Voce Library / Speech Recognition

Contributed Library Questions

mrscrow

Voce Library / Speech Recognition

in Contributed Library Questions • 2 years ago

Hi Guys,

following this thread from the old forum

http://processing.org/discourse/yabb2/YaBB.pl?num=1191403856/0

I started to play around with Voce

http://voce.sourceforge.net/

and it seems to work even though not very accurate.

Now I would like to understand a bit more what's actually happening behind and how I can implement own grammar files (.gram) which tetermin what the application can understand etc.

Therefor I would like to start discussing here and would be very happy if people join in who already used / experimented with this lib.

My first concern would be how to design the grammar file (which software, which structure is best). I am adding here one file I have been using from the examples of Voce. It works quiet ok with "quit" and "reset" but it always also gets some "ghost input" which is a mix of other words.

#JSGF V1.0;
/**
* JSGF Digits Grammar file
*/
grammar objects;
public <objects> = <colors> <objectTypes>;
public <miscellaneous> = (quit | reset);
<colors> = (yellow | red | blue | green | purple | orange);
<objectTypes> = (box | sphere | wall | tower | character);

Replies(14)

sunilvallu

Re: Voce Library / Speech Recognition

2 years ago

Hi mrscrow's,

Im also facing same issues as you had mentioned. But I have a doubt, can this library be used to detect any gibberish words/sounds rather than words from english dictionary? can you use to make it learn new language, may be not the complete language, but even to add just a new sound not a word? I'd appreciate any help or suggestions on this.

Thanks

Sunil

mrscrow

Re: Voce Library / Speech Recognition

2 years ago

hi sunil,

it seems it can recognize the words you put into the grammer file. though it only works with rather "normal" words, pretty much the same as your mac's speech output can spell, i guess. it isn't a voder :)

also it seems to depend a lot on a appropriate environment. Would be great to hear from somebody who has some more experience with this lib?

best,

Florian S..

Re: Voce Library / Speech Recognition

2 years ago

I bet you read the Whitepaper http://voce.sourceforge.net/files/VoceWhitePaper.pdf

What else do you need to know? :)

For me the library is at least working pretty good when you only need some commands. When you aim for dictation without grammar you may try google speech which depends on uploading a record to google and getting back some json as response.

The topic has been discussed here: http://mikepultz.com/2011/03/accessing-google-speech-api-chrome-11/

I also managed to record something, send the http request and parse the json inside processing. So if you are interested I may clean up the code ;)

sunilvallu

Re: Voce Library / Speech Recognition

2 years ago

Hey getflourish,

I did read the white paper, but I dont think one could train voce by uploading an audio file as far the documentation says. Thanks for suggesting the google speech api. And it would a great help if you could share your code and guide me on getting this work on processing.

Thanks,

sunil

vijayakv

Re: Voce Library / Speech Recognition

2 years ago

Hi

I am experimenting with voce on processing with some of the examples given online. But when I try to run the program I get the error "Unexpected char: U" (though sometimes it looks like "V" to me)

This is my processing code:

import voce.*;

void setup() {
size(200,200);
background(0);
voce.SpeechInterface.init("C:\Users\Vidya\Documents\Processing\libraries\voce-0.9.1\library",true,true,"C:\Users\Vidya\Documents\Processing\gramtest\grammar","test");
System.out.println("This is a speech recognition test. ");
}

void draw() {
stroke(255);
while (voce.SpeechInterface.getRecognizerQueueSize() > 0){
    String s = voce.SpeechInterface.popRecognizedString();
    println("You said: " + s);
    voce.SpeechInterface.synthesize(s);
}
}

and this is my grammar code

#JSGF V1.0;

grammar Test;

public <TEST> = (hi | one | two | ok) * ;

Please help. I need to do speech recognition with processing for my project

PhiLho

Re: Voce Library / Speech Recognition

2 years ago

Don't use Windows paths in strings in Processing!
Use voce.SpeechInterface.init("C:/Users/Vidya/Documents/Processing/libraries/voce-0.9.1/library",true,true,"C:/Users/Vidya/Documents/Processing/gramtest/grammar","test");
Or relative paths, if the library handles them...

vijayakv

Re: Voce Library / Speech Recognition

2 years ago

Thank you. That definitely got rid of the error. But now the problem is that I'm getting a NullPointerException. This is the error that I'm getting. This is not my code. Its a sample code posted on some forums. Please help. Thanks

