Speech Recogniser
Hello,
I'm a student of final Year BSc. & thinking to do a project of Speech dictator Systm using Java. Can you help me about that system. I mean about the scope of the system. & an important thing is that I am also not more fimiliar with java.
Thanks in advance.
Is there any book through which I can be able to do Speech to Text by using JSAPI.
Similar Messages
-
Dear All,
I�m developing a speech recognizer cum synthesizer project. For that Im using sphinx4 as my recognizer and FreeTTS as synthesizer. Here[u] I need to know can I train my voice in sphinx 4. If yes pls help me.
I�ll be very glad if could find any solution for Heap space problem in Eclipse.
Are there any sites available with reference codes or full code for this?follow the below links...
http://freetts.sourceforge.net/docs/index.php
http://freetts.sourceforge.net/docs/jsapi_setup.html -
Null pointer when trying to initialise speech recognition
Hi all,
I am attempting to utilise the JSAPI for a project for display at my Uni that utilises freeTTS and also some Java speech recognition. Through the tutorials online (such as the Hello World) I have built my speech recognizer but as I try to allocate() for the speech recogniser the program gives me a null pointer.
The grammar file that I load into the file reader exists and I do not get a file not found exception. Can anyone see a blindingly obvious error that I am missing?
Code below. The rec.allocate() (third line after the try... is where i am getting my null pointer from.
Cheers
Mark
public BigEars(SpeakEasy gui){
mainGui = gui;
try {
EngineModeDesc desk = new EngineModeDesc(Locale.ENGLISH);
rec = Central.createRecognizer(desk);
rec.allocate();
FileReader reader = new FileReader("speechRecog/grammar.txt");
RuleGrammar rules = rec.loadJSGF(reader);
rules.setEnabled(true);
rec.addResultListener(this);
rec.commitChanges();
rec.requestFocus();
rec.resume();
catch (Exception e) {
message("There is a problem with this code.");
e.printStackTrace();
Hi dheeraj_chd,
I never got a reply to this so to move forward I actually incorporated the Sphinx4 speech recognition program into my project. I do not know if this is any help to you but I got it up and running OK with it.
http://cmusphinx.sourceforge.net/sphinx4/
I hope this helps. It does dramatically increase the size of the application you are writing but at least it works!
Cheers
Mark -
Does JMF support RTP packets being sent "Faster than real time"?
I have a situation where some stored audio is passed to a speech recogniser using RTP. This is all working well with JMF. However, since this operation is "offline" (i.e. no live person is actually speaking or hearing this audio stream) and the recognizer is capable of processing the audio very quickly, then the RTP stream could be sending the audio in "faster than real time". What settings in the following components would allow this?
DataSource _dataSource = Manager.createDataSource(source);
Processor _processor = Manager.createProcessor(_dataSource);
TrackControl[] trackControls = _processor.getTrackControls();
Codec codec[] = new Codec[3];
codec[0] = new com.ibm.media.codec.audio.rc.RCModule();
codec[1] = new com.ibm.media.codec.audio.ulaw.JavaEncoder();
codec[2] = new com.sun.media.codec.audio.ulaw.Packetizer();
((com.sun.media.codec.audio.ulaw.Packetizer) codec[2]).setPacketSize(160);
_processor.realize();
DataSource dataOutput = _processor.getDataOutput();
SendStream _sendStream = _rtpManager.createSendStream(dataOutput, 0);
_sendStream.start();
_processor.start();I tried "setRate" on the processor but this had no effect. getRate showed that it was still 1.0
Best Regards,
JamieI wrote my own RTP client in about an hour - (seemed simpler than navigating JMF options). It is very basic, but works as I want. The RTP server (the speech recognizer it able to consume the stream and gives exactly the same results).
