Zoom is a wonderfully practical tool for online meetings. And since you’re conducting the meeting via your computer, it’s also a great way to record it. There is a “Record” button in the toolbar. The recording is automatically saved on the computer on which “Record” was pressed. This is also possible with free accounts.
If you have a paid account, you should turn off “Cloud recording” in the account settings beforehand, then the recording will be saved on the computer here as well and automatically converted to an mp4 file after the meeting is over.
This file can be automatically converted into text with the speech recognition f4x.
Caution. Some pitfalls for speech recognition in online meetings
With speech recognition, the better the recording, the better the result.
However, this is not trivial in practice. The built-in microphone on the laptop works quite well for short meetings. However, it is extremely unsuitable for speech recognition. The person speaking is relatively far away from the microphone, and you can usually hear reverberation. This has a negative impact on the recognition accuracy.
What can you expect?
Here we once recorded a short conversation via zoom and translated it into text using the speech recognition f4x. Person 1 used a good headset, person 2 the microphone built into the laptop. Both persons are recognized well, person 1 with headset, however, much better, interjections of person 2 are partly not recognized at all.
Example
#00:00:01-2# All right, Mr. Müller, I’ll start the recording. I hope you agree with that. <unk> yes, must now also be recorded, sheet metal agree with this. Yes, we are recording that now as well. That is simply safer for us to document, if they today’s topic of the meeting us again <unk> could explain.
#00:00:24-5# The
#00:00:26-4# Expansion of the A 49. O
#00:00:30-2# Yes, all right, that’s an exciting topic. <unk>. I actually wanted more of a neutral theme.
#00:00:38-5# Possibly there are different opinions, yes, of course
#00:00:49-5# <unk>
#00:00:55-4# <unk>. Which one sees them thinking of, <unk>, Lunch, <unk>. In the course of Krona’s time, has that changed?
#00:01:07-7# Yes, wonderful. Thank you very much. Lunch in its wonderfully noncommittal theme. Since we can work with thank you very much <unk>. I think that’s enough, too. And that was'it already. Yes, thank you very much, <unk> gladly and goodbye to many fit for lunch time. Yes,
Conclusion: Zoom transcript as protocol
As you can see: This is not a precise transcript, but the text is very suitable for recognizing topics.
Thanks to the time markers contained in the transcript, you can easily jump to the relevant point and, if necessary, listen again in the original recording – e.g. with the transcription software f4transcript.
So if you plan to make an automated transcript of the meeting, you should make sure that a) all participants use good microphones and b) the conversation guide contains as little simultaneous speech as possible.