Hiroshi Saruwatari

Statistics

Publications

167

Citations

6.2K

H-Index

Active since

1999

Affiliations

Nara Institute of Science and Technology(Current)

The University of Tokyo

Yamaha (Japan)

NTT (Japan)

Hiroshi Saruwatari is an author at Nara Institute of Science and Technology specializing in acoustics, computational acoustics, and digital signal processing.

ORCID

Publications per year

1999–2024

167

Publications

167

Determined Blind Source Separation Unifying Independent Vector Analysis and Nonnegative Matrix Factorization

Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada et al. · IEEE/ACM Transactions on Audio Speech and Language Processing · 2016 · 369 citations

Engineering, Musicology, Acoustics +9

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

Shoko Araki, Ryo Mukai, Shoji Makino et al. · IEEE Transactions on Speech and Audio Processing · 2003 · 323 citations

Health Professions, Audiology, Acoustics +11

Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks

Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari · IEEE/ACM Transactions on Audio Speech and Language Processing · 2017 · 228 citations

Computing, Computer Science, Machine Learning +16

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

Hiroshi Saruwatari, Tatsuyuki Kawamura, Tsuyoki Nishikawa et al. · IEEE Transactions on Audio Speech and Language Processing · 2006 · 210 citations

Engineering, Data Science, Psychoacoustics +14

UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

Takaaki Saeki, Detai Xin, Wataru Nakata et al. · Interspeech 2022 · 2022 · 208 citations

Computing, Computer Science, Computational Linguistics +14

1–5 of 167