ID R&D Patent Sets Benchmark for Preventing Voice Spoofs and Deepfakes

ID R&D, a provider of liveness detection and voice biometrics products, has been granted a patent for a new approach to detecting voice-based spoofing and deepfake attacks.

The method combines an analysis of different speech audio features with deep convolutional neural networks to enhance detection accuracy. It applies a multi-stage approach and analyzes voice samples by first dividing them into frames, which enables rapid, real-time detection during conversational speech.

ID R&D's IDLive Voice applies the newly patented techniques. It is being used to help protect people from identity fraud by ensuring that when a voice is used for biometric verification, it is that of a live human and not a recording or synthetic voice.

"True to our name, research is a strategic priority at ID R&D, and our products are built upon investigation and discovery of new ways to reduce fraud without burdening users," said Alexey Khitrov, CEO and co-founder of ID R&D, in a statement. "This most recent patent exemplifies the role of our research in being first to market with solutions that make access to digital services safer and easier for millions of people globally."

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues