3 Reasons Your Face Biometric Offering Is Better with Voice

Uncover new opportunities with Voice.

A growing number of Identity and Access Management providers offer face biometrics as part of their authentication and identity proofing suite. When combined with passive facial liveness detection, this biometric modality is secure and convenient for users.

But what about voice biometrics? While the accuracy of the technology hasn’t achieved the accuracy levels of face biometrics, the voice biometrics industry has made huge advances in performance with the relatively recent application of Machine Learning and Artificial Intelligence. And when combining voice authentication with face authentication in a single action or as a backup to each other, the results are remarkable.

Following are 3 reasons your face biometric offering is better with voice.

Enable choice and ensure flexibility.

What’s convenient for one user may not be for another. Likewise, user preferences can fluctuate depending on the situation. For instance, a customer may prefer the ease of logging in with voice when at home, but if they are in a meeting and need to access an app, face is the way to go. A solution that includes both face and voice biometrics ensures users have a choice. It also provides a convenient “fall back” option in conditions that aren’t well suited to one of the biometric options. For example, on a city street at night, voice may perform better whereas face would have the edge at a loud music festival.

An added advantage of a bimodal biometric approach is the ability to offer biometric login options that work across all interaction channels including web, mobile, contact center, conversational interfaces (like chat), and even standalone devices.

As enterprises make customer experience a priority, offering reliable, frictionless authentication solutions is a strategic initiative with executive and cross-functional support.

Further strengthen security.

While face biometrics offer high accuracy for authentication, combining face with voice in a bimodal biometric solution increases accuracy by a factor of 100. However, biometric security also depends on preventing spoofing. Biometric accuracy is meaningless when a photograph of a person passes the face authentication. When adding a second biometric modality, you also add a second means of detecting spoofs. ID R&D’s passive voice liveness on top of passive facial liveness results in incredible security — all while maintaining a near frictionless user experience.

Another powerful use case is deploying face biometrics with voice biometrics for “step-up” verification or as part of a robust, dynamic risk-based authentication (RBA) process.

Take a look at ID R&D’s bi-modal biometric login demo.

Deliver touchless authentication, even with face masks.

One of the many effects of the COVID 19 pandemic is the need to protect ourselves and others. This ranges from wearing face coverings in public to more protective equipment for healthcare professionals.

Voice biometrics offer a hands-free authentication option that works even with masks. The technology can be deployed with mobile applications, kiosks, ATMs, and building access control systems where removing a mask is risky.

Adding Voice Biometrics Is Easy

We’ve given you three good reasons to add voice. And fortunately, it’s easy to do. ID R&D voice biometrics and anti-spoofing are available for Android and iOS or as a server-side installation using a Docker or an SDK on Linux and Windows. The API follows similar models to face recognition systems and easily scales to any capacity because it is entirely stateless. The API doesn’t store anything and doesn’t know the concept of an identity. Simply extend your current identity management to add voice biometrics as a modality.

Partner with ID R&D

If your business currently provides facial recognition for authentication, adding voice biometrics is a way to drive new revenue and market advantage.

ID R&D provides award-winning core biometric products that are used by identity and access management, onboarding, and biometric integrators worldwide.

Our SDKs offer flexible white label deployment and include text dependent and text independent voice biometrics, voice anti-spoofing (liveness), and Level 1 and 2 ISO 30107-3 compliant passive facial liveness detection. With an extreme focus on R&D, we consistently deliver best-in-class accuracy as demonstrated by the leading industry challenges.

Proven Voice Biometric Performance

ID R&D’s IDVoice delivered strong 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).

#1 Ranked Voice Anti-spoofing Capabilities

ID R&D was the clear leader in the ASVspoof 2019: Automatic Speaker Verification Spoofing and Countermeasures Challenge for Logical Access.

Single-Frame Passive Facial Liveness

The world’s only single frame, passive facial liveness to achieve Level 1 and Level 2 ISO 30107-3 compliance. Strengthen face biometrics security with frictionless anti-spoofing.

Set up a demo session today to discuss how ID R&D can help you deliver additional capabilities, drive new revenue, and free valuable resources with our market-leading core biometric products.

(*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