Award Data

Speech data corrupted by reverberation, especially in combination with noise, has a drastically negative effect on the performance of speaker identification algorithms. Current approaches to the removal of reverb and noise rely on specific knowledge of room characteristics causing the reverb.The team of In-Depth Engineering and the University of Maryland propose to apply an innovative, generalized ...

Automatic speech recognition (ASR) technology is in wide use today and has been successfully integrated into a number of applications. Although there are also many potential applications for automatic speaker identification (SID), SID accuracy rates are generally not sufficient for widespread use in practical applications. For high accuracy ASR and SID, the microphone must be located near the talk ...

LongShortWay Inc. and Northeastern University propose a family of feature reduction and ensemble classifier methods based on Principal Component and Dynamic Logic feature clustering algorithms. New methods combine feature clustering with non-linear feature reduction via manifold learning, and bagging, boosting, and stacking ensemble algorithms.

Towing of a Magnetic Anomaly Detection (MAD) system is an important aspect of rotorcraftmaritime operation. The oscillatory rotorcraft combined with the long and flexible towingcable, the low mass ratio of the towed body to the towing aircraft, and the rotor wake effecton the towed body presents a challenge for integration of a modern MAD system withrotorcraft platform. The research objective is t ...

High-performance low-latency image processing is needed in next-generation DoD vision systems. In LLEVS Phase II, we bring low-latency digital imaging and future fusion applications to the warfighter, in a scalable small-SWaP product footprint leveraging COTS technology.We have a very detailed LLEVS FPGA design resulting from our Phase I efforts. We understand the entire critical path of the desig ...

Our Phase I work focused on improving modeling and simulations so that the impact of autonomous systems in the battlespace could be better understood. As we have trained our attention on Phase II, it has become increasingly clear that the work we are doing to improve the modeling and simulation of autonomous systems also provides significant leverage for the development of the intelligent behavior ...

EO/IR sensors can provide high spatial resolution images using multiple frequency bands ranging from the visible to mid-wave IR. EO/IR sensors have been very successful for terrain imaging from subsonic aircraft and from satellites. Imaging using these platforms has been studied extensively. EO/IR sensors can provide high spatial resolution images using multiple frequency bands ranging from the v ...

Coating materials and coating methods used to protect U.S. military aircraft and weapon systems from corrosion and wear are in need of environmentally benign alternatives in order to keep up with dynamic regulations associated with environment, safety, and occupational health. Thus, the Air Force is supporting research to develop alternatives to the dangerous materials identified on the OSD Emergi ...

NanoSonics HybridSil Ice Protective Coating (IPC) will provide a practical, near-term solution for protecting U.S. Navy ships from problematic ice buildup during arctic missions. A Phase II STTR transition will provide a pivotal funding bridge toward Phase III maturation of this very promising, empirically validated coating technology. Building from its Phase I success and strong collaborative, sh ...

Physical Sciences Inc. (PSI) proposes to design, develop, and demonstrate a portable, non-invasive, real-time sensor to assess the chemical and physical health of solid rocket motors as a function of age without affecting the motors integrity nor having direct contact with the propellant. In Phase II, a sensor to monitor specific gas species that are markers of the chemical and mechanical aging pr ...