Speech recognition should be as an eyes-free and hands-free interface. To realise this technology, we need to clarify acoustics in a helmet and determine how much high-level riding noise affects captured speech data. This paper describes the acoustics in a helmet and transfer functions of the microphone position. We constructed a data collection system and collected the speech data of motorbike riders on city roads and express highways. Speech recognition experiments were conducted and we obtained a recognition rate high of 83.1%.
Cite as: Tanaka, H., Fujimura, H., Miyajima, C., Nishino, T., Itou, K., Takeda, K. (2005) Data collection and evaluation of speech recognition for motorbike riders. Proc. Interspeech 2005, 2665-2668, doi: 10.21437/Interspeech.2005-255
@inproceedings{tanaka05b_interspeech,
author={H. Tanaka and H. Fujimura and C. Miyajima and T. Nishino and Katunobu Itou and Kazuya Takeda},
title={{Data collection and evaluation of speech recognition for motorbike riders}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={2665--2668},
doi={10.21437/Interspeech.2005-255}
}