World's Best Scientists 2026 revealed!
Hiroshi Saruwatari

Hiroshi Saruwatari

D-Index & Metrics

Computer Science

D-Index
41
Citations
8948
World Ranking
8702
National Ranking
116

Overview

Hiroshi Saruwatari is affiliated with the University of Tokyo in Japan and has contributed extensively to the field of computer science, focusing primarily on signal processing and artificial intelligence. Their research encompasses various subfields including computational mechanics, computer vision and pattern recognition, and cognitive neuroscience.

The scientist's main research topics center around speech and audio processing, speech recognition and synthesis, as well as music and audio processing. Additional areas of focus include blind source separation techniques, advanced adaptive filtering techniques, speech and dialogue systems, and natural language processing techniques.

Among recent significant papers authored or co-authored by Saruwatari are:

  • UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022, 2022, Interspeech 2022
  • Spatial Active Noise Control Based on Kernel Interpolation of Sound Field, 2021, IEEE/ACM Transactions on Audio Speech and Language Processing
  • JSUT and JVS: Free Japanese voice corpora for accelerating speech synthesis research, 2020, Nippon Onkyo Gakkaishi/Acoustical Science and Technology/Nihon Onkyo Gakkaishi
  • Directionally Weighted Wave Field Estimation Exploiting Prior Information on Source Direction, 2021, IEEE Transactions on Signal Processing
  • Multichannel Blind Source Separation Based on Evanescent-Region-Aware Non-Negative Tensor Factorization in Spherical Harmonic Domain, 2020, IEEE/ACM Transactions on Audio Speech and Language Processing

Frequent co-authors collaborating with Saruwatari include Shinnosuke Takamichi, Tomohiko Nakamura, Norihiro Takamune, Shoichi Koyama, and Daichi Kitamura.

The publication venues where Saruwatari has contributed most frequently are:

  • arXiv (Cornell University)
  • IEEE/ACM Transactions on Audio Speech and Language Processing
  • Interspeech 2022
  • IEICE Transactions on Information and Systems
  • Speech Communication

Saruwatari's research output reflects an interdisciplinary approach to signal processing and artificial intelligence, with various contributions advancing knowledge in speech synthesis, audio processing, and adaptive filtering methods. Their work forms part of the broader computer science discipline with a strong focus on audio and speech technologies.

Best Publications

  • The fundamental limitation of frequency domain blind source separation for convolutive mixtures of speech

    S. Araki;R. Mukai;S. Makino;T. Nishikawa

  • Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization

    Daichi Kitamura;Nobutaka Ono;Hiroshi Sawada;Hirokazu Kameoka

  • Evaluation of blind signal separation method using directivity pattern under reverberant conditions

    S. Kurita;H. Saruwatari;S. Kajita;K. Takeda

  • Blind source separation combining independent component analysis and beamforming

    Hiroshi Saruwatari;Satoshi Kurita;Kazuya Takeda;Fumitada Itakura

  • Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks

    Yuki Saito;Shinnosuke Takamichi;Hiroshi Saruwatari

  • Blind source separation based on a fast-convergence algorithm combining ICA and beamforming

    H. Saruwatari;T. Kawamura;T. Nishikawa;A. Lee

  • Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech

    Keigo Nakamura;Tomoki Toda;Hiroshi Saruwatari;Kiyohiro Shikano

  • Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum

    T. Toda;H. Saruwatari;K. Shikano

  • Blind Spatial Subtraction Array for Speech Enhancement in Noisy Environment

    Y. Takahashi;T. Takatani;K. Osako;H. Saruwatari

  • Maximum Likelihood Voice Conversion Based on GMM with STRAIGHT Mixed Excitation

    Yamato Ohtani;Tomoki Toda;Hiroshi Saruwatari;Kiyohiro Shikano

  • A review of blind source separation methods: two converging routes to ILRMA originating from ICA and NMF

    Hiroshi Sawada;Nobutaka Ono;Hirokazu Kameoka;Daichi Kitamura

  • GMM-Based Voice Conversion Applied to Emotional Speech Synthesis

    Hiromichi Kawanami;Yohei Iwami;Tomoki Toda;Hiroshi Saruwatari

  • Equivalence between frequency-domain blind source separation and frequency-domain adaptive beamforming for convolutive mixtures

    Shoko Araki;Shoji Makino;Yoichi Hinamoto;Ryo Mukai

  • Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech

    S. Araki;S. Makino;T. Nishikawa;H. Saruwatari

  • JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis

    Ryosuke Sonobe;Shinnosuke Takamichi;Hiroshi Saruwatari

  • Public speech-oriented guidance system with adult and child discrimination capability

    R. Nisimura;A. Lee;H. Saruwatari;K. Shikano

  • Noise robust real world spoken dialogue system using GMM based rejection of unintended inputs.

    Akinobu Lee;Keisuke Nakamura;Ryuichi Nisimura;Hiroshi Saruwatari

  • Musical-Noise-Free Speech Enhancement Based on Optimized Iterative Spectral Subtraction

    R. Miyazaki;H. Saruwatari;T. Inoue;Y. Takahashi

  • Automatic optimization scheme of spectral subtraction based on musical noise assessment via higher-order statistics

    Yoshihisa Uemura;Yu Takahashi;Hiroshi Saruwatari;Kiyohiro Shikano

  • Sound Field Recording Using Distributed Microphones Based on Harmonic Analysis of Infinite Order

    Natsuki Ueno;Shoichi Koyama;Hiroshi Saruwatari

  • Low-delay voice conversion based on maximum likelihood estimation of spectral parameter trajectory.

    Takashi Muramatsu;Yamato Ohtani;Tomoki Toda;Hiroshi Saruwatari

Frequent Co-Authors

Kiyohiro Shikano
Kiyohiro Shikano Nara Institute of Science and Technology
Tomoki Toda
Tomoki Toda Nagoya University
Nobutaka Ono
Nobutaka Ono Tokyo Metropolitan University
Shoji Makino
Shoji Makino Waseda University
Satoshi Nakamura
Satoshi Nakamura Nara Institute of Science and Technology
Kazuya Takeda
Kazuya Takeda Nagoya University
Shoko Araki
Shoko Araki NTT (Japan)
Hirokazu Kameoka
Hirokazu Kameoka NTT (Japan)
Hiroshi Sawada
Hiroshi Sawada NTT (Japan)

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 a career in Computer Science often means considering related fields and advanced specializations. Today, a wide range of affordable online bachelor's degree programs make earning a CS credential more accessible than ever, with flexible options suited to different lifestyles and budgets.

If you want to branch into engineering, there are reputable colleges offering an engineer degree online. These pathways can lead to roles in software development, data engineering, and beyond.

Professionals seeking leadership opportunities might choose to build business acumen alongside their technical skills. The best online executive mba programs allow students to gain essential management experience while maintaining their current roles.

For those interested in organizing and managing information, specialized graduate programs like the library science masters offer a unique blend of technology and knowledge management, preparing graduates for careers in digital libraries and information systems.

Best Scientists Citing Hiroshi Saruwatari

Trending Scientists

Recently Published Articles