Huawei patent voiceprint recognition technology for voice unlock feature

On July 24, 2019, Huawei and Duke Kunshan University has jointly applied for the new patent, Voiceprint recognition method, and device in China. This patent was passed and publically published on January 29, 2021, with a publication number CN112289325A.

Voiceprint recognization refers to the acoustic frequency spectrum that carries the speech information in a human voice like fingerprints, it has unique biometric signatures.

It is also known as speaker recognition technology and bio-identification technology that extracts phonetic features from the speaker’s voice signals to validate the speaker’s identity. According to the information, such a feature can be used to unlock a device and could be very handy in use.

The patent describes that the voiceprint recognition method and the device will be used to solve the issue of low robustness of the voiceprint recognition method in the prior art.

The method involves artificial intelligence and other related fields and specifically includes: electronic equipment prompts the user to enter a registered voice, electronic equipment collects the registered voice entered by the user, electronic equipment generates a sample voice under far-field conditions based on the registered voice, electronic device voices based on the sample voice. And the pattern recognition model is trained.

Aside from this, Huawei FreeBuds 2 and 3 have received the Bone Voiceprint feature with the new update. The Bone voiceprint generation biometric technology cooperates with AI recognition to complete the identity verification in one sentence.

Following the patent, this voiceprint recognition method could be used in upcoming Huawei smart products to improve voiceprint recognition. Still, there is no information regarding this is available now.

[Via]