Hirofumi Inaguma

2.1k total citations · 1 hit paper
35 papers, 1.0k citations indexed

About

Hirofumi Inaguma is a scholar working on Artificial Intelligence, Signal Processing and Infectious Diseases. According to data from OpenAlex, Hirofumi Inaguma has authored 35 papers receiving a total of 1.0k indexed citations (citations by other indexed papers that have themselves been cited), including 34 papers in Artificial Intelligence, 10 papers in Signal Processing and 0 papers in Infectious Diseases. Recurrent topics in Hirofumi Inaguma's work include Speech Recognition and Synthesis (28 papers), Natural Language Processing Techniques (26 papers) and Topic Modeling (19 papers). Hirofumi Inaguma is often cited by papers focused on Speech Recognition and Synthesis (28 papers), Natural Language Processing Techniques (26 papers) and Topic Modeling (19 papers). Hirofumi Inaguma collaborates with scholars based in Japan, United States and France. Hirofumi Inaguma's co-authors include Shinji Watanabe, Tatsuya Kawahara, Tomoki Hayashi, Wangyou Zhang, Nanxin Chen, Takaaki Hori, Shigeki Karita, Xiaofei Wang, Takenori Yoshimura and Ziyan Jiang and has published in prestigious journals such as IEEE/ACM Transactions on Audio Speech and Language Processing, arXiv (Cornell University) and Interspeech 2022.

In The Last Decade

Hirofumi Inaguma

35 papers receiving 969 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.

A Comparative Study on Transformer vs RNN in Speech Applications

2019 439 citations Shigeki Karita, Nanxin Chen et al. arXiv (Cornell University) profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Hirofumi Inaguma Japan	15	913	519	81	41	21	35	1.0k
Wangyou Zhang China	14	830 0.9×	693 1.3×	54 0.7×	29 0.7×	23 1.1×	43	1.0k
Shinnosuke Takamichi Japan	16	756 0.8×	682 1.3×	115 1.4×	64 1.6×	11 0.5×	116	978
Yanzhang He United States	15	829 0.9×	574 1.1×	71 0.9×	20 0.5×	30 1.4×	42	936
Suyoun Kim United States	12	1.1k 1.2×	804 1.5×	103 1.3×	48 1.2×	15 0.7×	24	1.3k
Thomas Fang Zheng China	16	813 0.9×	608 1.2×	97 1.2×	63 1.5×	37 1.8×	102	972
Xiaofei Wang China	11	579 0.6×	384 0.7×	73 0.9×	19 0.5×	13 0.6×	41	781
Vimal Manohar United States	15	1.0k 1.1×	749 1.4×	49 0.6×	48 1.2×	9 0.4×	28	1.1k
Tsubasa Ochiai Japan	7	897 1.0×	681 1.3×	71 0.9×	45 1.1×	5 0.2×	11	1.0k
J. McDonough Germany	13	655 0.7×	556 1.1×	69 0.9×	48 1.2×	9 0.4×	24	767
Shigeki Karita Japan	13	1.5k 1.7×	1.1k 2.1×	116 1.4×	72 1.8×	18 0.9×	26	1.8k

Countries citing papers authored by Hirofumi Inaguma

Since Specialization

Citations

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

Fields of papers citing papers by Hirofumi Inaguma

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Hirofumi Inaguma

This figure shows the co-authorship network connecting the top 25 collaborators of Hirofumi Inaguma. A scholar is included among the top collaborators of Hirofumi Inaguma 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 Hirofumi Inaguma. Hirofumi Inaguma 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.

Yan, Brian, Yun Tang, Hirofumi Inaguma, et al.. (2023). ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit. 400–411. 11 indexed citations

2.

Tang, Yun, et al.. (2023). Exploration on HuBERT with Multiple Resolution. 3287–3291. 1 indexed citations

3.

Wang, Changhan, Hirofumi Inaguma, Peng‐Jen Chen, et al.. (2023). Simple and Effective Unsupervised Speech Translation. 10771–10784. 9 indexed citations

4.

Inaguma, Hirofumi, Ilia Kulikov, Peng‐Jen Chen, et al.. (2023). UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units. 15655–15680. 18 indexed citations

5.

Tang, Yun, Anna Sun, Hirofumi Inaguma, et al.. (2023). Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks. 12441–12455. 4 indexed citations

6.

Chen, Peng‐Jen, Kevin Tran, Yilin Yang, et al.. (2023). Speech-to-Speech Translation for a Real-world Unwritten Language. 4969–4983. 12 indexed citations

7.

Tang, Yun, et al.. (2023). Named Entity Detection and Injection for Direct Speech Translation. 1–5. 1 indexed citations

8.

Shinohara, Yusuke, et al.. (2021). A Study of Transducer Based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies. 15 indexed citations

9.

Inaguma, Hirofumi, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, & Shinji Watanabe. (2021). ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder. 7503–7507. 13 indexed citations

10.

Inaguma, Hirofumi & Tatsuya Kawahara. (2021). Alignment Knowledge Distillation for Online Streaming Attention-Based Speech Recognition. IEEE/ACM Transactions on Audio Speech and Language Processing. 31. 1371–1385. 6 indexed citations

11.

Inaguma, Hirofumi, et al.. (2021). Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates. 922–929. 11 indexed citations

12.

Inaguma, Hirofumi, Tatsuya Kawahara, & Shinji Watanabe. (2021). Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation. 1872–1881. 26 indexed citations

13.

Guo, Pengcheng, Xuankai Chang, Tomoki Hayashi, et al.. (2021). Recent Developments on Espnet Toolkit Boosted By Conformer. 5874–5878. 149 indexed citations

14.

Inaguma, Hirofumi, et al.. (2021). ASR Rescoring and Confidence Estimation with Electra. 380–387. 6 indexed citations

15.

Zhao, Tianyu, et al.. (2020). End-to-End Speech-to-Dialog-Act Recognition. 3910–3914. 3 indexed citations

16.

Inaguma, Hirofumi, Jaejin Cho, Murali Karthick Baskar, Tatsuya Kawahara, & Shinji Watanabe. (2019). Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion. 6096–6100. 26 indexed citations

17.

Karita, Shigeki, Nanxin Chen, Tomoki Hayashi, et al.. (2019). A Comparative Study on Transformer vs RNN in Speech Applications. arXiv (Cornell University). 449–456. 439 indexed citations breakdown →

18.

Cho, Jaejin, Shinji Watanabe, Takaaki Hori, et al.. (2019). Language Model Integration Based on Memory Control for Sequence to Sequence Speech Recognition. 6191–6195. 1 indexed citations

19.

Inaguma, Hirofumi, Masato Mimura, Shinsuke Sakai, & Tatsuya Kawahara. (2018). Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR. 212–218. 4 indexed citations

20.

Inaguma, Hirofumi, Koji Inoue, Masato Mimura, & Tatsuya Kawahara. (2017). Social Signal Detection in Spontaneous Dialogue Using Bidirectional LSTM-CTC. 1691–1695. 12 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