I need to achieve the following scenario on iOS and Android:
For word "hello", the user speaks "hello", the phone recognises it, and tells how well it matches it.
I performed research online and understood that this was a Shazam-scenario and there were articles that explained how it works e.g. creating Fast Fourier Transformation and hashes. What I'm looking for here is some mature working library that you would recommend and people usually use today.
Any guidance will be appreciated.
Aucun commentaire:
Enregistrer un commentaire