Develop Reference

how to execute voice google search

I can't search in google using my voice. I disabled search by default and can only be enabled by saying the word "search". I separated the words and phrases to be searched for to another file so that it wont get mixed with my recognition file and the response file. I placed the path file under the if statement of "search" so that it can only be access when the I speak "search"
public partial class Form1 : Form
{
//user and jarvis texts
string[] grammarFile = (File.ReadAllLines(#"C:\Friday AI\user.txt.txt"));
string[] responseFile = (File.ReadAllLines(#"C:\Friday AI\jarvis.txt.txt"));
//speech synthesis
SpeechSynthesizer speechSynth = new SpeechSynthesizer();
//speech recognition
Choices grammarList = new Choices();
SpeechRecognitionEngine speechRecognition = new SpeechRecognitionEngine();
public Boolean search = false;
public Form1()
{
//initialize grammarfile
grammarList.Add(grammarFile);
Grammar grammar = new Grammar(new GrammarBuilder(grammarList));
try
{
speechRecognition.RequestRecognizerUpdate();
speechRecognition.LoadGrammar(grammar);
speechRecognition.SpeechRecognized += rec_SpeechRecognized;
speechRecognition.SetInputToDefaultAudioDevice();
speechRecognition.RecognizeAsync(RecognizeMode.Multiple);
}
catch
{
return;
}
private void rec_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
string result = e.Result.Text;
int resp = Array.IndexOf(grammarFile, result);
if (search)
{
Process.Start(#"chrome.exe", "--incognito https://www.google.com/search?q=" + result);
label5.Text = "Enabled";
}
if (wake == true)
{
if (result.Contains("search"))
{
search = true;
string[] globalsearch = (File.ReadAllLines(#"C:\Friday AI\global search words.txt"));
grammarList.Add(globalsearch);
label5.Text = "Enabled";
}

How to convert speech to text?

