AI Powered Speaker and Facial Recognition | AI News

  • Overview
  • Transcript

Learn how incorporating an AI-powered bot with facial and speaker recognition tools can help you automate some of the tedious meeting tasks you face each week.

Take a look at an AI Powered speaker and facial recognition system

Learn about and purchase the Intel® Speech Enabling Developer Kit

AI News YouTube Playlist

If you're like us, you attend lots of meetings with your boss, calls with your team, maybe even video conferences with clients. It can be a little daunting keeping track of it all. What if there was a solution that brings together AI and meetings? I'm David Shaw. And in this episode of AI News, we'll look at a way to automate those tedious meeting tasks you face each week.

A typical video conference call isn't very immersive. In fact, when I think of conference calls, I think about padded shoulders and 1980s office attire-- past the expiration date. Imagine a solution that could modernize record keeping by employing the latest AI guided recognition technologies.

Let me paint a picture for you. If you introduce an AI powered bot with facial and speaker recognition tools, typical meeting activities like recording comments and generating minutes could be fully automated, capturing ideas and discussion topics. Intel senior staff researcher Jonathan Wang and Julio Zamora came up with something that is just like that.

Combining their expertise, one in facial recognition and the other in voice and speech recognition, they developed a conference oriented multi-modal system for reidentifying participants. The system creates its own database over the course of a video conference, enrolling new users automatically and learning on the fly how to recognize individuals using a combination of speaker recognition and facial recognition.

Jonathan and Julio took advantage of several Intel technologies, the Intel Movidius vision processing unit, Intel RealSense technology, and the eight microphone circular array included in the Intel Speech Enabling Developer Kit. These are, quote, "the perfect components for this type of application because all you need is good eyes, good ears, and an efficient brain. Our algorithms are the glue that takes advantage of these components to generate a complete solution."

Check out this article and read all about this success story, including the technological milestones. Thanks for watching. Be sure to check out the links provided and I'll see you next week.