[Voce ERROR] Cannot load speech recognizer:
java.io.FileNotFoundException: .gramtest\grammar\test.gram (The system cannot find the path specified)
    at java.io.FileInputStream.open(Native Method)
    at java.io.FileInputStream.<init>(FileInputStream.java:106)
    at java.io.FileInputStream.<init>(FileInputStream.java:66)
    at sun.net.www.protocol.file.FileURLConnection.connect(FileURLConnection.java:70)
    at sun.net.www.protocol.file.FileURLConnection.getInputStream(FileURLConnection.java:161)
    at java.net.URL.openStream(URL.java:1010)
    at com.sun.speech.engine.recognition.JSGFParser.newGrammarFromJSGF(JSGFParser.java:261)
    at com.sun.speech.engine.recognition.BaseRecognizer.loadJSGF(BaseRecognizer.java:273)
    at com.sun.speech.engine.recognition.BaseRecognizer.loadJSGF(BaseRecognizer.java:230)
    at edu.cmu.sphinx.jsapi.JSGFGrammar.commitChanges(JSGFGrammar.java:615)
    at edu.cmu.sphinx.jsapi.JSGFGrammar.createGrammar(JSGFGrammar.java:318)
    at edu.cmu.sphinx.linguist.language.grammar.Grammar.allocate(Grammar.java:163)
    at edu.cmu.sphinx.linguist.flat.FlatLinguist.allocate(FlatLinguist.java:319)
    at edu.cmu.sphinx.decoder.search.SimpleBreadthFirstSearchManager.allocate(SimpleBreadthFirstSearchManager.java:602)
    at edu.cmu.sphinx.decoder.Decoder.allocate(Decoder.java:109)
    at edu.cmu.sphinx.recognizer.Recognizer.allocate(Recognizer.java:182)
    at voce.SpeechRecognizer.<init>(SpeechRecognizer.java:94)
    at voce.SpeechInterface.init(SpeechInterface.java:79)
    at gramtest.setup(gramtest.java:27)
    at processing.core.PApplet.handleDraw(Unknown Source)
    at processing.core.PApplet.run(Unknown Source)
    at java.lang.Thread.run(Thread.java:619)
[Voce] Initialization complete
This is a speech recognition test.
Exception in thread "Recognition thread" java.lang.IllegalStateException: Expected state Ready actual state Allocating
    at edu.cmu.sphinx.recognizer.Recognizer.checkState(Recognizer.java:147)
    at edu.cmu.sphinx.recognizer.Recognizer.recognize(Recognizer.java:113)
    at edu.cmu.sphinx.recognizer.Recognizer.recognize(Recognizer.java:135)
    at voce.SpeechRecognizer.run(SpeechRecognizer.java:129)
    at java.lang.Thread.run(Thread.java:619)
processing.app.debug.RunnerException: NullPointerException
    at processing.app.Sketch.placeException(Sketch.java:1543)
    at processing.app.debug.Runner.findException(Runner.java:582)
    at processing.app.debug.Runner.reportException(Runner.java:558)
    at processing.app.debug.Runner.exception(Runner.java:498)
    at processing.app.debug.EventThread.exceptionEvent(EventThread.java:367)
    at processing.app.debug.EventThread.handleEvent(EventThread.java:255)
    at processing.app.debug.EventThread.run(EventThread.java:89)
Error repainting line range {0,15}:
java.lang.ArrayIndexOutOfBoundsException: -154
    at javax.swing.text.Utilities.drawTabbedText(Utilities.java:132)
    at javax.swing.text.Utilities.drawTabbedText(Utilities.java:89)
    at javax.swing.text.Utilities.drawTabbedText(Utilities.java:67)
    at processing.app.syntax.SyntaxUtilities.paintSyntaxLine(SyntaxUtilities.java:151)
    at processing.app.syntax.TextAreaPainter.paintSyntaxLine(TextAreaPainter.java:644)
    at processing.app.syntax.TextAreaPainter.paintLine(TextAreaPainter.java:603)
    at processing.app.syntax.TextAreaPainter.paint(TextAreaPainter.java:415)
    at javax.swing.JComponent.paintToOffscreen(JComponent.java:5124)
    at javax.swing.RepaintManager$PaintManager.paintDoubleBuffered(RepaintManager.java:1479)
    at javax.swing.RepaintManager$PaintManager.paint(RepaintManager.java:1410)
    at javax.swing.RepaintManager.paint(RepaintManager.java:1224)
    at javax.swing.JComponent._paintImmediately(JComponent.java:5072)
    at javax.swing.JComponent.paintImmediately(JComponent.java:4882)
    at javax.swing.RepaintManager.paintDirtyRegions(RepaintManager.java:785)
    at javax.swing.RepaintManager.paintDirtyRegions(RepaintManager.java:713)
    at javax.swing.RepaintManager.seqPaintDirtyRegions(RepaintManager.java:693)
    at javax.swing.SystemEventQueueUtilities$ComponentWorkRequest.run(SystemEventQueueUtilities.java:125)
    at java.awt.event.InvocationEvent.dispatch(InvocationEvent.java:209)
    at java.awt.EventQueue.dispatchEvent(EventQueue.java:597)
    at java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:269)
    at java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:184)
    at java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:174)
    at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:169)
    at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:161)
    at java.awt.EventDispatchThread.run(EventDispatchThread.java:122)
Exception in thread "Animation Thread" java.lang.NullPointerException
    at voce.SpeechRecognizer.getQueueSize(SpeechRecognizer.java:152)
    at voce.SpeechInterface.getRecognizerQueueSize(SpeechInterface.java:149)
    at gramtest.draw(gramtest.java:33)
    at processing.core.PApplet.handleDraw(Unknown Source)
    at processing.core.PApplet.run(Unknown Source)
    at java.lang.Thread.run(Thread.java:619)

PhiLho

Re: Voce Library / Speech Recognition

2 years ago

The error gramtest\grammar\test.gram (The system cannot find the path specified) looks quite explicit, no?

vijayakv

Re: Voce Library / Speech Recognition

2 years ago

I checked the location. I even tried different locations. Tried different ways of giving the paths. Nothing seems to work

Florian S..

