Varying microphone patterns for meeting speech segmentation using spatial audio cues

Authors

Eva Cheng, University of WollongongFollow
I. Burnett, Faculty of Informatics, University of WollongongFollow
Christian Ritz, University of WollongongFollow

RIS ID

16145

Publication Details

Cheng, E., Burnett, I. S. & Ritz, C. H. (2006). Varying microphone patterns for meeting speech segmentation using spatial audio cues. Q. He, Y. Rui, S. Yang & Y. Zhuang In Pacific-Rim Conference on Multimedia, Nov 2-4, Hangzhou, China. LNCS - Advances in Multimedia Information Processing (PCM 2006), 4261 221-228.

Abstract

Meetings, common to many business environments, generally involve stationary participants. Thus, participant location information can be used to segment meeting speech recordings into each speaker’s ‘turn’. The authors’ previous work proposed the use of spatial audio cues to represent the speaker locations. This paper studies the validity of using spatial audio cues for meeting speech segmentation by investigating the effect of varying microphone pattern on the spatial cues. Experiments conducted on recordings of a real acoustic environment indicate that the relationship between speaker location and spatial audio cues strongly depends on the microphone pattern.