Publications

Refereed Journal Articles

1. Rintaro Ikeshita and Tomohiro Nakatani.
   Geometrically-Regularized Fast Independent Vector Extraction by Pure Majorization-Minimization.
   IEEE Transactions on Signal Processing, 2024.
2. Tetsuya Ueda, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki, and Shoji Makino.
   Blind and Spatially-Regularized Online Joint Optimization of Source Separation, Dereverberation, and Noise Reduction.
   IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024.
3. Hiroshi Sawada, Rintaro Ikeshita, Keisuke Kinoshita, and Tomohiro Nakatani.
   Multi-frame Full-rank Spatial Covariance Analysis for Underdetermined Blind Source Separation and Dereverberation.
   IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023.
4. Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Hiroshi Sawada, Naoyuki Kamo, and Shoko Araki.
   Switching Independent Vector Analysis and Its Extension to Blind and Spatially Guided Convolutional Beamforming Algorithms.
   IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022.
5. Nobutaka Ito, Rintaro Ikeshita, Hiroshi Sawada, and Tomohiro Nakatani.
   A Joint Diagonalization Based Efficient Approach to Underdetermined Blind Audio Source Separation Using the Multichannel Wiener Filter.
   IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021.
6. Rintaro Ikeshita, Tomohiro Nakatani, and Shoko Araki.
   Block Coordinate Descent Algorithms for Auxiliary-Function-Based Independent Vector Extraction.
   IEEE Transactions on Signal Processing, 2021.
7. Rintaro Ikeshita and Tomohiro Nakatani.
   Independent Vector Extraction for Fast Joint Blind Source Separation and Dereverberation.
   IEEE Signal Processing Letters, 2021.
8. Rintaro Ikeshita, Keisuke Kinoshita, Naoyuki Kamo, and Tomohiro Nakatani.
   Online Speech Dereverberation Using Mixture of Multichannel Linear Prediction Models.
   IEEE Signal Processing Letters, 2021.
9. Rintaro Ikeshita, Naoyuki Kamo, and Tomohiro Nakatani.
   Blind Signal Dereverberation Based on Mixture of Weighted Prediction Error Models.
   IEEE Signal Processing Letters, 2021.
10. Tomohiro Nakatani, Christoph Böddeker, Keisuke Kinoshita, Rintaro Ikeshita, Marc Delcroix, and Reinhold Haeb-Umbach.
    Jointly Optimal Denoising, Dereverberation, and Source Separation.
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020.
11. Kazuaki Shima, Takeshi Homma, Masataka Motohashi, Rintaro Ikeshita, Hiroaki Kokubo, Yasunari Obuchi, Jinhua She.
    Efficient Corpus Creation Method for NLU Using Interview with Probing Questions.
    Journal of Advanced Computational Intelligence and Intelligent Informatics, 2019.
12. Takeshi Homma, Yasunari Obuchi, Kazuaki Shima, Rintaro Ikeshita, Hiroaki Kokubo, and Takuya Matsumoto.
    In-Vehicle Voice Interface with Improved Utterance Classification Accuracy Using Off-the-Shelf Cloud Speech Recognizer.
    IEICE Transactions on Information and Systems, 2018.
13. Rintaro Ikeshita and Shin-ichi Tanigawa.
    Count Matroids of Group-Labeled Graphs.
    Combinatorica 38, 1101–1127 (2018).

Refereed Conference Proceedings

2024

1. Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, and Shigeru Katagiri. How Does End-to-End Speech Recognition Training Impact Speech Enhancement Artifacts?. ICASSP 2024.
2. Hanako Segawa, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Shoko Araki, Takeshi Yamada, and Shoji Makino. Neural Network-Based Virtual Microphone Estimation with Virtual Microphone and Beamformer-Level Multi-Task Loss. ICASSP 2024.

2023

3. Taishi Nakashima, Rintaro Ikeshita, Nobutaka Ono, Shoko Araki, and Tomohiro Nakatani. Fast Online Source Steering Algorithm for Tracking Single Moving Source Using Online Independent Vector Analysis. ICASSP 2023.
4. Koki Nishida, Norihiro Takamune, Rintaro Ikeshita, Daichi Kitamura, Hiroshi Saruwatari, Tomohiro Nakatani. NoisyILRMA: Diffuse-Noise-Aware Independent Low-Rank Matrix Analysis for Fast Blind Source Extraction. EUSIPCO 2023.
5. Tetsuya Ueda, Tomohiro Nakatani, Rintaro Ikeshita, Shoko Araki, and Shoji Makino. Spatially-Regularized Switching Independent Vector Analysis. APSIPA 2023.