package com.sss.mrcp;
import java.io.InputStream;
import java.net.DatagramPacket;
import java.net.DatagramSocket;
import java.net.InetAddress;
import java.util.Random;
public class RTP extends Thread {
InputStream is;
String address;
int port;
int localPort;
public RTP(InputStream is, int localPort, String address, int port) {
this.is = is;
this.address = address;
this.port = port;
this.localPort = localPort;
public void run() {
try {
DatagramSocket socket = new DatagramSocket(localPort);
Random r = new Random();
int sequenceNumber = r.nextInt();
int syncId = r.nextInt();
int timeStamp = 0;
int len = 256;
byte[] buf = new byte[len];
int code = 0;
int headerLength = 12;
while ((code = is.read(buf, headerLength, len - headerLength)) > -1) {
int i = 0;
buf[i++] = (byte) 0x80; // version info
buf[i++] = (byte) 0x08; // 8=alaw,0=ulaw
sequenceNumber++;
buf[i++] = (byte) (sequenceNumber / 0x100);
buf[i++] = (byte) (sequenceNumber % 0x100);
timeStamp += (len - 12);
int timeStampTop = (timeStamp / 0x10000);
buf[i++] = (byte) (timeStampTop / 0x100);
buf[i++] = (byte) (timeStampTop % 0x100);
int timeStampBottom = (timeStamp % 0x10000);
buf[i++] = (byte) (timeStampBottom / 0x100);
buf[i++] = (byte) (timeStampBottom % 0x100);
int syncIdTop = (syncId / 0x10000);
buf[i++] = (byte) (syncIdTop / 0x100);
buf[i++] = (byte) (syncIdTop % 0x100);
int syncIdBottom = (syncId % 0x10000);
buf[i++] = (byte) (syncIdBottom / 0x100);
buf[i++] = (byte) (syncIdBottom % 0x100);
DatagramPacket packet = new DatagramPacket(buf, code+headerLength, InetAddress.getByName(address), port);
socket.send(packet);
Thread.sleep(1); // this sets the speed of delivery "faster than real time"
} catch (Exception e) {
throw new RuntimeException(e);
} -
Speech recognition keyword not recognised
I have recently installed Montain lion and have set up and calibrated speech recognition. I very successfully issue voice commands to my Mac in order to open close applications etc. this all works very well as long as I do not use a keyword in order to activate it into the listening mode. I have tried several words including the default word, computer, but it just does not seem to recognise my keyword. Has anyone experienced a similar problem?
This is getting me a little frustrated and I wonder if anybody has experienced something similar and has found a solution thank you.
My daughter on a MacBook and using Snow Leopard has calibrated has voice recognition and uses her keyword successfully.
PaulLaunch the Console application in any of the following ways:
☞ Enter the first few letters of its name into a Spotlight search. Select it in the results (it should be at the top.)
☞ In the Finder, select Go ▹ Utilities from the menu bar, or press the key combination shift-command-U. The application is in the folder that opens.
☞ Open LaunchPad. Click Utilities, then Console in the icon grid.
Make sure the title of the Console window is All Messages. If it isn't, select All Messages from the SYSTEM LOG QUERIES menu on the left. If you don't see that menu, select
View ▹ Show Log List
from the menu bar.
Click the Clear Display icon in the toolbar. Then try the action that you're having trouble with again. Select any messages that appear in the Console window. Copy them to the Clipboard by pressing the key combination command-C. Paste into a reply to this message by pressing command-V.
When posting a log extract, be selective. In most cases, a few dozen lines are more than enough.
Please do not indiscriminately dump thousands of lines from the log into this discussion.
Important: Some private information, such as your name, may appear in the log. Anonymize before posting. -
Skype not recognising microphone or vice versa??
Hi, I can't get my microphone to work with Skype on my HP DX2300 Desktop PC. Windows XP PRO.
I have started using Skype, but so far only for texting. I have connected the microphone to the appropriate socket (microphone symbol on front of PC case). The Skype "Echo Sound Test Service" effectively tells me the microphone is not working or being recognised.
The microphone is working in that I can hear what I say into microphone coming out of PC speakers. However when I go to the Skype “Check your sound works” and click on check microphone the sound is no longer heard and there is nothing shown on the green bar (to indicate volume – if it worked).
On the windows “master volume” panel, front mic and mic volume are both not muted and volume set to max (have also tried half way).
From control panel, then “sounds and audio devices properties”, under sounds recording the default device is a Realtek HD audio input (selected from drop down menu with only that as an option).
From control panel, then “speech”, I can get to "speech properties" no problem. However there is only one tab ("Text to speech"), no "speech recognition tab". There is an "audio output" button, but no "audio input". If I could get this tab to appear somehow, would Skype then recognize it perhaps?
I have rebooted (more than once!) to check if that will wake it up somehow, but no!
Do I need another (??) microphone driver installed? Or is this a known Skype microphone recognition problem? (searching for this on internet couldn’t find anything). Not being very clever at computers I thought it best to seek advice first!Thanks to everyone for all the advice.
