Sonic handprints: Person identification with hand clapping sounds by a model-based method

A. Jylhä, Cumhur Erkut, U. Si̧msȩkli, A. Taylan Cemgil

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

5 Citationer (Scopus)

Abstract

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 identification 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 classification rate of 64 %. The algorithm runs in real-time, making it suitable also for interactive systems. Copyright
OriginalsprogEngelsk
TitelProceedings of the AES International Conference
Antal sider6
ForlagAudio Engineering Society
Publikationsdato1 dec. 2012
Sider150-155
ISBN (Trykt)978-162276007-7
StatusUdgivet - 1 dec. 2012
Begivenhed45th Audio Engineering Society International Conference 2012 on Applications of Time-Frequency Processing in Audio - Helsinki, Finland
Varighed: 1 mar. 20124 mar. 2012

Konference

Konference45th Audio Engineering Society International Conference 2012 on Applications of Time-Frequency Processing in Audio
Land/OmrådeFinland
ByHelsinki
Periode01/03/201204/03/2012

Fingeraftryk

Dyk ned i forskningsemnerne om 'Sonic handprints: Person identification with hand clapping sounds by a model-based method'. Sammen danner de et unikt fingeraftryk.

Citationsformater