Impression Evaluation Model for Button Sounds Using a Neural Network

Onishi G, Ishimitsu S, Sakamoto K, Arai T, Yoshimi T, Fujimoto Y, Kawasaki K. Impression Evaluation Model for Button Sounds Using a Neural Network. In: AES Conference: 34th International Conference: New Trends in Audio for Mobile and Handheld Devices. Audio Engineering Society; 2008. Paper 1. Available from: https://aes.org/publications/elibrary-page/?id=14418

@inproceedings{Onishi2008_14418,
  author = {Onishi, Gen and Ishimitsu, Shunsuke and Sakamoto, Koji and Arai, Takayuki and Yoshimi, Toshikazu and Fujimoto, Yuichi and Kawasaki, Kenichi},
  title = {{Impression Evaluation Model for Button Sounds Using a Neural Network}},
  booktitle = {AES Conference: 34th International Conference: New Trends in Audio for Mobile and Handheld Devices},
  note = {Paper 1},
  year = {2008},
  month = aug,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14418}
}

TY  - CPAPER
TI  - Impression Evaluation Model for Button Sounds Using a Neural Network
AU  - Onishi, Gen
AU  - Ishimitsu, Shunsuke
AU  - Sakamoto, Koji
AU  - Arai, Takayuki
AU  - Yoshimi, Toshikazu
AU  - Fujimoto, Yuichi
AU  - Kawasaki, Kenichi
T2  - AES Conference: 34th International Conference: New Trends in Audio for Mobile and Handheld Devices
M1  - Paper 1
PY  - 2008
DA  - 2008/08/06
UR  - https://aes.org/publications/elibrary-page/?id=14418
PB  - Audio Engineering Society
LA  - en
AB  - This paper presents an impression evaluation model for button sounds generated when users press the buttons on car audio equipment using a neural network. The dynamic characteristics of 11 kinds of button sounds obtained by their wavelet transform frequencies and sound pressure values are fed into the network model inputs. The model then responds with three factor scores, “esthetic”, “force” and “metallic”, and an evaluation value of “offensive - pleasant” as the outputs. By analyzing the inside functions of the neural network after training, we confirmed the model acquired a mechanism that extracted four impression evaluation values from the sound characteristics, thus showing the model could attain automation of button sound design.
ER  -