H
Hiroyuki Manabe
Researcher at NTT DoCoMo
Publications - 100
Citations - 852
Hiroyuki Manabe is an academic researcher from NTT DoCoMo. The author has contributed to research in topics: Signal & Virtual reality. The author has an hindex of 13, co-authored 95 publications receiving 745 citations. Previous affiliations of Hiroyuki Manabe include Tokyo Institute of Technology & Nippon Telegraph and Telephone.
Papers
More filters
Proceedings ArticleDOI
"Unvoiced speech recognition using EMG - mime speech recognition"
TL;DR: Unvoiced speech recognition, "Mime Speech Recognition", is proposed, not based on voice signals but electromyography (EMG), which will realize unvoiced communication, which is a new communication style.
Proceedings ArticleDOI
Full-time wearable headphone-type gaze detector
Hiroyuki Manabe,Masaaki Fukumoto +1 more
TL;DR: A headphone-type gaze detector for a full-time wearable interface that uses a Kalman filter to analyze multiple channels of EOG signals measured at the locations of headphone cushions to estimate gaze direction and is especially robust against signal anomalies.
Proceedings ArticleDOI
Multi-stream HMM for EMG-based speech recognition
Hiroyuki Manabe,Z. Zhang +1 more
TL;DR: An EMG-based speech recognition system that requires only mouth movements, voice need not be generated is proposed and it is found that the delta component of the static parameter leads to higher accuracy.
Journal ArticleDOI
Direct Gaze Estimation Based on Nonlinearity of EOG
TL;DR: Experiments with five subjects confirm that the proposed technique can estimate the absolute eye angle with an error of less than $4^\circ, and show improvements are achieved with several options such as weighting and multiple saccades.
Patent
Speech recognition system, speech recognition method, speech synthesis system, speech synthesis method, and program product
TL;DR: In this article, a speech recognition system consisting of a sound signal processor, an electromyographic signal processor and an image information processor is proposed. But the system is not suitable for high-volume speech recognition.