Currently with the GET Operations Status API call, confidence is returned as "High", Normal", or "Low".
Having the actual Confidence Score (0-1 i real numbers) returned would be much more useful than an arbitrary value.
GitHub Issue connected with this: https://github.com/MicrosoftDocs/azure-docs/issues/302212 votes
I am trying to build a system that has should be able to recognize all the speakers and the speeches each speaker has spoken.
I was trying to build the solution using “Speaker Recognition API”. I am passing the voice/audio stream to identification API and able to know who are the speakers there; but didn’t find a way to know who spoke what.
Is there any way to know who spoke what using “Speaker Recognition API” as it is required for my solution?
Reference to any other APIs Microsoft is building will be really helpful5 votes
I know Denmark is a small country, but there are still a need for support in Danish1 vote
Is there any plans to later support more than 10 profiles in the requests to identify speaker voices?
I am curious as to the technical limitations of the identification service. Is there plans in the future to make this a reliable service to make voice signature profiles out of?9 votes
Takes too long to recognize the speaker due to Azure service being on different coast. Is this still an issue? Or do we now have servers in more locations?1 vote
This is still an issue, but we are working on making the service geo-available.
The Speaker Recognition services does not accept legit WAV captured using UWP API.
See https://mtaulty.com/2016/02/10/project-oxfordspeaker-verification-from-a-windows-10uwp-app/. The author had to fix the WAV stream for it to be accepted by the service.1 vote
- Don't see your idea?