The Implementation of Real-Time Speaker Localization Using Multi-Modality

멀티모달러티를 이용한 실시간 음원추적 시스템 구현

  • Park, Jeong-Ok (Dept. of Electronics Engineering, Chonnam National University, RRC HECS) ;
  • Na, Seung-You (Dept. of Electronics Engineering, Chonnam National University, RRC HECS) ;
  • Kim, Jin-Young (Dept. of Electronics Engineering, Chonnam National University, RRC HECS)
  • 박정옥 (전남대학교 전자정보통신공학과, 전남대 지역협력연구센터) ;
  • 나승유 (전남대학교 전자정보통신공학과, 전남대 지역협력연구센터) ;
  • 김진영 (전남대학교 전자정보통신공학과, 전남대 지역협력연구센터)
  • Published : 2004.11.12

Abstract

This paper presents an implementation of real-time speaker localization using audio-visual information. Four channels of microphone signals are processed to detect vertical as well as horizontal speaker positions. At first short-time average magnitude difference function(AMDF) signals are used to determine whether the microphone signals are human voices or not. And then the orientation and distance information of the sound sources can be obtained through interaural time difference and interaual level differences. Finally visual information by a camera helps get finer tuning of the speaker orientation. Experimental results of the real-time localization system show that the performance improves to 99.6% compared to the rate of 88.8% when only the audio information is used.

Keywords