2022

6. Hiroshi Sawada, Rintaro Ikeshita, Keisuke Kinoshita, and Tomohiro Nakatani. Multi-Frame Full-Rank Spatial Covariance Analysis for Underdetermined BSS in Reverberant Environments. ICASSP 2022.
7. Naoyuki Kamo, Rintaro Ikeshita, Keisuke Kinoshita, and Tomohiro Nakatani. Importance of Switch Optimization Criterion in Switching WPE Dereverberation. ICASSP 2022.
8. Rintaro Ikeshita and Tomohiro Nakatani. ISS2: An Extension of Iterative Source Steering Algorithm for Majorization-Minimization-Based Independent Vector Analysis. EUSIPCO 2022.
9. Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, and Shigeru Katagiri. How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR. Interspeech 2022.
10. Hanako Segawa, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Shoko Araki, Takeshi Yamada, and Shoji Makino. Neural Virtual Microphone Estimator: Application to Multi-Talker Reverberant Mixtures. APSIPA 2022.

2021

11. Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Hiroshi Sawada, and Shoko Araki. Blind and Neural Network-Guided Convolutional Beamformer for Joint Denoising, Dereverberation, and Source Separation. ICASSP 2021.
12. Tetsuya Ueda, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki, and Shoji Makino. Low Latency Online Blind Source Separation Based on Joint Optimization with Blind Dereverberation. ICASSP 2021.
13. Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, and Shoko Araki. Neural Network-based Virtual Microphone Estimator. ICASSP 2021.
14. Tomohiro Nakatani, Rintaro Ikeshita, Naoyuki Kamo, Keisuke Kinoshita, Shoko Araki, and Hiroshi Sawada. Switching Convolutional Beamformer. EUSIPCO 2021.
15. Tetsuya Ueda, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki, and Shoji Makino. Low Latency Online Source Separation and Noise Reduction Based on Joint Optimization with Dereverberation. EUSIPCO 2021.
16. Naoki Narisawa, Rintaro Ikeshita, Norihiro Takamune, Daichi Kitamura, Tomohiro Nakamura, Hiroshi Saruwatari, and Tomohiro Nakatani. Independent Deeply Learned Tensor Analysis for Determined Audio Source Separation. EUSIPCO 2021.

2020

17. Rintaro Ikeshita, Tomohiro Nakatani, and Shoko Araki. Overdetermined Independent Vector Analysis. ICASSP 2020.
18. Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Keisuke Kinoshita, Tomohiro Nakatani, and Shoko Araki. Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer. ICASSP 2020.
19. Tomohiro Nakatani, Riki Takahashi, Tsubasa Ochiai, Keisuke Kinoshita, Rintaro Ikeshita, Marc Delcroix, and Shoko Araki. DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation. ICASSP 2020.
20. Tatsuki Kondo, Kanta Fukushige, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, and Tomohiro Nakatani. Convergence-guaranteed Independent Positive Semidefinite Tensor Analysis Based on Student's t Distribution. ICASSP 2020.
21. Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Hiroshi Sawada, and Shoko Araki. Computationally Efficient and Versatile Framework for Joint Optimization of Blind Speech Separation and Dereverberation. Interspeech 2020.
22. Hiroshi Sawada, Rintaro Ikeshita, and Tomohiro Nakatani. Experimental Analysis of EM and MU Algorithms for Optimizing Full-rank Spatial Covariance Model. EUSIPCO 2020.

2019

23. Naoyuki Kanda, Yusuke Fujita, Shota Horiguchi, Rintaro Ikeshita, Kenji Nagamatsu, and Shinji Watanabe. Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches. ICASSP 2019.
24. Rintaro Ikeshita, Nobutaka Ito, Tomohiro Nakatani, and Hiroshi Sawada. Independent Low-Rank Matrix Analysis with Decorrelation Learning. WASPAA 2019.
25. Tomohiro Nakatani, Keisuke Kinoshita, Rintaro Ikeshita, Hiroshi Sawada, and Shoko Araki. Simultaneous Denoising, Dereverberation, and Source Separation Using a Unified Convolutional Beamformer. WASPAA 2019.
26. Hiroshi Sawada, Rintaro Ikeshita, Nobutaka Ito, and Tomohiro Nakatani. Computational Acceleration and Smart Initialization of Full-rank Spatial Covariance Analysis. EUSIPCO 2019.
27. Rintaro Ikeshita, Nobutaka Ito, Tomohiro Nakatani, and Hiroshi Sawada. A Unifying Framework for Blind Source Separation Based on A Joint Diagonalizability Constraint. EUSIPCO 2019.

