Person Identification and Gender Recognition from Footstep Sound using Modulation Analysis
| dc.contributor.advisor | Mesgarani, Nima | en_US |
| dc.contributor.advisor | Fritz, Jonathan | en_US |
| dc.contributor.author | DeLoney, Chasity | |
| dc.date.accessioned | 2008-08-18T14:16:21Z | |
| dc.date.available | 2008-08-18T14:16:21Z | |
| dc.date.issued | 2008-08-08 | |
| dc.description | This report is the final project of a student in ISR's 2008 Research Experiences for Undergraduates program. | en |
| dc.description.abstract | We describe a person identification system that is based on classifying the sound of the footstep. The classification is done on the spectrotemporal modulations of sound that are estimated using a model of auditory processing. We describe how different footsteps form a unique footprint in the spectrotemporal modulation domain and how this representation captures the user specific signatures. Using this representation, we achieved higher than 60% accuracy in identifying 9 people with three different shoes and two floors. The study demonstrates the efficacy of the spectrotemporal features in the tasks examined. | en |
| dc.description.sponsorship | The National Science Foundation sponsors the Research Experiences for Undergraduates program. | en |
| dc.format.extent | 601228 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/1903/8379 | |
| dc.language.iso | en_US | en |
| dc.relation.isAvailableAt | Institute for Systems Research | en_us |
| dc.relation.isAvailableAt | Digital Repository at the University of Maryland | en_us |
| dc.relation.isAvailableAt | University of Maryland (College Park, MD) | en_us |
| dc.relation.ispartofseries | TR 2008-17 | |
| dc.subject | person identification | en |
| dc.subject | footstep classification | en |
| dc.subject | spectrotemporal modulations | en |
| dc.title | Person Identification and Gender Recognition from Footstep Sound using Modulation Analysis | en |
| dc.type | Technical Report | en |