I am trying to develop the following functionality.
The first task to convert text to voice - DONE
The second task to convert voice to text - Getting issue
The third task to implement these both on the given chat board where already AI chat is
I am using following code to get the text from voice/speech.
I am getting the result but is not proper which I want.
Please check below code snippet.
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading;
using System.Speech.Recognition;
using System.Speech.Synthesis;
namespace StartingWithSpeechRecognition
{
class Program
{
static SpeechRecognitionEngine _recognizer = null;
static ManualResetEvent manualResetEvent = null;
static void Main(string[] args)
{
manualResetEvent = new ManualResetEvent(false);
Console.WriteLine("To recognize speech, and write 'test' to the console, press 0");
Console.WriteLine("To recognize speech and make sure the computer speaks to you, press 1");
Console.WriteLine("To emulate speech recognition, press 2");
Console.WriteLine("To recognize speech using Choices and GrammarBuilder.Append, press 3");
Console.WriteLine("To recognize speech using a DictationGrammar, press 4");
Console.WriteLine("To get a prompt building example, press 5");
ConsoleKeyInfo pressedKey = Console.ReadKey(true);
char keychar = pressedKey.KeyChar;
Console.WriteLine("You pressed '{0}'", keychar);
switch (keychar)
{
case '0':
RecognizeSpeechAndWriteToConsole();
break;
case '1':
RecognizeSpeechAndMakeSureTheComputerSpeaksToYou();
break;
case '2':
EmulateRecognize();
break;
case '3':
SpeechRecognitionWithChoices();
break;
case '4':
SpeechRecognitionWithDictationGrammar();
break;
case '5':
PromptBuilding();
break;
default:
Console.WriteLine("You didn't press 0, 1, 2, 3, 4, or 5!");
Console.WriteLine("Press any key to continue . . .");
Console.ReadKey(true);
Environment.Exit(0);
break;
}
if (keychar != '5')
{
manualResetEvent.WaitOne();
}
if (_recognizer != null)
{
_recognizer.Dispose();
}
Console.WriteLine("Press any key to continue . . .");
Console.ReadKey(true);
}
#region Recognize speech and write to console
static void RecognizeSpeechAndWriteToConsole()
{
_recognizer = new SpeechRecognitionEngine();
_recognizer.LoadGrammar(new Grammar(new GrammarBuilder("test"))); // load a "test" grammar
_recognizer.LoadGrammar(new Grammar(new GrammarBuilder("exit"))); // load a "exit" grammar
_recognizer.SpeechRecognized += _recognizeSpeechAndWriteToConsole_SpeechRecognized; // if speech is recognized, call the specified method
_recognizer.SpeechRecognitionRejected += _recognizeSpeechAndWriteToConsole_SpeechRecognitionRejected; // if recognized speech is rejected, call the specified method
_recognizer.SetInputToDefaultAudioDevice(); // set the input to the default audio device
_recognizer.RecognizeAsync(RecognizeMode.Multiple); // recognize speech asynchronous
}
static void _recognizeSpeechAndWriteToConsole_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
if (e.Result.Text == "test")
{
Console.WriteLine("test");
}
else if (e.Result.Text == "exit")
{
manualResetEvent.Set();
}
}
static void _recognizeSpeechAndWriteToConsole_SpeechRecognitionRejected(object sender, SpeechRecognitionRejectedEventArgs e)
{
Console.WriteLine("Speech rejected. Did you mean:");
foreach (RecognizedPhrase r in e.Result.Alternates)
{
Console.WriteLine(" " + r.Text);
}
}
#endregion
#region Recognize speech and make sure the computer speaks to you (text to speech)
static void RecognizeSpeechAndMakeSureTheComputerSpeaksToYou()
{
_recognizer = new SpeechRecognitionEngine();
_recognizer.LoadGrammar(new Grammar(new GrammarBuilder("hello computer"))); // load a "hello computer" grammar
_recognizer.SpeechRecognized += _recognizeSpeechAndMakeSureTheComputerSpeaksToYou_SpeechRecognized; // if speech is recognized, call the specified method
_recognizer.SpeechRecognitionRejected += _recognizeSpeechAndMakeSureTheComputerSpeaksToYou_SpeechRecognitionRejected;
_recognizer.SetInputToDefaultAudioDevice(); // set the input to the default audio device
_recognizer.RecognizeAsync(RecognizeMode.Multiple); // recognize speech asynchronous
}
static void _recognizeSpeechAndMakeSureTheComputerSpeaksToYou_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
if (e.Result.Text == "hello computer")
{
SpeechSynthesizer speechSynthesizer = new SpeechSynthesizer();
speechSynthesizer.Speak("hello user");
speechSynthesizer.Dispose();
}
manualResetEvent.Set();
}
static void _recognizeSpeechAndMakeSureTheComputerSpeaksToYou_SpeechRecognitionRejected(object sender, SpeechRecognitionRejectedEventArgs e)
{
if (e.Result.Alternates.Count == 0)
{
Console.WriteLine("No candidate phrases found.");
return;
}
Console.WriteLine("Speech rejected. Did you mean:");
foreach (RecognizedPhrase r in e.Result.Alternates)
{
Console.WriteLine(" " + r.Text);
}
}
#endregion
#region Emulate speech recognition
static void EmulateRecognize()
{
_recognizer = new SpeechRecognitionEngine();
_recognizer.LoadGrammar(new Grammar(new GrammarBuilder("emulate speech"))); // load "emulate speech" grammar
_recognizer.SpeechRecognized += _emulateRecognize_SpeechRecognized;
_recognizer.EmulateRecognize("emulate speech");
}
static void _emulateRecognize_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
if (e.Result.Text == "emulate speech")
{
Console.WriteLine("Speech was emulated!");
}
manualResetEvent.Set();
}
#endregion
#region Speech recognition with Choices and GrammarBuilder.Append
static void SpeechRecognitionWithChoices()
{
_recognizer = new SpeechRecognitionEngine();
GrammarBuilder grammarBuilder = new GrammarBuilder();
grammarBuilder.Append("I"); // add "I"
grammarBuilder.Append(new Choices("like", "dislike")); // load "like" & "dislike"
grammarBuilder.Append(new Choices("dogs", "cats", "birds", "snakes", "fishes", "tigers", "lions", "snails", "elephants")); // add animals
_recognizer.LoadGrammar(new Grammar(grammarBuilder)); // load grammar
_recognizer.SpeechRecognized += speechRecognitionWithChoices_SpeechRecognized;
_recognizer.SetInputToDefaultAudioDevice(); // set input to default audio device
_recognizer.RecognizeAsync(RecognizeMode.Multiple); // recognize speech
}
static void speechRecognitionWithChoices_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
Console.WriteLine("Do you really " + e.Result.Words[1].Text + " " + e.Result.Words[2].Text + "?");
manualResetEvent.Set();
}
#endregion
#region Speech recognition with DictationGrammar
static void SpeechRecognitionWithDictationGrammar()
{
_recognizer = new SpeechRecognitionEngine();
_recognizer.LoadGrammar(new Grammar(new GrammarBuilder("exit")));
_recognizer.LoadGrammar(new DictationGrammar());
_recognizer.SpeechRecognized += speechRecognitionWithDictationGrammar_SpeechRecognized;
_recognizer.SetInputToDefaultAudioDevice();
_recognizer.RecognizeAsync(RecognizeMode.Multiple);
}
static void speechRecognitionWithDictationGrammar_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
if (e.Result.Text == "exit")
{
manualResetEvent.Set();
return;
}
Console.WriteLine("You said: " + e.Result.Text);
}
#endregion
#region Prompt building
static void PromptBuilding()
{
PromptBuilder builder = new PromptBuilder();
builder.StartSentence();
builder.AppendText("This is a prompt building example.");
builder.EndSentence();
builder.StartSentence();
builder.AppendText("Now, there will be a break of 2 seconds.");
builder.EndSentence();
builder.AppendBreak(new TimeSpan(0, 0, 2));
builder.StartStyle(new PromptStyle(PromptVolume.ExtraSoft));
builder.AppendText("This text is spoken extra soft.");
builder.EndStyle();
builder.StartStyle(new PromptStyle(PromptRate.Fast));
builder.AppendText("This text is spoken fast.");
builder.EndStyle();
SpeechSynthesizer synthesizer = new SpeechSynthesizer();
synthesizer.Speak(builder);
synthesizer.Dispose();
}
#endregion
}
}
If this is the wrong way then please suggest me right way or any reference link or tutorial will be highly appreciated.

