VocalZoom Transforms Voiceprint Verification for Biometrics Authentication Using Optical Sensor Technology


  • The transformative VoiceMatch-in-Sensor™ technology converts speaker’s facial skin vibrations into unique, noise-free voiceprint, with both the biometric acquisition and template matching all performed inside the optical sensor solution.
  • Technology is first to eliminate microphones, noise reduction software and previous verification vulnerabilities, also can perform accurate, low-power liveness detection to optimize for fraud protection.
  • Company’s goal is to make optically-acquired voiceprints the most secure, cost-effective, easiest biometric to verify for fraud-proof authentication.

YOKNEAM ILLIT, Israel--(BUSINESS WIRE)--VocalZoom, a leading supplier of Human-to-Machine Communication (HMC) optical sensors that enable a more natural, personalized and secure voice-control experience, today announced voice biometrics technology using its optical sensor that performs all voiceprint acquisition and embedded template matching, eliminates the microphones and noise reduction software of traditional acoustic solutions, and takes voiceprint verification out of an external processor or cloud-based server to the security of an embedded, match-in-sensor architecture.

“We all want the simplicity of authenticating to applications and services with our voice, but until now, solutions have been complex and expensive, are not reliable in noisy environments, and are vulnerable to cloned voiceprints,” said Tal Bakish, chief executive officer, VocalZoom. “VocalZoom plans to deliver the industry’s first speaker verification sensor using a match-in-sensor architecture, which will drive a paradigm shift in behavioral authentication.”

VocalZoom’s patented VoiceMatch-in-Sensor technology for embedded speaker verification products acquires data from users during the biometric enrollment process as their facial skin vibrates during speech. The VocalZoom optical HMC sensor converts this data into a voiceprint associated only with the person who was actually speaking, and stores it inside the sensor. This enables the sensor to meet FIDO compliance requirements, enabling easy plug-and-play installation as compared to existing fingerprint or other biometric sensors that don’t offer secure embedded biometric acquisition and template matching. Each time users authenticate, a voiceprint is again acquired in real time, again optically confirmed to be from a living person rather than a recording, and then securely matched inside the sensor solution against information in its embedded template to verify the user and complete the authentication process.

“Opus Research’s latest voice biometrics census, issued in September 2016, shows a doubling of voiceprint enrollments (more than 137 million globally), signaling voice as a ubiquitous, highly personalized authentication factor, with the capability to combine command and control with identification and access management,” said Dan Miller, lead analyst at Opus Research. “Device-based implementations are accelerating and technologies like VocalZoom’s match-in-sensor voiceprint verification technology will fuel this growth by improving security and fraud protection for products that are easier to build and use.”

The match-in-sensor architecture for embedded speaker verification has been proven with fingerprint biometrics, but was previously unfeasible for voice biometrics because of the cost, complexity and vulnerabilities associated with acquiring voiceprints using traditional acoustic technology. VocalZoom’s optical VoiceMatch-in-Sensor approach to voiceprint acquisition delivers a streamlined, compact solution with inherent liveness detection that can be included in products ranging from smartphones and PCs to ATMs and the connected car. The sensor also offers the ability to optically acquire other biometric information to be used as additional authentication factors, including the speaker’s unique heartbeat and facial characteristics.

About VocalZoom

VocalZoom supplies Human-to-Machine Communication (HMC) sensors for delivering a, natural, personalized and secure voice-controlled user experience in today’s increasingly mobile and interconnected world. The sensors enable accurate and reliable voice control and biometrics authentication in any environment, regardless of noise. Applications including mobile secure payments, headsets and wearables, mobile phones, access control, smart home solutions, and hands-free automotive voice control. For more information, visit www.VocalZoom.com and follow the company on LinkedIn.