Real-Time Simultaneous Identification of Multiple Voices

Real-Time Simultaneous Identification of Multiple Voices

Agency: 
Dept. of Defense

The technology provides multiple speaker identification by identifying voices (or other sounds) in a manner that uniquely mimics the essence of the ear-to-brain interconnection through extensive human voice identification learning and recognition training. The object is real-time or faster voice identification needing only relatively simple computing resources. Specifically, this invention looks for prosody matches (spectral patterns over time periods) that were trained into a software Artificial Neural Network (ANN)—based model. Although intended to be used together, the Infinite Impulse Response (IIR) filter patent can be singularly applied to other uses as well. 

Potential Applications:

  • Voice recognition for home automation
  • Sound detection for security systems
  • Assistive technology
  • Audio forensics
  • Biomimetic voice systems

Contact:

Learn more about how to boost your business with NSA available technologies.

National Security Agency
ATTN: Technology Transfer Program
9800 Savage Rd., Suite 6843
Ft. George G. Meade, MD 20755-6843
Telephone: (866) 680-4539
tech_transfer@nsa.gov

Region: 
Mid-Atlantic