Biometric firm’s technology advances breakthroughs in AI and voice recognition
NEW YORK, Dec. 18, 2019 — ID R&D, the award-winning biometrics technology provider offering AI-based voice, face, and behavioral biometrics and voice and face anti-spoofing products, today announces its accuracy results in the 2019 Speaker Recognition Evaluation (SRE): Conversation Telephone Speech (CTS) Challenge (*1) from the U.S. National Institute of Standards and Technology (NIST).
The NIST 2019 SRE CTS Evaluation is the latest in the ongoing series of speaker recognition evaluations aimed at providing a common test bed for measuring developments and supporting research teams in advancing technology (2*). The CTS Challenge uses conversational telephone speech to evaluate each team’s speaker detection performance. This year, 51 commercial and academic research teams from around the globe tested their solution at the 2019 NIST Speaker Recognition Evaluation.
“Using our advanced modified x-vector algorithms, ID R&D was able to complete the 2019 NIST challenge with outstanding results and low Equal Error Rate (EER) on challenging telephone audio data in the Tunisian Arabic language,” said ID R&D President, Alexey Khitrov. “ID R&D is committed to building voice biometric technology with breakthrough performance in accuracy, speed, and footprint.”
ID R&D was invited to share the methodology used to achieve these results with the NIST community at the NIST SRE Workshop in Singapore earlier in December.
ID R&D’s strong finish in the 2019 NIST Speaker Recognition Evaluation CTS Challenge comes on the heels of the company’s first-place finish in detecting synthetic speech in the global 2019 ASVspoof Challenge.
Increased security and improved user experience are two key elements driving companies to adopt biometric technology at a record pace. Voice and speech recognition are expected to see particularly strong growth, with Fortune Business Insights predicting the worldwide speech and voice recognition market reaching $28.3 Billion by 2026. Businesses are deploying voice authentication in virtually every industry, finding that customer expectations are moving swiftly toward a more convenient and friction-free user experience during online, mobile, call center, and IoT interactions.
ID R&D’s vision is to continue to drive industry-leading biometric accuracy rates to provide an unparalleled combination of security and convenience for authentication across any device or application. The company offers biometric matching for face, voice, and behavior, as well as passive liveness detection for both voice and face. The combination of biometric matching and liveness detection ensures users are both authorized and physically present, thwarting fraudsters trying to gain access using recorded or synthetic voice, or a photo or video.
“Accuracy in biometrics is essential and we are thrilled to be driving the industry toward ever-higher standards,” said Konstantin Simonchik, Chief Science Officer at ID R&D. “As voice interfaces become increasingly common in every industry, ID R&D is committed to leading innovation in both security and the user experience so that all of humanity can benefit from advancements in artificial intelligence.”
***Notes:
- (*1) The 2019 speaker recognition evaluation (SRE19) is the next in an ongoing series of speaker recognition evaluations conducted by the US National Institute of Standards and Technology (NIST) since 1996. The objectives of the evaluation series are (1) for NIST to effectively measure system-calibrated performance of the current state of technology, (2) to provide a common test bed that enables the research community to explore promising new ideas in speaker recognition, and (3) to support the community in their development of advanced technology incorporating these ideas.
https://www.nist.gov/system/files/documents/2019/07/22/2019_nist_speaker_recognition_challenge_v8.pdf - (*2) NIST 2019 Speaker Recognition Evaluation: CTS Challenge: Introduction
https://www.nist.gov/system/files/documents/2019/07/22/2019_nist_speaker_recognition_challenge_v8.pdf
About ID R&D
ID R&D is a provider of multimodal biometric security solutions headquartered in New York, NY. With extensive experience in biometrics, ID R&D combines science-driven technological capabilities with leading research and development to deliver seamless authentication experiences. ID R&D’s solutions are available for easy integration with mobile, web, and IoT applications, as well as in smart speakers, set-top boxes, and other IoT devices. The company offers the industry’s #1 voice biometric and #1 voice anti-spoofing technologies based on rankings in leading industry benchmark challenges, and has been recognized as a Top Pick at TechCrunch Disrupt, UBS Future of Banking Finalist, Microsoft Top-10 AI Startup, Best Banking Experience Finalist at VOICE Summit, Finovate Best ID Management Solution Finalist and a member of the accelerator Orange Fab. Learn more about ID R&D’s voice and face biometrics, voice and face biometric anti-spoofing, multimodal biometrics, and audio event detection at www.idrnd.ai.