Speaker & Video APIs from Microsoft Project Oxford

In a previous post I provided source code on how to utilize Microsoft Azure Media Services.  The code, although basic, provided a great introduction on how to build out a solution utilizing Azure Media Services in either the Microsoft Azure Commercial regions or the Microsoft Azure US Government regions.

Today, Microsoft has announced the availability of the Speaker & Video APIs from Microsoft Project Oxford.  The Video APIs makes it easy to analyze and automatically edit video using Microsoft video processing algorithms to detect and track faces in video, detect when motion has occurred in videos with stationary backgrounds, and smooths and stabilize videos.  With the new Speaker APIs you can use voice for another form of authention or for speaker identification.   By utilizing these new APIs you could extend your Azure Media Services solution to provide even more value with your existing  or new video assets.

Check out the announcement over on the Machine Learning Blog, or jump right over to Project Oxford and sign up to test out these features.

Leave a Reply