Voice biometric company’s patented methods improve recognition speed and accuracy; reduce hardware costs
NEW YORK, March 15, 2021 — ID R&D, a provider of AI-based voice and face biometrics, today announced that it has received US Patent 10,909,991, Systems for Text Dependent Speaker Recognition and methods thereof. The patent is further evidence of the company’s passion for advancing the performance and usability of biometrics.
The patented methods improve the speed and accuracy of speaker recognition — even when the amount of data gathered for training the speaker model is small. The invention drastically reduces CPU consumption, lowering hardware costs in commercial applications.
ID R&D’s core biometric and liveness products are used globally by OEM partners and enterprise customers. Relentless focus on superior biometric technology performance enables the company to lead the market in developing products that efficiently solve business problems and satisfy consumer demand for frictionless experiences.
“We are an R&D-driven company with a commitment to delivering products that are either first-in-class or entirely unique,” said Alexey Khitrov, president at ID R&D. “We get excited about making things that were previously impossible possible. Voice biometrics have the ability to re-invent age-old processes and add tremendous value to emerging technologies from smart home devices to connected cars.”
ID R&D is continuously innovating. The company already has several additional voice biometric patents pending that further improve on the awarded invention. ID R&D scientists are also actively involved in industry challenges designed to accelerate technology advancement. In addition to a first-place ranking in the latest ASVspoof competition, ID R&D demonstrated strong results in the NIST Speaker Recognition Evaluation.
Learn more about ID R&D voice biometrics and voice liveness detection for anti-spoofing.