Profiling Humans from Their Voice

Seminar Date: 
2019-02-15
Seminar Time: 
11am - 12pm
Seminar Location: 
5607 Baum Boulevard, Room 407A
Presenter: 
Rita Singh, PhD
Presenter's Institution: 
Carnegie Mellon University

This talk will provide a glimpse into the emerging science of human profiling from voice. The human voice is a powerful bio-parametric indicator. It carries information that can be linked to the current (referring to the time of recording of the voice) physical, physiological, demographic, medical, environmental and myriad other bio-relevant characteristics of the speaker. This capacity of the human voice to dynamically encode a person's bio-parametric factors as they exist at the time of speaking allows voice to potentially be more effective for profiling humans than DNA or fingerprints, since the latter do not reflect the signatures of the speaker's state and surroundings at the time of speaking. Driven by artificial intelligence, and insights into the human voice accumulated over decades of studies by researchers in multiple fields, the science of profiling humans from their voice seeks to uncover extremely fine-level micro-signatures of a speaker's bio-relevant factors for profiling. Its recent breakthroughs include recreating the human face from voice in-vacuo, and it continues to progress towards the generation of the human physical form in 3D from voice alone. Both these aspects are not perfected yet and represent work in progress.

 

Join from your computer or phone:

https://bluejeans.com/148972068?src=calendarLink

Phone: 1-888-240-2560 (US toll-free)

Meeting ID: 148 972 068 

^