Re: Voce Library / Speech Recognition

1 year ago

Pretty old topic but I uploaded a working example of a simple voce sketch here:

http://dl.dropbox.com/u/974773/VoiceRecognition.zip

You can alternatively check out my Speech to Text Library: http://stt.getflourish.com/

mimink21

Re: Voce Library / Speech Recognition

1 year ago

@ Florian

the above example is not working for some reason and returns the Illigal State Exception: Expected state Ready Actual State Deallocated, error when trying to configure the speach recogniser. Any ideas on how to fix that?

[Voce] Initializing synthesizer

[Voce] Initializing recognizer. This may take some time...

[Voce ERROR] Cannot configure speech recognizer:

Property Exception component:'jsgfGrammar' property:'grammarLocation' - value (C:\Users\I\Desktop\VoiceRecognition\VoiceRecognition/data/) is not a valid Resource

at edu.cmu.sphinx.util.props.ValidatingPropertySheet.setRaw(ValidatingPropertySheet.java:137)

at edu.cmu.sphinx.util.props.ConfigurationManager.setProperty(ConfigurationManager.java:250)

at voce.SpeechRecognizer.<init>(SpeechRecognizer.java:85)

at voce.SpeechInterface.init(SpeechInterface.java:79)

at VoiceRecognition.setup(VoiceRecognition.java:83)

at processing.core.PApplet.handleDraw(Unknown Source)

at processing.core.PApplet.run(Unknown Source)

at java.lang.Thread.run(Thread.java:662)

[Voce] Initialization complete

Exception in thread "Animation Thread" java.lang.NullPointerException

at voce.SpeechRecognizer.getQueueSize(SpeechRecognizer.java:152)

at voce.SpeechInterface.getRecognizerQueueSize(SpeechInterface.java:149)

at VoiceRecognition.draw(VoiceRecognition.java:88)

at processing.core.PApplet.handleDraw(Unknown Source)

at processing.core.PApplet.run(Unknown Source)

at java.lang.Thread.run(Thread.java:662)

Exception in thread "Recognition thread" java.lang.IllegalStateException: Expected state Ready actual state Deallocated

at edu.cmu.sphinx.recognizer.Recognizer.checkState(Recognizer.java:147)

at edu.cmu.sphinx.recognizer.Recognizer.recognize(Recognizer.java:113)

at edu.cmu.sphinx.recognizer.Recognizer.recognize(Recognizer.java:135)

at voce.SpeechRecognizer.run(SpeechRecognizer.java:129)

at java.lang.Thread.run(Thread.java:662)

vanguard29

Re: Voce Library / Speech Recognition

1 year ago

Still new to processing - but have been able to manage somewhat with a lot of the resources and examples that are available.

However, struggling with one item that I cannot find resolution on:

I am trying to get voce working but am getting the following message:

[Voce ERROR] Cannot configure speech recognizer:
Property Exception component:'jsgfGrammar' property:'grammarLocation' - value (C:/Users/User/Documents/Processing/libraries/voce/library/gram) is not a valid Resource
at edu.cmu.sphinx.util.props.ValidatingPropertySheet.setRaw(ValidatingPropertySheet.java:137)
at edu.cmu.sphinx.util.props.ConfigurationManager.setProperty(ConfigurationManager.java:250)
at voce.SpeechRecognizer.<init>(SpeechRecognizer.java:85)
at voce.SpeechInterface.init(SpeechInterface.java:79)
at VoiceRecognitionII.setup(VoiceRecognitionII.java:27)
at processing.core.PApplet.handleDraw(Unknown Source)
at processing.core.PApplet.run(Unknown Source)
at java.lang.Thread.run(Thread.java:662)
[Voce] Initialization complete

I'd like to understand what it means when it says that the grammar location is not a valid resource.

I saw another thread regarding Voce with the same type of question but no resolution.

pagapags

Re: Voce Library / Speech Recognition

1 year ago

Hi
i 'm experimenting this library it works quite well but i want to use a french language model (i'm french!)
I've downloaded the model lium_french_f0.tar.gz at
http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/

but i don't know how to use the differents files in the archive, how modifie the file voce.config.xml ?

Thank you for your help!

armageddi..

Re: Voce Library / Speech Recognition

11 months ago

Has anyone figured out successfully how to manage memory with this library (Voce)? I've been increasing allowed memory from preferences, but eventually I will still get an exception. I have attempted to teardown the session with destroy(), but have been unable to recreate it with init().

any ideas?

Top Reply

Response title

Attachments

New to this Portal?

Voce Library / Speech Recognition

Replies(14)

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Re: Voce Library / Speech Recognition

Statistics

Tags

Actions

Related Posts