Automatic Role Recognition Based on Conversational and Prosodic Behaviour


Salamin, Hugues and Truong, Khiet and Mohammadi, Gelareh (2010) Automatic Role Recognition Based on Conversational and Prosodic Behaviour. In: ACM International Conference on Multimedia, October 25-29, 2010, Firenze, Italy (pp. pp. 847-850).

[img] PDF
Restricted to UT campus only
: Request a copy
Abstract:This paper proposes an approach for the automatic recognition of roles in settings like news and talk-shows, where roles correspond to specific functions like Anchorman, Guest or Interview Participant. The approach is based on purely nonverbal vocal behavioral cues, including who talks when and how much (turn-taking behavior), and statistical properties of pitch, formants, energy and speaking rate (prosodic behavior). The experiments have been performed over a corpus of around 50 hours of broadcast material and the accuracy, percentage of time correctly labeled in terms of role, is up to 89%. Both turn-taking and prosodic behavior lead to satisfactory results. Furthermore, on one database, their combination leads to a statistically significant improvement.
Item Type:Conference or Workshop Item
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page