i want to create an application using inbuilt java package's which should support me in speech recognition
("Actually Thinking to develop app like in movie "her" which talks to human as and give response with AI")
There is no Java Platform package yet for speech recognition. However, there's at least one opsn-source project for speech recognition with a simple Java API ... http://voce.sourceforge.net/ (see also its dependencies).
Related
I'm pretty new to React Native and mobile development in general. But I have a simple Java library with junit tests and I want to do one of two things:
1) I want to convert this Java code to be used naturally with React Native for development on iOS and Android.
2) I want to use this java code to be used only with Android in a native-hybrid application.
I probably have a few gaps in my understanding of how all this works. I understand that Java is native for Android, and therefore is only used for Android development. React native bridges the cross-platform gap to decompile react native code into platform specific code.
If I wanted to use my Java code for development on iOS, does that happen through Native Modules? Is it possible to do regardless?
If it is only to be used on Android (which is fine), is using the setup described in the Native Modules section on React Native's website the way to go?
Thanks!
As far as I know, You cannot directly deploy code written by java to both Android and IOS in react-native. You can do it only for Android specific parts in react-native. If you want to use it as IOS compatible, you need to write a native module from IOS natives.
If u want to deploy your native Android module you can follow this https://hackernoon.com/first-experiences-with-react-native-bridging-an-android-native-module-for-app-authentication-501fec247b2b detailed example
If u want to create both android and IOS native modules u can follow this https://medium.com/#FizzyInTheHall/writing-a-react-native-bridge-library-bce5b90ea6d0 example
I am currently using tess-two library for OCR in Android, which gives us a result based on input image and training data. What I wish to do is build my own training data based on previous handwriting data. I looked through how to train data on a Linux system using tesseract:
http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3
Does tesseract have support for doing something like this on android?
Any other library which provides such functionality?
tesseract is primarily coded in C++. If you make use of the Native Development Kit (NDK) Google provides for Android, you can use all its classes.
Alternatively, you can try to code a similar learning system based on tesseract's in Java.
Hello I'm working on a project about controlling a robot with Turkish voice commands.
As I search on internet all I can find are Sphinx like speech recognition libraries but they don't support my language.
Is there any possible ways to form my own library for about 20 different commands?
Thanks.
Of course it's possible. The only thing you are missing is the Turkish acoustic model, which I am not sure if there are any free ones available. You can follow the great sphinxtrain tutorial to train one yourself (which is probably the biggest task in this project). You will then need to plug your commands into a grammar file (JSGF is supported as far as I remember). The accuracy should be rather good (99% should be the expectation).
It's an old question but for the reference, you can use Google Speech API in 110 languages
https://cloud.google.com/speech/
It works online, but there is an offline version for android
Is there any way to write a program of voice recognition in Java?
I understood that there are many technologies, and I found freetts which seems to be a comfortable one, though I succeeded to write a program of text-to-speech, but didn't find any reference of voice recognition with it.
Does anyone have references for me on that matter?
Thanks in advance
FreeTTS does not support speech recognition (as far as I know) - it is only implemented to support text-to-speech.
So you will need to use some other tool for speech recognition.
You can have a look at Sphinx which is a speech recognition tool written in Java which I had used for my university project.
Check this link to learn more about Sphinx
You will require some tweaking with Sphinx to suit you requirements - which is easier than creating your own speech recognition engine.
You can refer this video for a short tutorial on Sphinx.
I'm still pretty new to java and I was thinking about making a program where the computer could listen to you talking and write what you said on word or something using the java Robot. Honestly, I have no idea where to start with this and could really use some help on this. Also, I was looking around on my computer and noticed that it does have a voice engine of some sort, is there a way I could implement that into my program?
Thanks in advance
If you want to tap into your dictation software's facilities and hook them into your Java program, then start by taking a look at the JavaSpeech API or the Microsoft Speech API along with the Java Native Interface (JNI). The latter isn't a simple project for a beginner. The former, if your dictation software is compatible, could be something in the order of a few weeks of work for a relative beginner.
For making the dictated speech appear in Word or other external program, it's not clear to me where your Java program would fit in here: your dictation software will natively provide the facility of dictating to whatever the currently active window is, presumably.
Speech Recognition is a complex programming to understand. as you are a beginner go head and see Sphinx4 for recognition written entirely in java and FreeTTS as Synthesizer written entirely in java. first make a simpler recognizer then you can think of Dictation using JNI