- Text-dependent voice recognition: the system is only able to identify a person by its pronunciation of a secret phrase;
- Text-independent voice recognition: the system is able to identify a person only by their voice, whatever they say.
- User-dependent speech-to-text: the system can only speech-to-text from a certain person, which voice trained the model.
- User-independent speech-to-text: the system is able to speech-to-text from any person.