The skype tools / options / audio settings / microphone only had one in drop down menu - Realtek HD audio input, same as on the windows settings. So that looks logical and OK.
HOWEVER I have played around again and I now have it working. I think I found yet another place where audio / mic settings are under control panel / sounds and audio devices / audio tab then sound recording. I say "I think" because I tried so many mute / unmute and volume settings I am not really sure which wasn't correct. It seems really ridiculous how many places can affect microphone performance!
Incidentally someone on a different forum also suggested trying a USB mic, but another person said don't use one of them as they are rubbish. I don't know, just passing on their comment.
Anyway thanks again all for your help
Cheers
Rogerthedodger -
hi i have a problem when plugging in my ipod touch, it says in a little speech bubble at the bottom corner "usb device not recognised, one of the usb devices attached to this computer has malfunctioned, and windows does not recognise it"
ive tryed everything, ive updated the driver, ive uninstalled the driver, and nothing comes up in itunes. the ipod does nothing when plugged in, it does not charge as well when plugged in. ived tryed in itunes the diagnostic test but when i click it it says "itunes has encountered a problem and needs to close"
please help me!!!!
thanks, calpol55I am having the same problem. I went through all of the steps already listed (updating drivers, uninstalling drivers, uninstalling iTunes and all related software, reinstalling) and still no luck. I also tried syncing to a new computer, but am having the same problems. My Touch does at least charge when plugged into either computer, but is not recognized by either computer in iTunes to actually sync. The problem seemed to start after I updated iTunes on both computers, so I tried going back to the previous version of iTunes, but then I couldn't get iTunes to open because my library had been updated by a newer version of iTunes, so the old version wouldn't work anymore.
My Touch is not yet completely worthless since I can still charge and download apps and music straight to my Touch, but I can't organize anything very well and can't easily make new playlists or add new playlists from iTunes. -
SAP transaction enabled by speech recognition
hi
i'm looking into possible ways of approaching to an requirement that would enable users to perform transactions in the SAP GUI by giving commands (may be via voice recognition). I tried to check for materials that could help me to start with but unable to trace one. If this problem statemetn can be disucced i could get some ideas on how to proceed. so looking fwd for ur resposne.
thkx
PrabhuHi Prabhu,
As far as I understand there are two parts of it-
1. Invoke/trigger SAP applications from .NET.
2. Having an event to trap and trigger the execution.
Now first point (1) can be acheived through either SOAP (webservices) or RFC (.NET Connector) based communication. With this you will be able to invoke RFC/BAPI from .NET applications.
Regarding (2) you need to use SAPI liabrary (provided by Microsoft) to recognise the speech phrases and raise the event. And inside the even handler you can trigger the execution of SAP application.
Regards. -
Speech Recognition Not Working Well
Not matter how hard I try to get my speech recognition to work on my MacBook Pro, it is very temperamental! Even when I am in a quiet space it will respond, but after a while it won't. I've tried calibrating it, etc but doesn't make a huge difference.
What makes me think there is a problem is the fact that when speech recognition is activated there is supposed to be lights that light up (on the actual speech recognition widget thing - as I have noticed on various other MacBook Pro users' YouTube videos). But for mine, the bottom, blue light only lights up; and no matter how loud I shout at it, the blue light DOESN'T then go on to the green light. However, when I calibrate it, my speech is recognised as being in the 'green area'; so I am speaking t the right level.
I appreciate your help!Not matter how hard I try to get my speech recognition to work on my MacBook Pro, it is very temperamental! Even when I am in a quiet space it will respond, but after a while it won't. I've tried calibrating it, etc but doesn't make a huge difference.
What makes me think there is a problem is the fact that when speech recognition is activated there is supposed to be lights that light up (on the actual speech recognition widget thing - as I have noticed on various other MacBook Pro users' YouTube videos). But for mine, the bottom, blue light only lights up; and no matter how loud I shout at it, the blue light DOESN'T then go on to the green light. However, when I calibrate it, my speech is recognised as being in the 'green area'; so I am speaking t the right level.
I appreciate your help! -
Speech Recognition just won't load in WIN 8.1?
Am new to WIN 8.1 - can't get Speech Recognition to load/run... Will not run either from Control Panel, Charms (search for Speech Recognition, click Windows speech recognition or from icon in Task Bar nor from START screen.. BUT.. will run/load when
rebooted (but often won't work/recognise speech correctly (What was that appears??)) as it then automatically appears on bootup; even though it would not run/load in previous session before the reboot.. !!
