Microsoft now provides app developers with API-based access to voice biometric-based speaker identification. They call it “Speaker Recognition” and package it as part of its cloud-based “machine learning platform” called Project Oxford, which also features APIs for face recognition, speech processing, visual tools and language understanding. Developers need only have an account on Microsoft Azure and then navigate to Project Oxford in order to take advantage of the tools and resources to “build smarter apps.”

Project Oxford made its debut at Build 2015, a developers’ conference that convened in San Francisco in May (2015). The idea was to simplify the processes involved in adding expensive technologies to mobile apps. The tools support development and distribution of apps for iOS and Android platforms as well as various flavors of the Windows OS. Services are offered, initially, as part of a free beta in order to gauge how the services are being used.

Categories: Intelligent Authentication

Tags: Speaker recognition, Microsoft, Mobile Apps, Cloud APIs