Psinter
- 278
- 785
The what?Sophia said:I'll also have a look at Denningers blog.

If it serves you of something, recognizing in Android, if done through the Google API, (to my knowledge) requires the audio stream to be sent to a server since it is the servers the ones that do the speech recognition. Meaning that if used constantly, you would notice heavy network activity and possibly a drain in battery.
The implementation of this API is likely to stream audio to remote servers to perform speech recognition. As such this API is not intended to be used for continuous recognition, which would consume a significant amount of battery and bandwidth.
-Source (which to recognize speech without displaying a dialog also requires the implementation of another interface: RecognitionListener)
I once, while using the speech recognition API for Android for a project at uni experimented with the Japanese engine. It appears the little amount of Japanese I speak, I speak it clearer than English because it was very accurate to recognize my Japanese while when recognizing my English it changed words I had spoken with other words. So either I speak Japanese better than I speak English or the Japanese engine is better at recognizing than the English engine.
How does one even pronounce "though" anyway. Is it like "thought"? I'm going to use the text to speech from Google to show me... Done...
And is it Even though? or Even thought?
crazy sensitivity! is my password.