Vivoka has integrated the IDVoice solution from ID R&D into the latest version of its own voice development kit (VDK). The VDK is now in its third iteration and makes it easier for developers to build their own custom apps with voice biometrics capabilities.
To this end, IDVoice was attractive both for its accuracy and for its small compute footprint. The platform’s biometric engine weighs less than 1MB, making it small enough to fit on a Neural Processing Unit (NPU) without any significant drop in performance. In terms of accuracy, ID R&D achieved a false acceptance rate of just 0.01%, a figure that rivals a PIN for security and reliability.
Vivoka’s VDK, on the other hand, offers a simple user interface that allows developers to access a host of different voice utilities through a single software hub. These speech technologies can be integrated into devices and applications to support a wide variety of use cases, and can be tested in the VDK to ensure everything is working properly before being released to the market.
The ID R&D platform can recognize short voice segments and is equipped with anti-spoofing technology to thwart those who attempt to commit fraud with synthetic or recorded voices. This technology was good enough to take first place in the Short-Duration Speaker Verification (SdSV) challenge earlier this year, and first place in NIST’s ASVspoof challenge in 2019.
ID R&D can deliver solid results regardless of the speaker’s text and language, and is accurate enough to be used for authentication based on Android’s authentication guidelines. It can also help identify an individual speaker when many people are talking, at least when paired with Vivoka’s robust transcription and automatic speech recognition capabilities.
“Biometrics has the unique ability to bring instant personalization and authentication to voice-activated applications and devices of all kinds,” said Alexey Khitrov, CEO of ID R&D. “Running voice biometrics at the edge brings value never before realized to smart speakers, smart cameras, connected cars, robotics and more. “
“As the voice market continues to evolve, new use cases for voice technology will benefit from faster and easier ways for developers and businesses to build and test their ideas,” added William Simonin. , CEO of Vivoka.
Vivoka recently provided Vuzix with voice recognition technology for the latter’s M series of smart glasses. ID R&D, on the other hand, provided voice recognition technology for Thales’ trusted digital identity service in July.
November 2, 2021 – by Eric Weiss