ID R&D Wins First Place in Global Speaker Verification Challenge

Latest achievement showcases strength of ID R&D Voice Biometrics in microphone channel

NEW YORK,  March 23, 2021 – ID R&D, a provider of AI-based voice and face biometrics, today announced that it has won first place in the Short-duration Speaker Verification (SdSV) Challenge 2021. The challenge evaluated Text Independent (TI) speaker verification in the microphone channel. ID R&D previously achieved leading results in the NIST Speaker Recognition Evaluation which evaluates performance in the telephone/call center channel.

The rapid adoption of mobile apps, voice-enabled IoT devices, and conversational AI demonstrates consumer desire for easy-to-use, natural interfaces. The ability to deploy accurate text independent voice biometrics in the microphone channel significantly improves user convenience and personalization while enabling frictionless security. Use cases include device unlock, application authentication, personalized smart device interactions, voice-secured payments, and more. ID R&D recently published a whitepaper on its breakthrough in voice biometric accuracy for device unlock.

Historically, short-duration speaker verification strongly depended on the phonetic content. Using one language for enrollment and another for verification often resulted in performance degradation and, in turn, complexity for real-world deployments spanning multiple languages.  Designed to focus on the analysis and exploration of new ideas for short-duration speaker verification, the SdSV Challenge 2021 featured the difficult task of cross-lingual speaker verification (English vs. Persian).

ID R&D participated in the Challenge, defined as speaker verification in a text-independent mode, and finished first out of 24 participants on the SdSV Challenge leaderboard. ID R&D’s voice biometrics is language independent and capable of running on a very small footprint in support of embedded voice applications.

“Consumer interest in voice as a user interface is on the rise, driven by demand for touchless, on-the-go interactions. The ability to quickly and accurately recognize a speaker  in text independent mode opens the door to effortless personalization and a level of security that was previously impossible,” says Alexey Khitrov, president at ID R&D. “The SdSV Challenge is the leading benchmark for speaker verification in the microphone channel. Our first place ranking demonstrates the company’s  commitment to pushing voice biometrics beyond the call center to power the next generation of voice-enabled applications and devices.”

The results of the SdSV Challenge will be presented during INTERSPEECH 2021, Learn more about ID R&D speaker verification.

About ID R&D
ID R&D is an award-winning provider of AI-based voice and face biometrics and liveness detection. With one of the strongest R&D teams in the industry, ID R&D consistently delivers innovative, best-in-class biometric capabilities that raise the bar in terms of usability and performance. Our proven products have achieved superior results in industry-leading challenges, third-party testing, and real-world deployments in more than 40 countries.  ID R&D’s solutions are available for easy integration with mobile, web, messaging, and telephone channels, as well as in smart speakers, set-top boxes, and other IoT devices. ID R&D is based in New York, NY.