![](bg4.png)
(a) 1m
(b) 2m
Figure 5: Speech signals obtained in 1m and 2m.
6 CONCLUSIONS
We have developed the face and speaker recognition
system for multimodal user identification with the
aid of TMPCA and MFCC-GMM under network-
based home service robot environments,
respectively. Furthermore, we have used the low-
price camera and microphones for the
commercialization of network-based home service
robots. The experiments were performed on the face
and speaker database constructed in u-robot test bed
as like home environments. The presented method
could effectively recognize in network-based
environment, which is useful not only for intelligent
home robots but also for biometrics and digital home
networks. We shall study an efficient fusion scheme
for network-based multimodal user identification in
the near future.
This research was supported by Basic Science
Research Program through the National Research
Foundation of Korea (NRF) funded by the Ministry
of Education, Science and Technology.
(20110003296)
REFERENCES
Reynolds, D. A., Rose, R. C., 1995. Robust text-
independent speaker identification using Gaussian
mixture speaker models. IEEE Trans. on Speech and
Audio Processing, vol. 3, no. 1, pp. 72-83.
Kwak, K. C., Kim, H. J., Bae, K. S., Yoon, H. S., 2007.
Speaker identification and verification for intelligent
service robots. In International Conference on
Artificial Intelligence (ICAI2007), Las Vegas, May.
Ha, Y. G., Sohn, J. C., Cho, Y. J., and Yoon, H., 2005.
Towards ubiquitous robotic companion: Design and
implementation of ubiquitous robotic service
framework. ETRI Journal, vol. 27, no. 6, pp. 666-676.
Kim, D. H., Lee, J., Yoon, H. S., and Cha, E. Y., 2007. A
non-cooperative user authentication system in robot
environments. IEEE Consumer Electronics, vol. 53,
no. 2, pp. 804-811.
Yun, W. H., Kim, D. H., and Yoon, H. S., 2007. Fast
Group verification system for intelligent robot service.
IEEE Trans. on Consumer Electronics, vol. 53, no. 4,
pp. 1731-1735.
Ji, M., Kim, S., and Kim, H., 2008. Text-independent
speaker identification using soft channel selection in
home robot environments. IEEE Trans. on Consumer
Electronics, vol. 54, no. 1, pp. 140-144, 2008.
Lu, H., Plataniotis, K. N., and Venetsanopoulos, A. N.,
2008. MPCA: Multilinear principal component
analysis of tensor objects. IEEE Trans. on Neural
Networks, vol. 19, no. 1, pp. 18-39.
Kwak, K. C., and Kim, S. S., 2008. Sound source
localization with aid of excitation source information
in home robot environments. IEEE Trans. on
Consumer Electronics, vol. 54, no. 2, pp. 852-856.
Kim, H. J., Lee, J. Y., Kwak, K. C., and Yoon, H. S., 2007.
Network-based voice component framework for
human-robot interaction. International Symposium on
Communications and Information Technologies
(ISCIT 2007), pp. 1546-1550.
ICINCO 2011 - 8th International Conference on Informatics in Control, Automation and Robotics
340