The Requirements and Applications of Speech Recognition Technology for Voice Activated Command and Control in the Tactical Military Environment
Abstract
The US Army Communications/Electronics Research, Development and Engineering Center (CERDEC) at Fort Monmouth, NJ has been at the forefront of the research and development of speech recognition technologies for the tactical military environment for over twenty years. This includes the development of specialized techniques and technology to provide reliable performance in high noise environments. Additionally, unique to this technology is the ability to recognize whispered speech that is barely audible at one meter. The whispered speech recognition capability permits voice activation of C2 equipment during covert operations, such as urban house-to-house and room-to-room fighting, which requires the soldiers to maintain both hands weapons and an eyes-alert posture. This paper will presents a discussion of the unique and specialized requirements for a militarized speech recognizer, as well as the tactical advantages of militarized speech recognition technology as it could be applied in several C2 applications and environments. Additionally, this paper will present the results of a comparison study, which was performed between a custom military speech recognition technology and various manual input modalities, including keyboard and trackball, for activating a selected C2 application. The results of this paper demonstrate a clear superiority of continuous speech recognition over discrete speech recognition in both metrics, and a tradeoff of task execution speed for error rate for continuous speech recognition verses manual input.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2004
- Accession Number
- ADA465047
Entities
People
- Lockwood Reed
Organizations
- United States Army Communications-Electronics Command