ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Text-Independent Speaker Identification using Soft Channel Selection in Home Robot Environments
Cited 19 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
지미경, 김성탁, 김회린, 윤호섭
발행일
200802
출처
IEEE Transactions on Consumer Electronics, v.54 no.1, pp.140-144
ISSN
0098-3063
출판사
IEEE
DOI
https://dx.doi.org/10.1109/TCE.2008.4470036
협약과제
08MC5100, u-로봇 HRI 솔루션 및 핵심 소자 기술 개발, 황대환
초록
With the aim of achieving the best possible speaker identification rate in a distant-talking environment, we developed a multiple microphone-based text-independent speaker identification system using soft channel selection. The system selects and combines the identification results based on the reliability of an individual channel result using a single perceptron. Thus, it allows for user-customized service with high identification accuracy in home robot environments. From the experimental results, it is shown that the proposed system is effective in a distant-talking environment, thereby providing a speech interface for a wide range of potential hands-free applications in a ubiquitous environment. © 2008 IEEE.
키워드
Human robot interaction, Hypothesis combination, Multiple microphones, Speaker identification, Speaker recognition
KSP 제안 키워드
Channel Selection, Hands-Free, Home robot, Human-Robot Interaction(HRI), Identification rate, Speaker Identification(SI), Speech interface, Text-independent speaker identification, Ubiquitous environments, Wide range, customized service