问题
As I understand Android API uses google speech recognition service for speech to text.
I've learned API and I see it's pretty simple and just converts voice to words array.
Is any way to improve the recognition, I mean, if I know the context can I send some parameters to the service in order to improve the recognition?
Or alternatively is any other speech recognition service which can be used for this purpose?
Thanks in advance.
回答1:
Is any way to improve the recognition, I mean, if I know the context can I send some parameters to the service in order to improve the recognition?
No
Or alternatively is any other speech recognition service which can be used for this purpose?
Most SaaS service do not provide customization capabilities because it requires them to tune things internally. They usually work with predefined configuration.
If you want adaptation for improved accuracy and support for fixed grammars you can check CMUSphinx tutorial on Android.
回答2:
I think the answer of the Nikolay Shmyrev is a good guide for you .but in addition of this, I would say that the Accuracy also may depends on the RMS the closer the mic of the mobile the good output results you would get.
来源：https://stackoverflow.com/questions/29139275/improve-android-speech-recognition-with-additional-context