Posey's Tips & Tricks
The One Transcription Feature Microsoft Teams Needs Now
The new live transcription feature in Teams is much-needed, but there's one more feature that Microsoft could add to make Teams truly indispensable to meetings. If only AI technology is advanced enough for it.
Even before the pandemic hit, Microsoft was investing a tremendous amount of resources into its Teams platform, and the push to further enhance Teams has not slowed down at all. Microsoft introduced numerous new Teams features last year in response to the transition to work-from-home, and there are more on the way.
Although Teams has come a long way since its humble beginnings, there is still one feature Microsoft could create that would be a total game-changer. I'm not sure that artificial intelligence technology has progressed enough to make it possible just yet, but if the technology isn't quite there now, it soon will be.
So what is this game-changing capability? Before I get to that, let me tell you about a related feature that was recently introduced: live transcription. If you want to transcribe a Teams meeting, all you have to do is turn the feature on.
Transcribing a Teams meeting is an easy, two-step process. The first step is to use the Teams Admin Center to allow meetings to be transcribed. To do so, open the Teams Admin Center, expand the Meetings container, then click on the Meeting Policies tab. Click the Add button and you will be taken to a screen like the one shown in Figure 1 that allows you to configure the meeting policies. As you can see in the figure, the option to allow transcription is disabled by default, so you will need to set the Allow Transcription option to On.
Setting the Allow Transcription option to On doesn't cause Teams meetings to be transcribed; it only gives meeting organizers the option to transcribe meetings. This is where the second step comes into play: During a meeting, the meeting organizer will need to turn the transcription feature on in order for the meeting to be transcribed.
One of the things that makes the transcription feature so unique is that the transcription happens in near-real time. In other words, Teams will transcribe a meeting participant's words as they are spoken. This capability is brand-new, so I haven't had a chance to try it out for myself yet. However, I have been told that Teams does a good job of accurately transcribing what participants are saying, and there is also a way to edit a transcript after the meeting in case something is transcribed incorrectly.
Another thing I find particularly interesting about the new live transcription capability is that it supports speaker attribution. In other words, Teams is smart enough to associate a participant's name with the words they have spoken.
Incidentally, I have heard rumors of hardware vendors working on smart speakers designed to enable speaker attribution in conference room environments. In a conference room, participants on a Teams call are less likely to be logged in individually, which means that Teams can't get a participant's name from their session ID to include speaker attribution in the transcript. Instead, there may be one Teams session that services the entire room. The smart speakers I have been hearing about will supposedly be able to differentiate one person's voice from another and assign an attribution based on a person's voiceprint.
On the surface, it would be easy to assume that the live transcription feature is designed to help those with disabilities, and indeed, live transcription probably is useful as an accessibility feature. Live transcription is also useful in that it creates a transcript on the spot so no one has to remember to transcribe the meeting later on.
However, the one big use case that keeps coming up is that live transcription can help those who show up late to a meeting catch up quickly.
At the beginning of this post, I mentioned that there is one capability that Microsoft could add to Teams that would be a real game-changer. That feature is a real-time -- and constantly evolving -- meeting summary.
The idea is that as the live transcription is created, a separate AI could be used to analyze the transcript, pick out the important points and create a short synopsis of those points. That way, anyone who shows up late to a meeting would be able to digest the meeting's most important points by reading a paragraph or two, rather than sifting through the full transcript.
As I said earlier, I'm not sure if AI has evolved to the point of being able to reliably create this type of synopsis in real-time, but the technology will exist soon if it does not already.
Having a real-time synopsis that covers everything important that has been discussed in a meeting would be an absolute game-changer. Not only would it benefit those who showed up late to a meeting, but the synopsis could be sent out to participants after the meeting as a post-meeting summary covering what was discussed and any action items.
About the Author
Brien Posey is a 22-time Microsoft MVP with decades of IT experience. As a freelance writer, Posey has written thousands of articles and contributed to several dozen books on a wide variety of IT topics. Prior to going freelance, Posey was a CIO for a national chain of hospitals and health care facilities. He has also served as a network administrator for some of the country's largest insurance companies and for the Department of Defense at Fort Knox. In addition to his continued work in IT, Posey has spent the last several years actively training as a commercial scientist-astronaut candidate in preparation to fly on a mission to study polar mesospheric clouds from space. You can follow his spaceflight training on his Web site.