4 indexed citations

2.

Heymann, Jahn, Lukas Drude, Reinhold Haeb‐Umbach, Keisuke Kinoshita, & Tomohiro Nakatani. (2019). Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR. 6655–6659. 21 indexed citations

3.

Drude, Lukas, Jahn Heymann, Christoph Boeddeker, & Reinhold Haeb‐Umbach. (2018). NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing. 1–5. 48 indexed citations

4.

Heymann, Jahn, et al.. (2018). Smoothing along Frequency in Online Neural Network Supported Acoustic Beamforming.. 1–5. 3 indexed citations

5.

Schmalenstroeer, Joerg, et al.. (2018). Front-end processing for the CHiME-5 dinner party scenario. 35–40. 85 indexed citations

6.

Watanabe, Shinji, Takaaki Hori, Shigeki Karita, et al.. (2018). ESPnet: End-to-End Speech Processing Toolkit. 2207–2211. 848 indexed citations breakdown →

7.

Heymann, Jahn, Michiel Bacchiani, & Tara N. Sainath. (2018). Performance of Mask Based Statistical Beamforming in a Smart Home Scenario. 6722–6726. 23 indexed citations

8.

Heymann, Jahn, Lukas Drude, Reinhold Haeb‐Umbach, Keisuke Kinoshita, & Tomohiro Nakatani. (2018). Frame-Online DNN-WPE Dereverberation. 19 indexed citations

9.

Heymann, Jahn, Lukas Drude, & Reinhold Haeb‐Umbach. (2017). A generic neural acoustic beamforming architecture for robust multi-channel speech processing. Computer Speech & Language. 46. 374–385. 28 indexed citations

10.

Boeddeker, Christoph, et al.. (2017). Optimizing neural-network supported acoustic beamforming by algorithmic differentiation. 171–175. 15 indexed citations

11.

Heymann, Jahn, et al.. (2017). Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery. 488–492. 23 indexed citations

12.

Heymann, Jahn, et al.. (2017). Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system. 5325–5329. 72 indexed citations

13.

Zeyer, Albert, et al.. (2016). Robust Online Multi-Channel Speech Recognition.. 1–5. 2 indexed citations

14.

Heymann, Jahn, et al.. (2016). Noise-Presence-Probability-Based Noise PSD Estimation by Using DNNs. 1–5. 4 indexed citations

15.

Heymann, Jahn, Lukas Drude, & Reinhold Haeb‐Umbach. (2016). Wide Residual BLSTM Network with Discriminative Speaker Adaptation for Robust Speech Recognition. Computer Speech & Language. 37 indexed citations

16.

Menne, Tobias, Jahn Heymann, Anastasios Alexandridis, et al.. (2016). The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation. Computer Speech & Language. 21 indexed citations

17.

Heymann, Jahn, et al.. (2015). BLSTM supported GEV beamformer front-end for the 3RD CHiME challenge. 444–451. 98 indexed citations

18.

Heymann, Jahn, Reinhold Haeb‐Umbach, Pavel Golik, & Ralf Schlüter. (2015). Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions. 18. 5053–5057. 3 indexed citations

19.

Heymann, Jahn, et al.. (2014). Iterative Bayesian word segmentation for unsupervised vocabulary discovery from phoneme lattices. 25. 4057–4061. 17 indexed citations

20.

Heymann, Jahn, et al.. (2013). Unsupervised word segmentation from noisy input. 458–463. 16 indexed citations

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