You are here

Voice Control and Authentication on Mobile Tactical Systems

Description:

TECH FOCUS AREAS: Cybersecurity; Network Command, Control and Communications; Artificial Intelligence/Machine Learning; General Warfighting Requirements (GWR)

 

TECHNOLOGY AREAS: Bio Medical; Sensors; Electronics; Information Systems; Battlespace

 

OBJECTIVE: This topic seeks hands-off voice/acoustic recognition for increased usability and interoperability with TAK. Additionally, synchronous and automatic user authentication for enhanced information security, using two factors of authentication (something you are and something you have) is also sought, as well as detection and identification of various sounds.

 

DESCRIPTION:  In tactical environments, existing authentication mechanisms in TAK and mobile devices have proven to be insufficient or cumbersome for operators. Gloves and other gear can make it difficult to interact with the phone’s screen for passcode or other forms of authentication requiring contact with the screen. Likewise, for the same reasons, it proves difficult to interact with and control ATAK (Android Team Awareness Kit) efficiently to disperse and assimilate information relevant to the mission. These deficiencies point to a need for hands-off TAK authentication, through voice biometrics and proximity-based access control, as well as voice command and control of TAK devices. The ability to extract information from voice-based radio communications and/or detect and identify non-vocal sounds in the environment (i.e., gunshots and vehicles) could also prove to be useful as part of this effort. Proximity-based access control includes the ability to grant or deny access based on proximity to friendly forces and teammates, enemy forces, military bases, etc. This research aims to explore voice biometrics, voice commands, and proximity-based access control as it relates to the TAK ecosystem.

 

PHASE I: For all sub-efforts: based on the research performed within this phase, develop a roadmap for development in Phase II and determine the scientific, technical, and commercial feasibility of the proposed solution. For proximity-based access control: demonstrate in a simulated environment the ability to perform proximity-based authentication based on distance from peers and/or established locations. For voice authentication: identify strategies to mitigate vulnerabilities and exploits inherent in many voice authentication implementations, such as the replay and synthesis attacks, and explore the feasibility of detecting duress in an operator’s voice to prevent coerced, unauthorized access. For voice command and control (VC2): demonstrate ability to perform very basic control of ATAK via voice and determine areas of future work for Phase II. For both VC2 and voice authentication: research techniques to minimize the effects of background noise in a tactical environment (e.g., shouting, gunshots, engines) while maintaining a low false negative rate for authentication and increased reliability for command and control. Incorporate all of these techniques into a proposed solution that provides offline voice authentication, proximity-based access control, and VC2 for mobile devices.

 

PHASE II: Implement the roadmap established during Phase I. Collect data and/or utilize public datasets as needed. Obtain necessary hardware (e.g., mobile phones), then implement and test the proposed solution. Demonstrate the solution’s capability in tactical environments and revise as necessary to improve reliability and security, gathering and incorporating end-user feedback when possible. Develop a plan for Phase III.

 

 

PHASE III DUAL USE APPLICATIONS: A commercial solution for proximity-based access control, voice authentication in tactical and loud environments, and VC2 would be marketable to military and first-responder users of ATAK, as well as other users who simply desire enhanced voice recognition in tumultuous environments.

 

NOTES: The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the proposed tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct questions to the Air Force SBIR/STTR Help Desk: usaf.team@afsbirsttr.us

 

REFERENCES:

  1. https://www.sciencedirect.com/science/article/abs/pii/S1051200420300178
  2. Active Voice Authentication, DTIC ADB406545, DTIC AFRL-RI-RS-TR-2015-005
  3. https://wavellroom.com/2019/11/12/the-utility-of-voice-recognition-within-defence/
  4. https://dl.acm.org/doi/abs/10.1145/3378904.3378908; https://link.springer.com/chapter/10.1007/978-3-319-52464-1_8
  5. https://ieeexplore.ieee.org/abstract/document/7815208/

 

KEYWORDS: TAK; Biometrics; Authentication; Voice

US Flag An Official Website of the United States Government