S
Shinji Sako
Researcher at Nagoya Institute of Technology
Publications - 44
Citations - 964
Shinji Sako is an academic researcher from Nagoya Institute of Technology. The author has contributed to research in topics: Japanese Sign Language & Sign language. The author has an hindex of 12, co-authored 44 publications receiving 911 citations. Previous affiliations of Shinji Sako include University of Tokyo.
Papers
More filters
The HMM-based speech synthesis system (HTS) version 2.0.
Heiga Zen,Takashi Nose,Junichi Yamagishi,Shinji Sako,Takashi Masuko,Alan W. Black,Keiichi Tokuda +6 more
TL;DR: This paper describes HTS version 2.0 in detail, as well as future release plans, which include a number of new features which are useful for both speech synthesis researchers and developers.
Automatic song composition from the lyrics exploiting prosody of Japanese language
TL;DR: An algorithm that can automatically generate songs from Japanese lyrics by considering composition as an optimal-solution search problem under constraints given by the prosody of the lyrics is presented.
Proceedings Article
Recent development of the HMM-based speech synthesis system (HTS)
Heiga Zen,Heiga Zen,Keiichiro Oura,Takashi Nose,Junichi Yamagishi,Junichi Yamagishi,Shinji Sako,Tomoki Toda,Takashi Masuko,Takashi Masuko,Alan W. Black,Keiichi Tokuda +11 more
TL;DR: This paper describes recent developments of HTS in detail, as well as future release plans.
Proceedings Article
HMM-based text-to-audio-visual speech synthesis.
TL;DR: This paper describes a technique for text-to-audio-visual speech synthesis based on hidden Markov models (HMMs), in which lip image sequences are modeled based on imageor pixel-based approach to reduce the dimensionality of visual speech feature space.
Book ChapterDOI
Subunit modeling for japanese sign language recognition based on phonetically depend multi-stream hidden markov models
Shinji Sako,Tadashi Kitamura +1 more
TL;DR: This paper proposes an efficiently method of generating subunit using multi-stream HMM which is correspond to phonological elements of sign language and an isolated word recognition experiment has confirmed the effectiveness of the proposed method.