WEKO3
アイテム
HMM-Based Probabilistic Flick Keyboard Adaptable to Individual User
https://ipsj.ixsq.nii.ac.jp/records/99496
https://ipsj.ixsq.nii.ac.jp/records/99496a1cc6316-8a2d-49e6-ac60-5c59821a2dd6
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-JNL5503014 (1.0 MB)
|
Copyright (c) 2014 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | Journal(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2014-03-15 | |||||||||
| タイトル | ||||||||||
| タイトル | HMM-Based Probabilistic Flick Keyboard Adaptable to Individual User | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | HMM-Based Probabilistic Flick Keyboard Adaptable to Individual User | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | [一般論文] PDA interfaces, usability, input technologies, personalization | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||
| 資源タイプ | journal article | |||||||||
| 著者所属 | ||||||||||
| KDDI R&D Laboratories, Inc. | ||||||||||
| 著者所属 | ||||||||||
| KDDI R&D Laboratories, Inc. | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| KDDI R&D Laboratories, Inc. | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| KDDI R&D Laboratories, Inc. | ||||||||||
| 著者名 |
Toshiyuki, Hagiya
× Toshiyuki, Hagiya
× Tsuneo, Kato
|
|||||||||
| 著者名(英) |
Toshiyuki, Hagiya
× Toshiyuki, Hagiya
× Tsuneo, Kato
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | To provide an accurate and user-adaptable software keyboard for touchscreens, we propose a probabilistic flick keyboard based on hidden Markov models (HMMs). Touch and flick operations for each character are modeled by HMMs. This keyboard reduces input errors by taking the trajectory of the actual touch position into consideration and by user adaptation. We evaluated the performance of an HMM-based flick keyboard and maximum-likelihood linear regression (MLLR) adaptation. Experimental results showed that a user-dependent model reduced the error rate by 28.3%. In a practical setting, the MLLR adaptation to a specific user with only 10 words reduced the error rate by 16.6% and increased the typing speed by 11.9%. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.22(2014) No.2 (online) DOI http://dx.doi.org/10.2197/ipsjjip.22.410 ------------------------------ |
|||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | To provide an accurate and user-adaptable software keyboard for touchscreens, we propose a probabilistic flick keyboard based on hidden Markov models (HMMs). Touch and flick operations for each character are modeled by HMMs. This keyboard reduces input errors by taking the trajectory of the actual touch position into consideration and by user adaptation. We evaluated the performance of an HMM-based flick keyboard and maximum-likelihood linear regression (MLLR) adaptation. Experimental results showed that a user-dependent model reduced the error rate by 28.3%. In a practical setting, the MLLR adaptation to a specific user with only 10 words reduced the error rate by 16.6% and increased the typing speed by 11.9%. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.22(2014) No.2 (online) DOI http://dx.doi.org/10.2197/ipsjjip.22.410 ------------------------------ |
|||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AN00116647 | |||||||||
| 書誌情報 |
情報処理学会論文誌 巻 55, 号 3, 発行日 2014-03-15 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 1882-7764 | |||||||||
