I'm writing an android app and I want to use the android OS voice recognition. How do I incorporate it into the application?
Have you seen the API Demo, "VoiceRecognition" - http://developer.android.com/resources/samples/ApiDemos/src/com/example/android/apis/app/VoiceRecognition.html
That should give you a head start.
Related
I am currently working with a Pepper robot (academic version and the QiSDK and NaoQi 2.9). Since I am using the academic version I can't use the cloud based automatic speech recognition service from Softbank which is not included and therefore e.g. I can't use wildcards or other chatbot engines besides QiChat.
Does anybody of you know how I can implement my own speech recognition service for Pepper? I can't find where I can get access to the audiostream of Pepper's microphones.
I've read the documentation from Softbank:
https://developer.softbankrobotics.com/pepper-qisdk
and
https://qisdk.softbankrobotics.com/sdk/doc/pepper-sdk/ch4_api/conversation/reference/basechatbot.html
And I've tried to create a SpeechRecognizer based on Android, which works, but uses the Tablets microphone and not Peppers.
Remote Speech Recognition is a service that you will need to by on top if it was not included with your original Pepper offer!
Regards,
Jonas
I was also curious and contacted the softbank support.
Summary:
With version 2.9. you have no access to the head microphones and can only access the tablet mic.
i am trying to build a game with unity which have Arabic speech recognition to be used on android devices. I am stuck at the speech recognition tool. which one is more suitable with unity ? can i use google API directly ? if yes can i control the data ?
or sphinx is more suitable for game on android device ? I have read about sphinx but the acoustic model of Arabic language was not available but for it.
I have tried to make it using MATLAB but it will cost me a lot to build it on mobile using MATLAB coder and also it does not have all the required libraries.
any help about this ?
Official unity plugin for pocketsphinx is here:
https://github.com/cmusphinx/pocketsphinx-unity-demo
Arabic model has to be trained, yes. In the end you could have a good system, but you have to invest enough into it.
I'm developing an application for Xamarin.Android and Xamarin.iOS and therefore I would need a possibility to start a recorder by just giving a command by speech.
I've found some sample here https://github.com/xamarin/monodroid-samples/blob/master/ApiDemo/App/VoiceRecognition.cs for Android ...
My question is how to do that in iOS?
You would need a 3rd party library for that.
For example:
http://wiki.ios.xamarin.com/index.php?title=HowTo/Interop/Interopping_with_Open_Source_Text-to-Speech_%28TTS%29_C_libraries__for_iPhone.&galleryOffset=showall
or Nuance's Dragon Voice to Text API:
Has anyone created a MonoTouch binding for the Nuance Dragon Mobile Speech SDK for iOS?
Is there any way I can make an app using jelly bean's offline speech recognition api & choose the sensitivity?
Actually I want to build an app, which tests user's English speaking & score.
If anyone can provide link to an app that currently does the same thing, that will be helpful too, because on that case I wouldn't need build an app to help myself
If you want an offline speech recognition on android, use Pocketsphinx:
http://cmusphinx.sourceforge.net/2011/05/building-pocketsphinx-on-android/
I want see the source code for the voice enabled-keyboard feature for android.
Can someone tell me where to find the code?
I assume you're referring to the speech recognition feature demonstrated on the Nexus One with Android 2.1.
If this application is open sourced as part of Android, it will be posted on the Android Open Source Project website at https://android.googlesource.com.
However, Android 2.1 has not yet been posted; it should hopefully be available soon.
In the meantime, you could take a look at the source to the voice dialler application.
As far as I know this code is not currently planned to be open sourced -- it is owned by Google as part of their voice recognition server technology. The IME is a fork that Google made of the standard platform input method, adding voice search to it, much like other manufacturers make their own proprietary customizations.