The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam kertas kerja ini, kami mencadangkan sistem sokongan reka bentuk automatik untuk peranti akustik padat seperti pembesar suara mikro di dalam telefon pintar. Sistem sokongan reka bentuk yang dicadangkan mengeluarkan dimensi peranti akustik padat dengan ciri akustik yang dikehendaki. Sistem ini menggunakan rangkaian neural dalam (DNN) untuk mendapatkan hubungan antara ciri frekuensi peranti akustik padat dan dimensinya. Data latihan dijana oleh kaedah domain masa perbezaan terhingga akustik (FDTD) supaya banyak data latihan boleh diperolehi dengan mudah. Kami menunjukkan keberkesanan sistem yang dicadangkan melalui beberapa perbandingan antara ciri frekuensi yang dikehendaki dan direka bentuk.
Kai NAKAMURA
Kansai University
Kenta IWAI
Ritsumeikan University
Yoshinobu KAJIKAWA
Kansai University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Kai NAKAMURA, Kenta IWAI, Yoshinobu KAJIKAWA, "Acoustic Design Support System of Compact Enclosure for Smartphone Using Deep Neural Network" in IEICE TRANSACTIONS on Fundamentals,
vol. E102-A, no. 12, pp. 1932-1939, December 2019, doi: 10.1587/transfun.E102.A.1932.
Abstract: In this paper, we propose an automatic design support system for compact acoustic devices such as microspeakers inside smartphones. The proposed design support system outputs the dimensions of compact acoustic devices with the desired acoustic characteristic. This system uses a deep neural network (DNN) to obtain the relationship between the frequency characteristic of the compact acoustic device and its dimensions. The training data are generated by the acoustic finite-difference time-domain (FDTD) method so that many training data can be easily obtained. We demonstrate the effectiveness of the proposed system through some comparisons between desired and designed frequency characteristics.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E102.A.1932/_p
Salinan
@ARTICLE{e102-a_12_1932,
author={Kai NAKAMURA, Kenta IWAI, Yoshinobu KAJIKAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Acoustic Design Support System of Compact Enclosure for Smartphone Using Deep Neural Network},
year={2019},
volume={E102-A},
number={12},
pages={1932-1939},
abstract={In this paper, we propose an automatic design support system for compact acoustic devices such as microspeakers inside smartphones. The proposed design support system outputs the dimensions of compact acoustic devices with the desired acoustic characteristic. This system uses a deep neural network (DNN) to obtain the relationship between the frequency characteristic of the compact acoustic device and its dimensions. The training data are generated by the acoustic finite-difference time-domain (FDTD) method so that many training data can be easily obtained. We demonstrate the effectiveness of the proposed system through some comparisons between desired and designed frequency characteristics.},
keywords={},
doi={10.1587/transfun.E102.A.1932},
ISSN={1745-1337},
month={December},}
Salinan
TY - JOUR
TI - Acoustic Design Support System of Compact Enclosure for Smartphone Using Deep Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1932
EP - 1939
AU - Kai NAKAMURA
AU - Kenta IWAI
AU - Yoshinobu KAJIKAWA
PY - 2019
DO - 10.1587/transfun.E102.A.1932
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E102-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2019
AB - In this paper, we propose an automatic design support system for compact acoustic devices such as microspeakers inside smartphones. The proposed design support system outputs the dimensions of compact acoustic devices with the desired acoustic characteristic. This system uses a deep neural network (DNN) to obtain the relationship between the frequency characteristic of the compact acoustic device and its dimensions. The training data are generated by the acoustic finite-difference time-domain (FDTD) method so that many training data can be easily obtained. We demonstrate the effectiveness of the proposed system through some comparisons between desired and designed frequency characteristics.
ER -