Kazuki Irie

1.5k total citations
28 papers, 398 citations indexed

About

Kazuki Irie is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Kazuki Irie has authored 28 papers receiving a total of 398 indexed citations (citations by other indexed papers that have themselves been cited), including 25 papers in Artificial Intelligence, 7 papers in Signal Processing and 4 papers in Computer Vision and Pattern Recognition. Recurrent topics in Kazuki Irie's work include Topic Modeling (17 papers), Speech Recognition and Synthesis (16 papers) and Natural Language Processing Techniques (15 papers). Kazuki Irie is often cited by papers focused on Topic Modeling (17 papers), Speech Recognition and Synthesis (16 papers) and Natural Language Processing Techniques (15 papers). Kazuki Irie collaborates with scholars based in Germany, Switzerland and United States. Kazuki Irie's co-authors include Hermann Ney, Ralf Schlüter, Albert Zeyer, Zoltán Tüske, Juergen Schmidhuber, Tamer Alkhouli, Jürgen Schmidhuber, Hank Liao, Wei Zhou and Shankar Kumar and has published in prestigious journals such as Neuron, Neural Computation and Nature Machine Intelligence.

In The Last Decade

Kazuki Irie

27 papers receiving 373 citations

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Kazuki Irie Germany 11 311 144 42 23 22 28 398
Albert Zeyer Germany 10 256 0.8× 172 1.2× 25 0.6× 12 0.5× 20 0.9× 21 323
Matthew Middlehurst United Kingdom 5 271 0.9× 312 2.2× 37 0.9× 12 0.5× 22 1.0× 9 447
Tianmeng Yang China 3 212 0.7× 190 1.3× 36 0.9× 19 0.8× 50 2.3× 5 362
Zhihan Yue China 3 208 0.7× 190 1.3× 35 0.8× 16 0.7× 49 2.2× 4 360
Mohammad Shokoohi-Yekta United States 5 200 0.6× 241 1.7× 51 1.2× 24 1.0× 22 1.0× 8 378
Philémon Brakel Canada 7 236 0.8× 118 0.8× 62 1.5× 13 0.6× 72 3.3× 11 392
Ziheng Duan United States 9 127 0.4× 72 0.5× 25 0.6× 20 0.9× 19 0.9× 23 285
Yuchen Fan China 9 574 1.8× 430 3.0× 106 2.5× 10 0.4× 30 1.4× 15 691
Vassilios Petridis Greece 12 175 0.6× 54 0.4× 77 1.8× 58 2.5× 29 1.3× 17 305
V. Kamakshi Prasad India 10 163 0.5× 111 0.8× 98 2.3× 34 1.5× 30 1.4× 56 315

Countries citing papers authored by Kazuki Irie

Since Specialization
Citations

This map shows the geographic impact of Kazuki Irie'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 Kazuki Irie with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Kazuki Irie more than expected).

Fields of papers citing papers by Kazuki Irie

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Kazuki Irie. 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 Kazuki Irie. The network helps show where Kazuki Irie may publish in the future.

Co-authorship network of co-authors of Kazuki Irie

This figure shows the co-authorship network connecting the top 25 collaborators of Kazuki Irie. A scholar is included among the top collaborators of Kazuki Irie 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 Kazuki Irie. Kazuki Irie is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Gershman, Samuel J., Ila Fiete, & Kazuki Irie. (2025). Key-value memory in the brain. Neuron. 113(11). 1694–1707.e1. 2 indexed citations
2.
Irie, Kazuki & Brenden M. Lake. (2025). Overcoming classic challenges for artificial neural networks by providing incentives and practice. Nature Machine Intelligence. 7(10). 1602–1611.
3.
Irie, Kazuki, et al.. (2024). MoEUT: Mixture-of-Experts Universal Transformers. 28589–28614. 1 indexed citations
4.
Irie, Kazuki, et al.. (2023). Unsupervised Learning of Temporal Abstractions With Slot-Based Transformers. Neural Computation. 35(4). 593–626. 1 indexed citations
5.
Irie, Kazuki, et al.. (2023). Approximating Two-Layer Feedforward Networks for Efficient Transformers. 674–692. 2 indexed citations
6.
7.
8.
Irie, Kazuki, et al.. (2021). Going Beyond Linear Transformers with Recurrent Fast Weight Programmers. arXiv (Cornell University). 1 indexed citations
9.
Irie, Kazuki. (2020). Fortschritte bei der neuronalen Sprachmodellierung in der automatischen Spracherkennung. RWTH Publications (RWTH Aachen). 5 indexed citations
10.
Irie, Kazuki, et al.. (2020). Domain Robust, Fast, and Compact Neural Language Models. 27. 7954–7958. 2 indexed citations
11.
Zhou, Wei, et al.. (2020). The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment. 7839–7843. 23 indexed citations
12.
Irie, Kazuki, et al.. (2020). How Much Self-Attention Do We Needƒ Trading Attention for Feed-Forward Layers. 45. 6154–6158. 1 indexed citations
13.
Irie, Kazuki, Rohit Prabhavalkar, Anjuli Kannan, et al.. (2019). Model Unit Exploration for Sequence-to-Sequence Speech Recognition.. arXiv (Cornell University). 5 indexed citations
14.
Irie, Kazuki, Albert Zeyer, Ralf Schlüter, & Hermann Ney. (2019). Training Language Models for Long-Span Cross-Sentence Evaluation. 419–426. 21 indexed citations
15.
16.
Irie, Kazuki, Zoltán Tüske, Tamer Alkhouli, Ralf Schlüter, & Hermann Ney. (2016). LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition. 3519–3523. 58 indexed citations
17.
Tüske, Zoltán, Kazuki Irie, Ralf Schlüter, & Hermann Ney. (2016). Investigation on log-linear interpolation of multi-domain neural network language model. 268. 6005–6009. 9 indexed citations
18.
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
19.
20.
Wiesler, Simon, Kazuki Irie, Zoltán Tüske, Ralf Schlüter, & Hermann Ney. (2014). The RWTH English lecture recognition system. 3286–3290. 2 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

Breakdown of academic impact, for papers by Albert Zeyer Breakdown of academic impact, for papers by Matthew Middlehurst Breakdown of academic impact, for papers by Tianmeng Yang Breakdown of academic impact, for papers by Zhihan Yue Breakdown of academic impact, for papers by Mohammad Shokoohi-Yekta Breakdown of academic impact, for papers by Philémon Brakel Breakdown of academic impact, for papers by Ziheng Duan Breakdown of academic impact, for papers by Yuchen Fan Breakdown of academic impact, for papers by Vassilios Petridis Breakdown of academic impact, for papers by V. Kamakshi Prasad
Rankless by CCL
2026