Title:

Fingerprinting to Identify Repeated Sound Events in Long-Duration Personal Audio Recordings

Author(s):

Ogle, James P.
Ellis, Daniel P. W.

Date:

2007

Type:

Presentations

Department:

Electrical Engineering

Permanent URL:

http://hdl.handle.net/10022/AC:P:14040

Notes:

Presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing, Honolulu, Hi., April 15-20, 2007.

Abstract:

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.).

Subject(s):

Artificial intelligence
Electrical engineering

Item views:

13

Metadata:

description

View | Download