2018

28. Rintaro Ikeshita and Yohei Kawaguchi. Independent Low-rank Matrix Analysis Based on Multivariate Complex Exponential Power Distribution. ICASSP 2018.
29. Rintaro Ikeshita. Independent Positive Semidefinite Tensor Analysis in Blind Source Separation. EUSIPCO 2018.
30. Rintaro Ikeshita, Yohei Kawaguchi, and Kenji Nagamatsu. Fast Multichannel Nonnegative Matrix Factorization with Constraints on Active Source Candidates. IWAENC 2018.

2017

31. Rintaro Ikeshita, Masahito Togami, Yohei Kawaguchi, Yusuke Fujita, and Kenji Nagamatsu. Local Gaussian Model with Source-Set Constraints in Audio Source Separation. MLSP 2017.
32. Rintaro Ikeshita, Yohei Kawaguchi, Masahito Togami, Yusuke Fujita, and Kenji Nagamatsu. Independent Vector Analysis with Frequency Range Division and Prior Switching. EUSIPCO 2017.
33. Yohei Kawaguchi, Sandra Ramaswami, Ryoichi Takashima, Takashi Endo, and Rintaro Ikeshita. Sub-Nyquist Non-uniform Sampling for Low-cost Sound Monitoring. APSIPA 2017.

2015

34. Yusuke Fujita, Ryoichi Takashima, Takeshi Homma, Rintaro Ikeshita, Yohei Kawaguchi, Takashi Sumiyoshi, Takashi Endo, and Masahito Togami. Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection. ASRU 2015.

Non-Refereed Conference Proceedings

1. Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Hiroshi Sawada, Naoyuki Kamo, and Shoko Araki. Switching independent vector extraction and its joint optimization with weighted prediction error dereverberation. The 24th International Congress on Acoustics (ICA), 2022.
2. Hiroshi Sawada, Rintaro Ikeshita, Keisuke Kinoshita, and Tomohiro Nakatani. Evaluating the dereverberation-separation capability of multi-frame full-rank spatial covariance analysis. The 24th International Congress on Acoustics (ICA), 2022.

CHiME Speech Separation and Recognition Challenges

CHiME-7 (2023)

• Ranked 3rd place in CHiME-7 Task 1
• Team: NTT
• Team members: Naoyuki Kamo; Naohiro Tawara; Kohei Matsuura; Takanori Ashihara; Takafumi Moriya; Atsunori Ogawa; Hiroshi Sato; Tsubasa Ochiai; Atsushi Ando; Rintaro Ikeshita; Takatomo Kano; Marc Delcroix; Tomohiro Nakatani; Taichi Asami; Shoko Araki

CHiME-5 (2018)

• Ranked 2nd place in CHiME-5
• Team: Hitachi–JHU
• Team members: Naoyuki Kanda; Rintaro Ikeshita; Shota Horiguchi; Yusuke Fujita; Kenji Nagamatsu; Xiaofei Wang; Vimal Manohar; Nelson Enrique Yalta Soplin; Matthew Maciejewski; Szu-Jui Chen; Aswin Shanmugam Subramanian; Ruizhi Li; Zhiqi Wang; Jason Naradowsky; L. Paola Garcia-Perera; Gregory Sell

CHiME-3 (2015)

• Ranked 6th place in CHiME-3
• Team: Hitachi R&D
• Team members: Yusuke Fujita; Ryoichi Takashima; Takeshi Homma; Rintaro Ikeshita; Yohei Kawaguchi; Takashi Sumiyoshi; Takashi Endo; Masahito Togami

Theses

Master (2015)

• Department of Mathematical Informatics, Graduate School of Information Science and Technology, University of Tokyo, Japan
• Thesis: Infinitesimal Rigidity of Symmetric Frameworks (GoogleScholar)
• Supervisor: Prof. Kazuo Murota

Bachelor (2013)

• Department of Mathematical Engineering and Information Physics, University of Tokyo, Japan
• Thesis: 群論を用いた対称性をもつメカニズムの分岐解析 (in Japanese)
• Supervisor: Prof. Yoshihiro Kanno