Vote count:
0
They said voice processing is low level topic. Instead of process incoming data directly from microphone, it would be better if i could process the visualized sound. Because i only need to read some specific range of voices that are obvious to see inside a picture. At the image below inside link, you can see how iOS recorder display sounds as visuals.
I wonder is it logical to follow that kind of a method? Then what should i suppose to know to read the data from images? Which kind of frameworks or things should i study? If that kind of thinking is a piece of crap, so what should i suppose to prefer to learn? Thanks!
asked 1 min ago
detecting audio data from the visualization
Aucun commentaire:
Enregistrer un commentaire