Sciweavers

Share
IROS
2006
IEEE

Evaluation of Prosodic and Voice Quality Features on Automatic Extraction of Paralinguistic Information

9 years 5 months ago
Evaluation of Prosodic and Voice Quality Features on Automatic Extraction of Paralinguistic Information
- Aiming to realize a non-verbal communication between humans and robots, the use of acoustic parameters related with voice quality features, besides classical prosodic features, is proposed and evaluated for automatic extraction of paralinguistic information (intentions, attitudes, and emotions) in dialog speech. Experimental results indicated that prosodic features were effective for detecting groups of paralinguistic information expressing specific functions (such as affirmation, denial, and asking for repetition), accounting for 61 % of the global identification rate. Voice quality features were effective for detecting part of the paralinguistic information expressing emotions or attitudes (such as surprise, disgust and admiration), leading to 12 % improvement in the global identification rate.
Carlos Toshinori Ishi, Hiroshi Ishiguro, Norihiro
Added 12 Jun 2010
Updated 12 Jun 2010
Type Conference
Year 2006
Where IROS
Authors Carlos Toshinori Ishi, Hiroshi Ishiguro, Norihiro Hagita
Comments (0)
books