Fingerprinting to Identify Repeated Sound Events in Long-Duration Personal Audio Recordings
James P. Ogle; Daniel P. W. Ellis
- Fingerprinting to Identify Repeated Sound Events in Long-Duration Personal Audio Recordings
Ogle, James P.
Ellis, Daniel P. W.
- Electrical Engineering
- Permanent URL:
- Presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing, Honolulu, Hi., April 15-20, 2007.
- 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.).
- Item views: