鎖骨の音響特性を利用した個人識別・認証システム

• Item type: SIG Technical Reports(1)
• 公開日: 2022-09-29
• タイトル: 鎖骨の音響特性を利用した個人識別・認証システム
• タイトル / 言語: en
• タイトル: Identification and Authentication Using Acoustic Characteristics of Clavicle
• 言語: jpn
• キーワード / 主題Scheme: Other
• キーワード / 主題: 計測・認証1
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: 慶應義塾大学大学院理工学研究科
• 著者所属: 慶應義塾大学大学院理工学研究科
• 著者所属(英): en
• 著者所属(英): Faculty of Science and Technology, Keio University
• 著者所属(英): en
• 著者所属(英): Faculty of Science and Technology, Keio University
• 著者名: 川崎, 陽平; 杉浦, 裕太
• 著者名(英): Yohei, Kawasaki; Yuta, Sugiura
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this study, we propose a personal identification and authentication system that utilizes differences in the acoustic characteristics of the clavicle between individuals. A transducer and a microphone were attached to each shoulder, and a sweep signal generated by the transducer was propagated through the clavicle and measured by the microphone. Fast Fourier transform and Mel filter bank processing were applied to the measured data, and Mel frequency cepstrum coefficients were extracted and used as features. The generalization performance of the model was evaluated by 10-fold cross-validation using the correct response rate for personal identification and the equal error rate for personal authentication as evaluation indices.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this study, we propose a personal identification and authentication system that utilizes differences in the acoustic characteristics of the clavicle between individuals. A transducer and a microphone were attached to each shoulder, and a sweep signal generated by the transducer was propagated through the clavicle and measured by the microphone. Fast Fourier transform and Mel filter bank processing were applied to the measured data, and Mel frequency cepstrum coefficients were extracted and used as features. The generalization performance of the model was evaluated by 10-fold cross-validation using the correct response rate for personal identification and the equal error rate for personal authentication as evaluation indices.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12049625
• 書誌情報: 研究報告エンタテインメントコンピューティング（EC）; 巻 2022-EC-65, 号 17, p. 1-4, 発行日 2022-09-29
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8914
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会