Sound-based person identification has largely focused on speaker recognition. However, also non-speech sounds may convey personal information, as suggested by our previous studies on hand clap recognition. We propose the use of a probabilistic model-based technique for person identication based on their hand clapping sounds. The method is based on a Hidden Markov Model which uses spectral templates in its observation model. The technique has been evaluated in an experiment with 16 subjects, resulting in an overall correct classication rate of 64 %. The algorithm runs in real-time, making it suitable also for interactive systems.
Authors:
Jylhä, Antti; Erkut, Cumhur; Simsekli, Umut; Cemgil, A. Taylan
Affiliations:
Aalto University School of Electrical Engineering, Aalto, Finland; Bogazici University, Istanbul, Turkey(See document for exact affiliation information.)
AES Conference:
45th International Conference: Applications of Time-Frequency Processing in Audio (March 2012)
Paper Number:
1-4
Publication Date:
March 1, 2012
Subject:
Processing of Audio
Click to purchase paper as a non-member or you can login as an AES member to see more options.
No AES members have commented on this paper yet.
To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.