音声ペン：音声認識結果を手書き文字入力で利用できる新たなペン入力インタフェース

Speech Pen: New Pen Input Interface Capable of Utilizing Speech Recognition for Digital Writing

著者/Authors

栗原　一貴	Kazutaka Kurihara	東京大学大学院情報理工学系研究科コンピュータ科学専攻	Department of Computer Science, The University of Tokyo
後藤　真孝	Masataka Goto	産業技術総合研究所	National Institute of Advanced Industrial Science and Technology
緒方　淳	Jun Ogata	産業技術総合研究所	National Institute of Advanced Industrial Science and Technology
五十嵐　健夫	Takeo Igarashi	東京大学大学院情報理工学系研究科コンピュータ科学専攻/科学技術振興機構さきがけ	Department of Computer ScienceThe University of Tokyo / JST PRESTO

概要/Abstract

This paper introduces a multimodal input system, called "speech pen" that assists digital writing during lectures or presentations with background speech and handwriting recognition. The instructor basically freely speaks to the audience and writes on an electronic whiteboard as usual. The system recognizes those speech and handwriting in the background and provides the instructor with predictions for the further writing by using the recognition results. The instructor can accept a prediction and paste it in the board to save manual writing. If all predictions are wrong or useless, the instructor can simply ignore them. The speech-pen system also allows the sharing of context information for predictions among the instructor and the audience; the speech recognition result of the instructor is sent to the audience to support their own note taking. A preliminary study shows the effectiveness of this system and the implications for further improvements.

キーワード/Keywords

予測手書き文字入力,音声認識,手書き文字認識,マルチモーダルインタフェース,コンテクスト共有,プレゼンテーション