At Build 2018, Microsoft Intelligent Teams speakers demoed with the promise to follow individual voices, but also translate and transcribe the meetings. The underlying technology came right out of Pro AV via EPOS and Yealink.
Now it’s out of prototype and Microsoft is selling the speakers along with other accessories. The original prototype form factor has been most closely realized in the Yealink option; the EPOS option more resembles a retro Dot. It looks like translation features did not yet make it into production.
Here’s the scoop directly from Microsoft
1. Inclusive meetings powered by Microsoft Teams
Intelligent speakers are intelligent peripherals for Microsoft Teams Rooms on Windows and are designed to bring high quality audio experiences to remote participants can clearly hear all the voices in the room. And they are optimized for Cortana voice assistance to offer touch-less experience to join and end meetings in shared spaces.
2. Intelligent transcription with speaker attribution
Intelligent speakers will bring people identification in live transcription in a shared environment enabling clear voice capture of participants in the meeting room. Allowing everyone in the meeting to spend less time note taking and easily follow along who said what in the room. Intelligent speakers include a 7-microphone array to identify voices of up to ten people in meeting rooms so whether you are working remotely or in the conference room, you can effectively see who said what during and after the meeting.
3. Powered by Microsoft Graph
Knowing who is speaking makes transcription more accurate and meaningful. Once we know who is speaking, we can leverage the power of intelligence through Microsoft Graph that provides access to rich people-centric data and insight in the Microsoft Cloud to contextualize the transcription. For example, because we know who the speaker is, the acronyms, names of colleagues, and different words the speaker uses can be more accurately transcribed.
4. Enterprise grade privacy and security
Voice data will be securely stored in the Office 365 Cloud, and users will retain control of their information, including the ability to delete it at any time. The capture of voice data can be turned on or off for each meeting. Additionally, admins have full control to turn on/off people identification through voice recognition feature across the organization.
The first two partners to launch intelligent speakers are EPOS with Capture 5 and Yealink with MS Speech, EPOS Capture 5 and Yealink M Speech intelligent speakers can be purchased individually and in bundles to work with Microsoft Teams Rooms on Windows products.
Intelligent speakers is available in preview and will be available with a Teams Rooms Standard or Premium license. Future licensing requirements for people identification in transcription are subject to change. The Teams intelligent speaker is available in English in the United States, future regions to come.