ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Speaker Identification and Verification for Intelligent Service Robots
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Keun-Chang Kwak, Hye-Jin Kim, Kyung-Suk Bae, Ho-Sub Yoon
Issue Date
2007-06
Citation
International Conference on Artifical Intelligence (ICAI) 2007, pp.1-5
Language
English
Type
Conference Paper
Abstract
This paper is concerned with a text-independent speaker identification/verification and speech recognition for intelligent service robots with humanlike auditory system. The objective of this paper is to develop and integrate audio-based Human-Robot Interaction (HRI) components that can naturally interact between human and robot through audio information obtained from microphones in the noisy environments. Furthermore, we can naturally communicate with intelligent service robot through a Korean-based spontaneous speech recognition and text-independent speaker recognition to provide a customized service such as daily life schedule and selection of preferable TV channel for the identified speaker. The robot platform used in this study is WEVER, which is a network-based intelligent service robot developed at Intelligent Robot Research Division in Electronics and Telecommunication Research Institute (ETRI). This robot refers to an Ubiquitous Robotic Companion (URC) that provides necessary services anytime and anywhere. The experimental results obtained for ETRI speaker database reveal that the approach presented in this paper yields a good identification (94.5%) and verification (FAR: 0.014%, FRR: 0.067%) performance within 3 meter.
KSP Keywords
Audio information, Auditory system, Human-Robot Interaction(HRI), Intelligent Robot, Intelligent Service Robot, Research institute, Robot platform, Speaker Identification(SI), TV channel, Text-independent speaker identification, audio-based