I am currently developing a cross-platform application that should run on Google GLASS (Android 4.0.4), a smartphone (Android 4.0.4 or later) and another wearable. At least it will be the ICS version - Ice Cream Sandwich.
This application provides me with various event driven views triggered by a user or system (Network - Event).
For user management, I want to implement speech recognition, which just needs to recognize numbers or at least individual numbers and commands back and forth. It is important that it also works offline, it must work in the background when the application starts, and it should not cover the user interface.
Related work:
SpeechRecognizer seems to have autonomous functionality only with jellybean (havent found a way to use it on Android 4.0.4).
Implementing a custom IME and using VoiceTyping seems very expensive and dirty to me. (for example, Utter !, by the way, really good work!)
The first attempts to use pocketsphinx havent been successful yet ...
I would be very happy for your help and any suggestions that may be useful to me.
source
share