How to use Azure speaker recognition

43秒

SHARE

First, register a speaker with Create Profile in Identification Profile.

Next, load the audio file with Create enrollment

Does this get smarter the more you throw?

Then throw the sound you want to identify to Speaker Recognition

It will then return the ID of the corresponding speaker from the speakers registered in Create Profile.

This curl writing is the most powerful

http://blog.livedoor.jp/tak_tak0/archives/52342644.html

curl -v -X POST "https://api.projectoxford.ai/spid/v1.0/identificationProfiles/a8e51a87-4e66-4a40-9c4d-3288a2af7492/enroll?shortAudio=true " -H "Content-Type: multipart/form-data" -H "Ocp-Apim-Subscription-Key: 4a7d60b9d6aa4f4e86630866cb4034f7" --data-binary @VoipRingback 1 .wav

前の記事

Deep Learning with Raspi Stretc…

次の記事

Using SORACOM with Raspberry Pi