I. Burnett, E. Cheng, and C. Ritz, “Investigating Spatial Audio Coding Cues for Meeting Audio Segmentation,” in Proc. AES Convention 120, May 2006, pp. 6703:1-12. [Online]. Available: https://aes.org/publications/elibrary-page/?id=13507
Burnett I, Cheng E, Ritz C. Investigating Spatial Audio Coding Cues for Meeting Audio Segmentation. In: AES Convention 120. Audio Engineering Society; 2006.pp. 6703:1-12. Available from: https://aes.org/publications/elibrary-page/?id=13507
@inproceedings{Burnett2006_13507,
author = {Burnett, Ian and Cheng, Eva and Ritz, Christian},
title = {{Investigating Spatial Audio Coding Cues for Meeting Audio Segmentation}},
booktitle = {AES Convention 120},
pages = {6703:1-12},
url = {https://aes.org/publications/elibrary-page/?id=13507},
year = {2006},
month = may,
publisher = {Audio Engineering Society},
address = {Paris France}
}
TY - CPAPER
TI - Investigating Spatial Audio Coding Cues for Meeting Audio Segmentation
AU - Burnett, Ian
AU - Cheng, Eva
AU - Ritz, Christian
T2 - AES Convention 120
SP - 1
EP - 12
M1 - Paper 6703
PY - 2006
DA - 2006/05/06
UR - https://aes.org/publications/elibrary-page/?id=13507
PB - Audio Engineering Society
CY - Paris France
LA - en
AB - As multiparty meetings involve participants that are generally stationary when actively speaking, participant location information can be used to segment the recorded meeting audio into speaker ‘turns.’ In this paper, speaker location information derived from ‘spatial cues’ generated by spatial audio coding techniques is investigated. The validity of using spatial cues for meeting audio segmentation is explored through investigating multiple microphone meeting audio recording techniques and extracting and comparing spatial cues used by different spatial audio coders. Experimental results show the statistical relationship between speaker location and interchannel level and phase-based spatial cues strongly depends on the microphone pattern. Results also indicate that interchannel correlation-based spatial cues represent location information that is ambiguous for meeting audio segmentation.
ER -