Am running HP spectre i5, 4 meg 128GB... This failure is very frustrating - lots of other reports of this occurring but can't find any solutions specific to WIN 8.1.. PLEASE HELP - use dictation lot as typing is abysmal!!Hi.. yep, have seen the video thank you.. the problem is NOT knowing how to use it.. (Have been in computers and using speech recognition, mainly Nuance DS Professional for
ages..)
The problem I have is in LOADING the application… sometimes it will load on the click of the mouse (or touch of the screen on this HP SPECTRE) – be it loaded from the task
bar icon that I set up, from the Windows Speech Recognition command vis the CHARMS or even from the START tiles.. other times it will not!! Must frustrating (will have to buy a new Nuance DNS professional as windows 8.1 is not a platform for DNS Version
10 that I have used for ages – needs !! or maybe go back to WIN&7??)
Couple of things I have noticed that may help others is that the programme may not load if one clicks the icon too quickly.. I find that hovering the mouse over the icon and
waiting until “Windows speech recognition” appears, THEN clicking the icon works at times.. after the small win Speech Recognition mode (grey) icon is closed by pressing the red “close” button then it is hard to get the programme to load again.. then one must
go to Task manager and stop the Speech Recognition programme by clicking on the end task button..
So.. it’s the initial loading and running of the programme that concerns me.. perhaps the bods at MS could look at how memory is allocated to this programme and why when
closing the Speech Recognition programme from the “grey” speech recognition mode button it is subsequently “hard” to reload it again and the programme seemingly seems to still run in Task Manager after this close button has been pressed…?? (But,
I won’t hold my breath)…
Cheers -
Screensaver password & speech recognition
I've seen from older forum messages that a screensaver password can be set in in System Preferences > Security. I've found this doesn't actually work and I wonder if it is because the one account on my Mac, an admin account, does not itself have a password? I don't want a user account password as I'm the only user and never really take my MacBook out the house. What do you think? User password or not?
Also I would like to use the Speech Recognition feature even though it often doesn't recognise requests for the time and date (so I use a regular clock in the bar at the top. The thing is the Mac always starts up with the round gray speech icon on the deskop and I always have to double click it to get it in on the dock. Can this be changed so it starts when the computer starts and stays in the dock?When you go to the System Prefs > Security, check off the box that says "Require password to wake this computer..." etc. Then, in order to have this setup, yes, you must have a password for the one account on your computer.
I can't help you with the Speech Recognition thing, sorry.
Good Luck! -
Ignore voice commands / Speech Recognition Server timeout
I'm fairly new to AppleScript but I've found it really entertaining and gloriously simple to pick up so far. I've been using it mostly to make my own speakable items for the Mac's voice control, and I've managed to write some basic things like voice commands to set/change volume and brightness. My goal at this point is to be able to do the majority of things I want to do on my computer by voice only. Sue me - I just rewatched Iron Man and I really wish I had a JARVIS system right now.
This means that the computer must always be listening for commands (I have set it to 'listen continuously with keyword', and set the keyword as 'optional before commands'). It defeats the purpose if I have to walk over and hit a key to start listening for commands. At the same time, I don't want to have to speak a keyword, because I will invariably forget to do so and it's also an added hassle (especially when I have several commands to say - I don't want to have to say the keyword before each command).
You might have an idea of where this is going. Obviously, if the computer is always listening, it will pick up on normal conversation and try to interpret it.
I could just deactivate voice commands when I'm not using it, but as I said earlier, I don't want to have to either hit a key or say a keyword. In other words, I want to be able to activate and deactivate voice commands by voice. Deactivating is easy. Activating is what presents an interesting problem, because if it's deactivated, how will it hear my reactivation command?
Thus, the first part of my question: is there a way - any way at all - to get voice commands to ignore commands until given some keyword, short of literally changing its settings to listen for a keyword before the command?
I decided to try to use speech recognition. This must, I think, be involved in some way, because as I said earlier, this presents the unique problem of having voice commands deactivated yet still able to recognise the reactivation command. I had noticed that while the computer is listening for a specific command, it ignores anything that isn't what it is listening for. I tried to use this to my advantage and wrote a script to listen for a reactivation command; until the reactivation command was given, the computer would ignore everything else. The problem is that the speech recognition server times out after two minutes. I have tried to increase this, but to no avail (see below for my attempts).
