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.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.