2007 Presentations (Communicative Events)
Fingerprinting to Identify Repeated Sound Events in Long-Duration Personal Audio Recordings
Body-worn audio recorders can collect huge "personal audio" archives of everything heard by the user, but navigating this data is a challenge. We investigate a noise-resistant audio fingerprint as a way to identify recurrent sound events. The fingerprint works well for data that is highly repeatable (e.g. phone rings) but not for more "organic" sounds (door closures etc.).
- icassp07-fprint-poster.pdf application/pdf 2.5 MB Download File
More About This Work
- Academic Units
- Electrical Engineering
- Published Here
- July 13, 2012
Presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing, Honolulu, Hi., April 15-20, 2007.