World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
45
Citations
10359
World Ranking
7106
National Ranking
3117

Overview

Takuya Yoshioka is affiliated with Microsoft in the United States and has a significant body of research in computer science, focusing on signal processing and artificial intelligence. Their work largely concentrates on speech recognition, synthesis, and audio processing technologies.

The scientist has published extensively with 209 works in the field of computer science. Key subfields of study include signal processing, artificial intelligence, computer vision and pattern recognition, electrical and electronic engineering, and computational mechanics.

Their main research topics cover a range of speech and audio-related areas:

  • Speech Recognition and Synthesis
  • Speech and Audio Processing
  • Music and Audio Processing
  • Indoor and Outdoor Localization Technologies
  • Advanced Adaptive Filtering Techniques
  • Multimodal Machine Learning Applications
  • Speech and dialogue systems

Yoshioka has contributed to multiple publications in notable venues, emphasizing peer-reviewed conferences and journals:

  • arXiv (Cornell University)
  • ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Interspeech 2022
  • Zenodo (CERN European Organization for Nuclear Research)
  • IEEE Journal of Selected Topics in Signal Processing

Frequent collaborators include researchers such as Naoyuki Kanda, Zhuo Chen, Jinyu Li, Şefik Emre Eskimez, and Zhong Meng, reflecting a broad network within speech and audio processing research communities.

Among recent publications are the following papers:

  • WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing, 2022, IEEE Journal of Selected Topics in Signal Processing
  • Icassp 2022 Deep Noise Suppression Challenge, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • CHiME-6 Challenge: Tackling Multispeaker Speech Recognition for Unsegmented Recordings, 2020, arXiv (Cornell University)
  • Personalized speech enhancement: new models and Comprehensive evaluation, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation, 2022, Interspeech 2022

Best Publications

  • WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

    Sanyuan Chen;Chengyi Wang;Zhengyang Chen;Yu Wu

  • Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation

    Yi Luo;Zhuo Chen;Takuya Yoshioka

  • 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

  • CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings

    Shinji Watanabe;Michael Mandel;Jon Barker;Emmanuel Vincent

  • Generalization of Multi-Channel Linear Prediction Methods for Blind MIMO Impulse Response Shortening

    T. Yoshioka;T. Nakatani

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

    Takuya Yoshioka;Nobutaka Ito;Marc Delcroix;Atsunori Ogawa

  • Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise

    Takuya Higuchi;Nobutaka Ito;Takuya Yoshioka;Tomohiro Nakatani

  • Continuous Speech Separation: Dataset and Analysis

    Zhuo Chen;Takuya Yoshioka;Liang Lu;Tianyan Zhou

  • Blind Separation and Dereverberation of Speech Mixtures by Joint Optimization

    Takuya Yoshioka;Tomohiro Nakatani;Masato Miyoshi;Hiroshi G Okuno

  • End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation

    Yi Luo;Zhuo Chen;Nima Mesgarani;Takuya Yoshioka

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

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

  • Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network

    Zhuo Chen;Xiong Xiao;Takuya Yoshioka;Hakan Erdogan

  • Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition

    Takuya Yoshioka;Hakan Erdogan;Zhuo Chen;Fil Alleva

  • Continuous Speech Separation with Conformer

    Sanyuan Chen;Yu Wu;Zhuo Chen;Jian Wu

  • Online MVDR Beamformer Based on Complex Gaussian Mixture Model With Spatial Prior for Noise Robust ASR

    Takuya Higuchi;Nobutaka Ito;Shoko Araki;Takuya Yoshioka

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

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

  • Integrated Speech Enhancement Method Using Noise Suppression and Dereverberation

    T. Yoshioka;T. Nakatani;M. Miyoshi

  • Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms

    Hirokazu Kameoka;Tomohiro Nakatani;Takuya Yoshioka

Frequent Co-Authors

Marc Delcroix
Marc Delcroix NTT (Japan)
Jinyu Li
Jinyu Li Microsoft (United States)
Shoko Araki
Shoko Araki NTT (Japan)
Hakan Erdogan
Hakan Erdogan Google (United States)
Xuedong Huang
Xuedong Huang Microsoft (United States)
Yu Wu
Yu Wu Microsoft Research Asia (China)
Shujie Liu
Shujie Liu Microsoft Research Asia (China)

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 computer science opens doors to a range of majors in college that can enhance your career prospects in tech and beyond. From data science to software engineering, the flexibility in specialization lets you customize your educational journey.

For those considering advanced education but worried about workload, it's helpful to look into what is the easiest masters degree to get. This can help you balance career and studies, especially if you want to upskill without overwhelming commitments.

Pursuing terminal degrees is also more accessible than ever. If you're focused on value, many affordable online doctoral programs are available, allowing you to advance your qualifications while managing costs.

Additionally, for those interested in leadership or educational roles, online edd degrees offer quick, flexible pathways to doctorate-level credentials.

Whether you're just starting out or looking to continue your studies, online programs make education in computer science more accessible, affordable, and tailored to your goals.

Best Scientists Citing Takuya Yoshioka

Trending Scientists

Recently Published Articles