I googled around and found regular speech-api from google. But I think that this is not what I need. I need continuous voice recognition and the ability to trigger other actions when a particular word is pronounced. Is there anything in sdk for Android that I can use?
If not: is it possible to implement third-party libraries? (If yes: what - and what should I think about when implementing a third-party library?)
Edit: I thought about it again. I have to admit only one word (it probably won't be in googles-speech databases). I have the opportunity to record it. This means that I can constantly match the incoming audio stream regarding my recording. This should work without a database. But I'm new to Android development. Do you have any suggestions on using the API to record and map recorded data? Or is there a better way to constantly wait for a particular word to appear and then process any further actions?
btw: if it was unclearly described: the application should continue to record and ensure that the word occurs again when the reaction has been completed.
source
share