The System.Speech.Recognition is an old API.
I think you have to use Google Speech API: https://cloud.google.com/speech/docs/basics Or MS Bing speech API: https://azure.microsoft.com/en-us/services/cognitive-services/speech/
I preferred the Google API. And here is very small example:
using Google.Apis.Auth.OAuth2;
using Google.Cloud.Speech.V1;
using Grpc.Auth;
using System;
var speech = SpeechClient.Create( channel );
var response = speech.Recognize( new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "hu",
}, RecognitionAudio.FromFile( "888.wav" ) );
foreach ( var result in response.Results )
{
foreach ( var alternative in result.Alternatives )
{
Console.WriteLine( alternative.Transcript );
}
}
But you can find more samples:
https://cloud.google.com/speech/docs/samples
Regrads

c# - Record audio on keydown

The problem is simple: I want to record audio using the microphone when and only when a key is held down. When the key is lifted I want it to stop recording. Then pass this recording to the speech recognition.
The issue is when I press and hold the Z button, It will go into the gkh_KeyUp event and continue to run this code. I want to simply record while it is held, not run this record function a bunch of times.
I want to use this in conjunction with Microsofts speech recognition.
using System.Speech.Recognition;
public partial class Form1 : Form
{
SpeechRecognitionEngine recognizer = new SpeechRecognitionEngine();
Grammar dictationGrammar = new DictationGrammar();
public Form1()
{
InitializeComponent();
globalKeyboardHook gkh = new globalKeyboardHook();
gkh.HookedKeys.Add(Keys.Z);
//gkh.HookedKeys.Add(Keys.B);
gkh.KeyDown += new KeyEventHandler(gkh_KeyDown);
gkh.KeyUp += new KeyEventHandler(gkh_KeyUp);
recognizer = new SpeechRecognitionEngine();
dictationGrammar = new DictationGrammar();
recognizer.LoadGrammar(dictationGrammar);
}
void gkh_KeyUp(object sender, KeyEventArgs e)
{
textBox1.Text = "Up" + e.KeyCode.ToString();
try
{
RecognitionResult result = recognizer.Recognize();
textBox1.Text = result.Text;
}
catch (InvalidOperationException exception)
{
textBox1.Text = String.Format("Could not recognize input from default aduio device. Is a microphone or sound card available?\r\n{0} - {1}.", exception.Source, exception.Message);
}
e.Handled = true;
}
void gkh_KeyDown(object sender, KeyEventArgs e)
{
textBox1.Text += "Down" + e.KeyCode.ToString();
try
{
//recognizer.SetInputToDefaultAudioDevice();
recognizer.SetInputToAudioStream()
}
catch (InvalidOperationException exception)
{
button1.Text = String.Format("Could not recognize input from default aduio device. Is a microphone or sound card available?\r\n{0} - {1}.", exception.Source, exception.Message);
}
e.Handled = true;
}
private void button1_Click(object sender, EventArgs e)
{
SpeechRecognitionEngine recognizer = new SpeechRecognitionEngine();
Grammar dictationGrammar = new DictationGrammar();
recognizer.LoadGrammar(dictationGrammar);
try
{
button1.Text = "Speak Now";
recognizer.SetInputToDefaultAudioDevice();
//recognizer.SetInputToAudioStream;
RecognitionResult result = recognizer.Recognize();
textBox1.Text = result.Text;
}
catch (InvalidOperationException exception)
{
button1.Text = String.Format("Could not recognize input from default aduio device. Is a microphone or sound card available?\r\n{0} - {1}.", exception.Source, exception.Message);
}
finally
{
recognizer.UnloadAllGrammars();
}
}
private void textBox1_TextChanged(object sender, EventArgs e)
{
}
Keyboard hook: http://www.codeproject.com/Articles/19004/A-Simple-C-Global-Low-Level-Keyboard-Hook

