Sonic Handprints: Person Identification with Hand Clapping Sounds by a Model-Based Method

Jylhä A, Erkut C, Simsekli U, Cemgil AT. Sonic Handprints: Person Identification with Hand Clapping Sounds by a Model-Based Method. In: AES Conference: 45th International Conference: Applications of Time-Frequency Processing in Audio. Audio Engineering Society; 2012. Paper 1-4. Available from: https://aes.org/publications/elibrary-page/?id=16186

@inproceedings{Jylha2012_16186,
  author = {Jylhä, Antti and Erkut, Cumhur and Simsekli, Umut and Cemgil, A. Taylan},
  title = {{Sonic Handprints: Person Identification with Hand Clapping Sounds by a Model-Based Method}},
  booktitle = {AES Conference: 45th International Conference: Applications of Time-Frequency Processing in Audio},
  note = {Paper 1-4},
  year = {2012},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=16186}
}

TY  - CPAPER
TI  - Sonic Handprints: Person Identification with Hand Clapping Sounds by a Model-Based Method
AU  - Jylhä, Antti
AU  - Erkut, Cumhur
AU  - Simsekli, Umut
AU  - Cemgil, A. Taylan
T2  - AES Conference: 45th International Conference: Applications of Time-Frequency Processing in Audio
M1  - Paper 1-4
PY  - 2012
DA  - 2012/03/06
UR  - https://aes.org/publications/elibrary-page/?id=16186
PB  - Audio Engineering Society
LA  - en
AB  - 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.
ER  -