Tsubasa Ochiai

1.4k total citations
58 papers, 854 citations indexed

About

Tsubasa Ochiai is a scholar working on Signal Processing, Artificial Intelligence and Computational Mechanics. According to data from OpenAlex, Tsubasa Ochiai has authored 58 papers receiving a total of 854 indexed citations (citations by other indexed papers that have themselves been cited), including 51 papers in Signal Processing, 42 papers in Artificial Intelligence and 10 papers in Computational Mechanics. Recurrent topics in Tsubasa Ochiai's work include Speech and Audio Processing (50 papers), Speech Recognition and Synthesis (40 papers) and Music and Audio Processing (31 papers). Tsubasa Ochiai is often cited by papers focused on Speech and Audio Processing (50 papers), Speech Recognition and Synthesis (40 papers) and Music and Audio Processing (31 papers). Tsubasa Ochiai collaborates with scholars based in Japan, Czechia and United States. Tsubasa Ochiai's co-authors include Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Kateřina Žmolíková, Jaň Černocký, Lukáš Burget, Rintaro Ikeshita, Shigeru Katagiri and Naohiro Tawara and has published in prestigious journals such as IEEE Access, IEEE Signal Processing Magazine and IEEE Journal of Selected Topics in Signal Processing.

In The Last Decade

Tsubasa Ochiai

49 papers receiving 815 citations

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Tsubasa Ochiai Japan 16 784 667 96 44 39 58 854
Yihui Fu China 7 565 0.7× 420 0.6× 207 2.2× 78 1.8× 46 1.2× 12 626
Tsubasa Ochiai Japan 7 681 0.9× 897 1.3× 51 0.5× 16 0.4× 71 1.8× 11 1.0k
Jeih-weih Hung Taiwan 12 464 0.6× 361 0.5× 106 1.1× 35 0.8× 76 1.9× 88 556
Shubo Lv China 5 552 0.7× 386 0.6× 221 2.3× 85 1.9× 45 1.2× 9 597
Mengtao Xing China 2 430 0.5× 292 0.4× 173 1.8× 70 1.6× 37 0.9× 2 467
Yan-Hui Tu China 12 414 0.5× 270 0.4× 121 1.3× 45 1.0× 26 0.7× 29 497
Cheng Yu Taiwan 6 333 0.4× 232 0.3× 77 0.8× 49 1.1× 34 0.9× 12 372
Chengzhu Yu United States 16 633 0.8× 597 0.9× 64 0.7× 35 0.8× 66 1.7× 36 759
Antti Hurmalainen Finland 11 428 0.5× 274 0.4× 84 0.9× 18 0.4× 53 1.4× 23 471
Aditya Arie Nugraha Japan 10 617 0.8× 301 0.5× 206 2.1× 46 1.0× 44 1.1× 31 676

