Hi, these days I was reading about speaker recognition in some papers (I'll give some links in other posts) and my conclusions can be resumed in this image:
General steps for speaker recognition. |
So, I have been doing some proof of concept using CoMIRVA library but I didn't reach anything useful, but exploring Microsoft Speech API (SAPI) I saw an interesting topic in StackOverflow where I found Mistral platform.
I didn't use Mistral, for now, but I'm reading its wiki and in this days I'll be testing this platform in deep.
Talking about Mistral, I can tell that it's written in C++, so it's cool because I hope to implement Mistral in an Android application using Android NDK.
So, as I go by testing I'm going to write here my progress.
No hay comentarios:
Publicar un comentario