You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I believe ethically we should have at least the ability for a consent mechanism (this might not technically easy at this point but I think we should be thinking about a mechanism).
We would have to identify known speakers.
Have them state their consent and optimal timeout for that consent.
In some countries there may be legal issues with recording I think giving the user the option to use this is a good move.
I've got eyes on Speechmatics flow it like a great technology for recognition and diarization.
The text was updated successfully, but these errors were encountered:
Diarization is so hit or miss I don't believe this is feasible right now. I was having a conversation with myself and it thought 4 speaker were talking. I've looking into diarization extensively for meeting minutes as well and nothing works even close to what you could call 'reliably'.
Legal issues will be tough here and I think each user will have to make their own call - likely lots of us operating illegally for the foreseeable future. Not sure if a 'hands up' emoji is appropriate but that's where I believe we are today.
I believe ethically we should have at least the ability for a consent mechanism (this might not technically easy at this point but I think we should be thinking about a mechanism).
We would have to identify known speakers.
Have them state their consent and optimal timeout for that consent.
In some countries there may be legal issues with recording I think giving the user the option to use this is a good move.
I've got eyes on Speechmatics flow it like a great technology for recognition and diarization.
The text was updated successfully, but these errors were encountered: