Abstract
We propose two real-time sound recognition approaches that are able to distinguish a predefined whistle sound on a NAO robot in various noisy environments. The approaches use one, two, and four microphone channels of a NAO robot. The first approach is based on a frequency/band-pass filter whereas the second approach is based on logistic regression. We conducted experiments in six different settings varying the noise level of both the surrounding environment and the robot itself. The results show that the robot will be able to identify the whistle reliability even in very noisy environments.
| Original language | English (US) |
|---|---|
| Title of host publication | RoboCup 2014 - Robot World Cup XVIII |
| Publisher | Springer Verlag |
| Pages | 245-257 |
| Number of pages | 13 |
| Volume | 8992 |
| ISBN (Print) | 9783319186146 |
| DOIs | |
| State | Published - 2015 |
| Event | 18th Annual RoboCup International Symposium, RoboCup 2014 - Joao Pessoa, Brazil Duration: Jul 19 2014 → Jul 24 2014 |
Other
| Other | 18th Annual RoboCup International Symposium, RoboCup 2014 |
|---|---|
| Country | Brazil |
| City | Joao Pessoa |
| Period | 7/19/14 → 7/24/14 |
Fingerprint
ASJC Scopus subject areas
- Computer Science(all)
- Theoretical Computer Science
Cite this
Single- and multi-channel whistle recognition with NAO robots. / Poore, Kyle; Abeyruwan, Saminda; Seekircher, Andreas; Visser, Ubbo E.
RoboCup 2014 - Robot World Cup XVIII. Vol. 8992 Springer Verlag, 2015. p. 245-257.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Single- and multi-channel whistle recognition with NAO robots
AU - Poore, Kyle
AU - Abeyruwan, Saminda
AU - Seekircher, Andreas
AU - Visser, Ubbo E
PY - 2015
Y1 - 2015
N2 - We propose two real-time sound recognition approaches that are able to distinguish a predefined whistle sound on a NAO robot in various noisy environments. The approaches use one, two, and four microphone channels of a NAO robot. The first approach is based on a frequency/band-pass filter whereas the second approach is based on logistic regression. We conducted experiments in six different settings varying the noise level of both the surrounding environment and the robot itself. The results show that the robot will be able to identify the whistle reliability even in very noisy environments.
AB - We propose two real-time sound recognition approaches that are able to distinguish a predefined whistle sound on a NAO robot in various noisy environments. The approaches use one, two, and four microphone channels of a NAO robot. The first approach is based on a frequency/band-pass filter whereas the second approach is based on logistic regression. We conducted experiments in six different settings varying the noise level of both the surrounding environment and the robot itself. The results show that the robot will be able to identify the whistle reliability even in very noisy environments.
UR - http://www.scopus.com/inward/record.url?scp=84958543057&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84958543057&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-18615-3_20
DO - 10.1007/978-3-319-18615-3_20
M3 - Conference contribution
SN - 9783319186146
VL - 8992
SP - 245
EP - 257
BT - RoboCup 2014 - Robot World Cup XVIII
PB - Springer Verlag
ER -