World's Best Scientists 2026 revealed!
Keisuke Kinoshita

Keisuke Kinoshita

D-Index & Metrics

Computer Science

D-Index
42
Citations
7205
World Ranking
8416
National Ranking
113

Overview

Keisuke Kinoshita is a researcher affiliated with NTT in Japan, specializing in computer science with a focus on signal processing and artificial intelligence. Their research contributions span multiple subfields including signal processing, computational mechanics, cognitive neuroscience, and mechanical engineering.

The scientist's principal topics of work include:

  • Speech and Audio Processing
  • Speech Recognition and Synthesis
  • Music and Audio Processing
  • Advanced Adaptive Filtering Techniques
  • Hearing Loss and Rehabilitation
  • Blind Source Separation Techniques
  • Microstructure and Mechanical Properties of Steels

Keisuke Kinoshita's recent publications profile includes:

  • "Neural Target Speech Extraction: An overview", 2023, IEEE Signal Processing Magazine
  • "End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend", 2021, arXiv (Cornell University)
  • "SoundBeam: Target Sound Extraction Conditioned on Sound-Class Labels and Enrollment Clues for Increased Performance and Continuous Learning", 2022, IEEE/ACM Transactions on Audio Speech and Language Processing
  • "Changes in States of Carbon and Mechanical Properties with Aging at 50°C after Quenching in Low Carbon Steel", 2020, MATERIALS TRANSACTIONS
  • "Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition", 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

The researcher's frequent co-authors include:

  • Marc Delcroix
  • Tomohiro Nakatani
  • Shoko Araki
  • Tsubasa Ochiai
  • Naoyuki Kamo

Keisuke Kinoshita has published extensively in venues such as:

  • arXiv (Cornell University)
  • IEEE/ACM Transactions on Audio Speech and Language Processing
  • ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Interspeech 2022
  • 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

The scientist's work combines elements from signal processing and artificial intelligence to address challenges in speech and audio technologies. Their research covers advanced filtering techniques and addresses practical issues such as speech enhancement, dereverberation, and beamforming.

In addition to audio and speech processing, Keisuke Kinoshita has contributed research to understanding the microstructure and mechanical properties of steels, highlighting interdisciplinary engagement with computational mechanics and materials science.

Best Publications

  • Speech Dereverberation Based on Variance-Normalized Delayed Linear Prediction

    Tomohiro Nakatani;Takuya Yoshioka;Keisuke Kinoshita;Masato Miyoshi

  • The reverb challenge: Acommon evaluation framework for dereverberation and recognition of reverberant speech

    Keisuke Kinoshita;Marc Delcroix;Takuya Yoshioka;Tomohiro Nakatani

  • A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

    Keisuke Kinoshita;Marc Delcroix;Sharon Gannot;Emanuël A. P. Habets

  • Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition

    Takuya Yoshioka;A. Sehr;M. Delcroix;K. Kinoshita

  • The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices

    Takuya Yoshioka;Nobutaka Ito;Marc Delcroix;Atsunori Ogawa

  • Suppression of Late Reverberation Effect on Speech Signal Using Long-Term Multiple-step Linear Prediction

    K. Kinoshita;M. Delcroix;T. Nakatani;M. Miyoshi

  • SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures

    Katerina Zmolikova;Marc Delcroix;Keisuke Kinoshita;Tsubasa Ochiai

  • Single Channel Target Speaker Extraction and Recognition with Speaker Beam

    Marc Delcroix;Katerina Zmolikova;Keisuke Kinoshita;Atsunori Ogawa

  • Blind speech dereverberation with multi-channel linear prediction based on short time fourier transform representation

    T. Nakatani;T. Yoshioka;K. Kinoshita;M. Miyoshi

  • Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures.

    Kateřina Žmolíková;Marc Delcroix;Keisuke Kinoshita;Takuya Higuchi

  • A Multichannel MMSE-Based Framework for Speech Source Separation and Noise Reduction

    Mehrez Souden;Shoko Araki;Keisuke Kinoshita;Tomohiro Nakatani

  • Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam

    Marc Delcroix;Tsubasa Ochiai;Katerina Zmolikova;Keisuke Kinoshita

  • Low-Latency Real-Time Meeting Recognition and Understanding Using Distant Microphones and Omni-Directional Camera

    T. Hori;S. Araki;T. Yoshioka;M. Fujimoto

  • Exploiting spectro-temporal locality in deep learning based acoustic event detection

    Miquel Espi;Masakiyo Fujimoto;Keisuke Kinoshita;Tomohiro Nakatani

  • Neural Network-Based Spectrum Estimation for Online WPE Dereverberation.

    Keisuke Kinoshita;Marc Delcroix;Haeyong Kwon;Takuma Mori

  • Neural Target Speech Extraction: An overview

    Unknown

  • Improving Noise Robust Automatic Speech Recognition with Single-Channel Time-Domain Enhancement Network

    Keisuke Kinoshita;Tsubasa Ochiai;Marc Delcroix;Tomohiro Nakatani

  • All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis

    Thilo von Neumann;Keisuke Kinoshita;Marc Delcroix;Shoko Araki

  • Harmonicity-Based Blind Dereverberation for Single-Channel Speech Signals

    T. Nakatani;K. Kinoshita;M. Miyoshi

  • A Unified Convolutional Beamformer for Simultaneous Denoising and Dereverberation

    Tomohiro Nakatani;Keisuke Kinoshita

  • Spectral Subtraction Steered by Multi-Step Forward Linear Prediction For Single Channel Speech Dereverberation

    K. Kinoshita;T. Nakatani;M. Miyoshi

  • Listening to Each Speaker One by One with Recurrent Selective Hearing Networks

    Keisuke Kinoshita;Lukas Drude;Marc Delcroix;Tomohiro Nakatani

Frequent Co-Authors

Marc Delcroix
Marc Delcroix NTT (Japan)
Shoko Araki
Shoko Araki NTT (Japan)
Takuya Yoshioka
Takuya Yoshioka Microsoft (United States)
Reinhold Haeb-Umbach
Reinhold Haeb-Umbach University of Paderborn
Walter Kellermann
Walter Kellermann University of Erlangen-Nuremberg
Shinji Watanabe
Shinji Watanabe Carnegie Mellon University
Hiroshi Sawada
Hiroshi Sawada NTT (Japan)
Yanmin Qian
Yanmin Qian Shanghai Jiao Tong University
Nobutaka Ono
Nobutaka Ono Tokyo Metropolitan University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online degrees offers flexibility for students from various backgrounds. If affordability is a priority, consider the cheapest online colleges, which can help you achieve your goals without financial strain.

Not everyone starts their academic journey with a high GPA. Fortunately, there are excellent online schools that accept low gpa, providing opportunities for motivated students to pursue a computer science degree.

Graduates in computer science can explore a variety of tech careers, but interdisciplinary possibilities exist as well. Learn about jobs with elementary education and environmental science degree—ideal for those considering a shift between tech, education, or environmental sectors.

Students seeking to fast-track their education can benefit from accelerated computer science degree online programs. These pathways make it possible to earn your degree and enter the workforce sooner.

Best Scientists Citing Keisuke Kinoshita

Trending Scientists