CODEWITHSUNDEEP
c#asp.net-mvcazureazure-cognitive-services
Sana
Sana

Reputation: 447

SpeakerRecognition - Identifying more than one speaker in an audio - C#

Working with the SpeakerRecognitionAPI, I have successfully been able enroll and identify a speaker. Now, I have multiple users speaking in an audio, How to identify multiple user from the audio? I have been searching alot since 5 hours but couldnt find anything. Any help would be appreciated.Thanks. I am working on .net MVC structure.

Upvotes: 0

Views: 266

Answers (2)

Sana
Sana

Reputation: 447

So, after dense research. You will have to send the identification profiles ids separated by comma in order to find out the profiles speaking in the audio but there is no support of diarization as if now. Moving to google speech api because well it gives that feature.

Upvotes: 0

Nicolas R
Nicolas R

Reputation: 14609

You just have to enroll of your users like you did with the 1st one, and then query Identification method of Speaker Recognition part of the API, passing in input the Ids of the identification profiles

See API Method here: https://westus.dev.cognitive.microsoft.com/docs/services/563309b6778daf02acc0a508/operations/5645c523778daf217c292592

Be careful, you can only limit to 10 Ids...

API doc

Upvotes: 1

Related Questions