Our CoNNear technology delivers measurable improvements across objective benchmarks, listener preference studies, and real-time performance.
For the scientific background behind these results, see our Scientific Evidence page.
HASPI (Hearing Aid Speech Perception Index) is an objective measure of how well speech can be understood after hearing-aid processing. Higher scores mean better predicted speech intelligibility.
NAL-NL2 is the current industry-standard fitting rule. OHC is our own outer hair cell compensation strategy, designed to compete with NAL-NL2. CS is the very first hearing-aid algorithm that attempts to compensate for hidden hearing loss (cochlear synaptopathy) within a hearing-aid framework.
In a listener study with n = 14, participants rated sound quality across speech in quiet (SiQ), speech in noise (SiN), classical music, and pop music. Green means the processed sound was rated better than unprocessed; red means worse; a + means the rating was significantly better than NAL-NL2 processing.
This plot shows the neural representation error (NRMSE) between hearing-impaired and normal-hearing models across phoneme categories. A lower score means the processed signal is closer to normal hearing and predicts better speech understanding.
Paired listener testing with n = 14 shows a significant improvement in word recognition with OHC compensation compared to unprocessed audio. On average, tested patients showed a 12.5% improvement in speech understanding.
In an ongoing clinical trial, patients listen to speech processed with different hearing-aid algorithms — OHC (outer hair cell compensation), CS (cochlear synaptopathy compensation), and OHC+CS (combined) — compared to unprocessed audio.
Low-latency real-time processing makes CoNNear suitable for hearables and hearing aids — matching or outperforming leading commercial devices.
Want to know more about the science behind these results? Visit our Scientific Evidence page.