Thus, the second part of my question: assuming there is no other answer to my first question, is there a way to get speech recognition to listen indefinitely?
Here are the two things I tried to make the timeout last longer, specifically for five minutes (300 seconds) in both cases. Neither worked; both timed out after 120 seconds.
tell application "SpeechRecognitionServer"
set userinput to listen for {"resume voice commands"} giving up after 300
end tell
and
with timeout of 300 seconds
set userinput to listen for {"resume voice commands"}
end timeoutUPDATE: I have since come up with an alternate solution. I created two speakable items, one for 'deactivation' and one for 'activation'. The deactivation command uses UI scripting to set voice commands to 'keyword required' mode (i.e. the keyword is required before each command); the activation command simply sets it back to 'keyword optional' mode.
I figure that as long as I choose a keyword that's unique enough that it (and things that sound like it) won't come up too often in conversation, the computer will ignore anything I say once I activate the keyword requirement. Then, I only need to say the keyword once along with the reactivation command to bring it out of this 'ignore commands' state.
In a way, this is actually better, because it allows me to continue to use voice commands if I really need to, as opposed to having to say the reactivation command to get my computer to listen to me, saying my intended command, and then saying the deactivation command to make it ignore me again.
All the same, if anyone has answers to any of my two original questions, please don't hesitate to share your knowledge! It might come in handy later! -
Speech Recognition - wouldn't quit
The Speech recognition function wouldn't disappear after a few tries - in fact, it stayed on the desktop but only listened to my voice a couple of times before no longer recognising it...had to restart the computer just to get rid of it.
sircounttiger,
WHADSA madda wid da way Noo Yawkers tawk?
Accents are not supposed to make a difference, but try the techniques mentioned in some of these Knowledge Base Articles.
;~) -
Wondering if using the Apple ID finger print on the ipad, is there a way to set it up so that parents can set their fingers to be the only ones able to purchase from app store and itunes, but still able to recognise the kids fingerprints to turn on the ipad and play with apps?
Not currently a function of iOS. However, you could set a restriction on purchases
using a separate passcode in Restrictions. No one could make a purchase without
that passcode. But you cannot tie the Restrictions to a single fingerprint or subset
of fingerprints. Any fingerprint that is registered to open the iPad gives full access to
all non-restriced apps/functions on the iPad. -
How can I convert an audio file (speech) into a text?
Hello everybody!
Can someone explain how I can convert a garageband file (voice speech) into a text? My Mac is a Mac OS X 10.5.8 version, so I don't have programs such as mountain Lion. I thought to use googlevoice. Is this option available? If yes, how can I use it?
Thanks.Hello, I only find google voice available for Abdroid!?
http://www.ehow.com/info_10033225_google-voice-system-requirements-android.html
Some possibilitities, not sure if they have 10.5.8 compatble versions anymore...
http://atmac.org/speech-to-text-dictation-software-for-os-x
Some reviews of later Dragon Speak...
http://www.finetunedmac.com/forums/ubbthreads.php?ubb=showflat&Number=22962
Maybe you are looking for
-
Change log issues-2 images for a single requests
Hi , in change log table for a single request i found 2 before images and two after images, is this normal behaviour if not when can we see the such type of scenarios. because it leads to zero records when it isn updated in to the further data target
-
I am using a desktop PC; was Windows 8 64 bit; upgraded this morning to Windows 8.1. I am using Microsoft Office 2010; my contacts, tasks and calendars are in iCloud. Now when I am in Outlook, it will not open contacts, calendar or tasks .. It tells
-
Toshiba satalite L305D starts then shuts off. Need help.
Basically the computer will start then about 10-20 sec later will shut off. No display what so ever. Doesnt seem like the computer is getting to POST. Ive done my research, im just looking for some things to try. Things Ive tried. * Changed power ad
-
Dear all, I am using Labview 8.5. I am trying to get system date. I use Format Date/Time String tool in a "%Y%m%d" format. The PROBLEM is the Format Date/Time String return 'YYYYMMDD' only. Please see my attachment to see. Please help me with this,
-
I am new to Macs or Mac books can anyone help with
i have bought a Mac book, its not new but its been fully refurbished But as I am completely new to the operating system, can anyone help with book marks, downloading pictures from a camera, using MS word I am hoping to use this mac book on my travels