A Novel and High Performance System for Enhancing Speech in Helmet, Phase I

We propose a highly innovative system for enhancing speech in helmet. First, we propose to apply a circular array with 8 microphones that are inside the helmet. In our past studies, it was found that circular arrays have better directivity than linear arrays. The use of 8 microphones achieves a compromise between performance and complexity. Second, since the speech source and mics are close, we apply proven near-field beamforming to speech acquisition. This will ensure better speech acquisition and high signal-to-noise ratio. Third, we propose to apply latest developments in speech separation to untangle the speech from other background noises. The particular technique is known as Adaptive Decorrelation Filter (ADF) and has been proven to outperform conventional techniques such as Independent Component Analysis (ICA). ADF has strong potential in separating breathing noise from normal speech. Then only the speech segments will be transmitted. The proposed algorithms will be implemented in Field Programmable Gate Array (FPGA) in Phase 2.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.