I tried to verify the speaker identification by the Speaker Recognition API of Azure Cognitive Services with Python. # 1
Introduction
Cognitive Services provides various APIs, but this time I tried speaker identification with the "Speaker Recognition API". (It doesn't seem to be very popular in Japan ...)
By the way, speaker identification is to identify "who is talking now", and it may be a feeling of trying, and it may be quite accurate. .. I felt that. (Well, I've only tried it with my own voice)
That's why I would like to verify it immediately!
Advance preparation
First, we will prepare resources in Azure.
Log in to Azure and click "Create Resource".
Enter Speaker Recognition in the search box at the top left of the screen.
Click "Create" on the screen below.
You will be taken to the creation screen, so enter each item!
By the way, F0 is 10,000 free transactions / month (sufficient for verification)
When you're done, click "Create!" At the bottom of the screen.
Now that the resource has been deployed, click Go to Resource.
The subscription key is displayed.
This will be used later, so press the copy button and save it!
You are now ready to use the Speaker Recognition API.
It's going to be hard to see, so the actual processing will be described in the next article!
Next article (actual verification)
Recommended Posts