Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Kengo Fujita.
international conference on human-computer interaction | 2011
Kengo Fujita; Tsuneo Kato
This paper describes the design and development process of our new eyes- and hands-free interface which provides the fundamental functions of a mobile phone by voice interaction through a Bluetooth headset. We first identify four conditions which must be met in order to make the interface acceptable to Japanese users. Next, we define design guides which address each of these conditions. In accordance with the design guides, we propose and implement the interface system. To assess the effectiveness of the proposed interface, we had participants operate a mobile phone while walking while simultaneously confirming a switching signal which either permitted or forbade them to walk. The experimental results showed that the proposed interface was more effective than the conventional interfaces for operating a mobile phone while simultaneously performing other tasks. The participants pointed out some problems during the interviews, and we address these problems.
international conference on acoustics, speech, and signal processing | 2010
Tsuneo Kato; Kengo Fujita; Nobuyuki Nishizawa
This paper presents an efficient frame-synchronous beam pruning for automatic speech recognition. With conventional beam pruning, hypotheses that have a greater potential to reach various words on a lexical tree are likely to be pruned out, since this potential is not taken into account. To make the beam pruning less restrictive for hypotheses with a greater potential and vice versa, the proposed method adds a reward as a monotonically increasing function of the number of reachable words from the node where a hypothesis stays on a lexical tree, to the likelihood of the hypothesis. The reward is designed not to collapse the ASR probabilistic framework. The proposed method reduces the processing time from 30% to 70% for grammar-based tasks. For a language-model-based dictation task, it also causes an additional reduction from the processing time of the beam pruning with the language model look-ahead technique.
Archive | 2007
Kengo Fujita; Tsuneo Kato; Hisashi Kawai; 恒夫 加藤; 恒 河井; 顕吾 藤田
IEICE Transactions on Information and Systems | 2011
Tsuneo Kato; Kengo Fujita; Nobuyuki Nishizawa
conference of the international speech communication association | 2005
Kengo Fujita; Tsuneo Kato; Hideaki Yamada; Hisashi Kawai
Transactions of Japan Society of Kansei Engineering | 2016
Tomonori Yazaki; Kengo Fujita; Oulen Tumur; Shinya Nagashio; Kazuhiko Yamazaki
Transactions of Japan Society of Kansei Engineering | 2016
Tomonori Yazaki; Kengo Fujita; Yoshihiko Takagi; Sumaru Niida
電子情報通信学会技術研究報告. HCS, ヒューマンコミュニケーション基礎 | 2014
Xin Xu; Kengo Fujita; Tsuneo Kato; Fumiaki Sugaya
mobile and ubiquitous multimedia | 2014
Xin Xu; Jianming Wu; Kengo Fujita; Tsuneo Kato; Fumiaki Sugaya
Archive | 2014
顕吾 藤田; Kengo Fujita
Collaboration
Dive into the Kengo Fujita's collaboration.
National Institute of Information and Communications Technology
View shared research outputs