Countries citing papers authored by Tsubasa Ochiai

Since Specialization
Citations

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

Fields of papers citing papers by Tsubasa Ochiai

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Tsubasa Ochiai

This figure shows the co-authorship network connecting the top 25 collaborators of Tsubasa Ochiai. A scholar is included among the top collaborators of Tsubasa Ochiai 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 Tsubasa Ochiai. Tsubasa Ochiai 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.
Delcroix, Marc, et al.. (2025). SoundBeam meets M2D: Target Sound Extraction with Audio Foundation Model. 1–5. 2 indexed citations
2.
Kamo, Naoyuki, Naohiro Tawara, Hiroshi Satō, et al.. (2025). Microphone array geometry-independent multi-talker distant ASR: NTT system for DASR task of the CHiME-8 challenge. Computer Speech & Language. 95. 101820–101820.
3.
Ochiai, Tsubasa, Marc Delcroix, Takafumi Moriya, et al.. (2025). Target sound information extraction: Speech and audio processing with neural networks conditioned on target clues. Nippon Onkyo Gakkaishi/Acoustical science and technology/Nihon Onkyo Gakkaishi. 46(3). 197–209.
4.
Ochiai, Tsubasa, Marc Delcroix, Tomohiro Nakatani, & Shoko Araki. (2025). AI-powered Beamforming for Listening to Moving Talkers. NTT technical review. 23(1). 50–55.
5.
Delcroix, Marc, et al.. (2024). Probing Self-Supervised Learning Models With Target Speech Extraction. 535–539. 1 indexed citations
6.
Ochiai, Tsubasa, Marc Delcroix, Rintaro Ikeshita, et al.. (2024). Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance. IEEE/ACM Transactions on Audio Speech and Language Processing. 32. 3589–3602. 4 indexed citations
7.
Ochiai, Tsubasa, Marc Delcroix, Masahiro Yasuda, et al.. (2024). Online Target Sound Extraction with Knowledge Distillation from Partially Non-Causal Teacher. 561–565. 1 indexed citations
8.
Chang, Xuankai, Shinji Watanabe, Marc Delcroix, et al.. (2024). Module-Based End-to-End Distant Speech Processing: A case study of far-field automatic speech recognition. IEEE Signal Processing Magazine. 41(6). 39–50.
9.
Kamo, Naoyuki, Naohiro Tawara, Kohei Matsuura, et al.. (2023). NTT Multi-Speaker ASR System for the DASR Task of CHiME-7 Challenge. 45–50. 4 indexed citations
10.
Delcroix, Marc, et al.. (2022). SoundBeam: Target Sound Extraction Conditioned on Sound-Class Labels and Enrollment Clues for Increased Performance and Continuous Learning. IEEE/ACM Transactions on Audio Speech and Language Processing. 31. 121–136. 21 indexed citations
11.
Sato, Hiroshi, Tsubasa Ochiai, Marc Delcroix, et al.. (2022). Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6287–6291. 13 indexed citations
12.
Zhang, Wangyou, Christoph Boeddeker, Shinji Watanabe, et al.. (2021). End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend. arXiv (Cornell University). 23 indexed citations
13.
Delcroix, Marc, Tsubasa Ochiai, Hiroshi Satō, et al.. (2021). Developing AI that Pays Attention to Who You Want to Listen to: Deep-learning-based Selective Hearing with SpeakerBeam. NTT technical review. 19(9). 39–45.
14.
Satō, Hiroshi, Tsubasa Ochiai, Keisuke Kinoshita, et al.. (2021). Multimodal Attention Fusion for Target Speaker Extraction. 16 indexed citations
15.
Satō, Hiroshi, Tsubasa Ochiai, Marc Delcroix, et al.. (2021). Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition. arXiv (Cornell University). 13 indexed citations
16.
Ochiai, Tsubasa, Marc Delcroix, Rintaro Ikeshita, et al.. (2020). Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer. 6384–6388. 52 indexed citations
17.
Nakatani, Tomohiro, Tsubasa Ochiai, Keisuke Kinoshita, et al.. (2020). DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation. 6399–6403. 15 indexed citations
18.
Ochiai, Tsubasa, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, & Tomohiro Nakatani. (2019). Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues. 2718–2722. 33 indexed citations
19.
Ochiai, Tsubasa, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, & Tomohiro Nakatani. (2019). A Unified Framework for Neural Speech Separation and Extraction. 6975–6979. 11 indexed citations
20.
Delcroix, Marc, Kateřina Žmolíková, Tsubasa Ochiai, et al.. (2019). Compact Network for Speakerbeam Target Speaker Extraction. 6965–6969. 30 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 Yihui Fu Breakdown of academic impact, for papers by Tsubasa Ochiai Breakdown of academic impact, for papers by Jeih-weih Hung Breakdown of academic impact, for papers by Shubo Lv Breakdown of academic impact, for papers by Mengtao Xing Breakdown of academic impact, for papers by Yan-Hui Tu Breakdown of academic impact, for papers by Cheng Yu Breakdown of academic impact, for papers by Chengzhu Yu Breakdown of academic impact, for papers by Antti Hurmalainen Breakdown of academic impact, for papers by Aditya Arie Nugraha
Rankless by CCL
2026