There is no difference between real very frequent keypresses and keypresses emulated when you hold the button.
You'd need to use a timeout, if the down was not emitted after 0.5 seconds after up, you stop the recording.
You can access hold state of the key if you still want to use a hook, but you need to use a bit lower level access. You can explore WM_KEYDOWN event and look for a bit 30 of the key state:
How to disable WM_KEYDOWN repeat event for Shift/Ctrl/Alt key?

Getting Error object reference not set to an instance of the object [duplicate]

This question already has answers here:
What is a NullReferenceException, and how do I fix it?
(27 answers)
Closed 7 years ago.
I'm creating windows form speech recolonization application but somehow not able to fix the object reference issue:
Can anyone please tell where I'm going wrong, as I'm getting Getting Error object reference not set to an instance of the object in the below code.
public partial class Form1 : Form
{
SpeechSynthesizer ss = new SpeechSynthesizer();
PromptBuilder pb = new PromptBuilder();
SpeechRecognitionEngine sre = new SpeechRecognitionEngine();
Choices list;
public Form1()
{
InitializeComponent();
}
private void btnStart_Click(object sender, EventArgs e)
{
btnStart.Enabled = false;
btnStop.Enabled = true;
try
{
list.Add(new string[] { "Hello", "Open Chrome", "Close", "What is the current time", "Thank You" });
Grammar gr = new Grammar(new GrammarBuilder(list));
try
{
sre.RequestRecognizerUpdate();
sre.LoadGrammar(gr);
sre.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(sre_SpeechRecognized);
sre.SetInputToDefaultAudioDevice();
sre.RecognizeAsync(RecognizeMode.Multiple);
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Exception Caught");
}
}
catch (Exception exception)
{
MessageBox.Show(exception.Message, "Exception Caught");
}
}
void sre_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
switch (e.Result.Text.ToString())
{
case "Hello":
ss.SpeakAsync("Hello There");
break;
case "Open Chrome":
System.Diagnostics.Process.Start("Chrome", "https://www.google.com");
break;
case "Close":
Application.Exit();
break;
case "What is the current time":
ss.SpeakAsync("Current time is :" + DateTime.UtcNow.ToLongDateString());
break;
case "Thank You":
ss.SpeakAsync("Thank You for using this service");
break;
default:
ss.SpeakAsync("Please correct your choice");
break;
}
txtContents.Text = e.Result.Text.ToString() + Environment.NewLine;
}
private void btnStop_Click(object sender, EventArgs e)
{
sre.RecognizeAsyncStop();
btnStart.Enabled = true;
btnStop.Enabled = false;
}
}

Instead of
Choices list;
do
Choices list = new Choices();
Reason:
You use list even before it is initialized.
list.Add(new string[] { "Hello", "Open Chrome", "Close", "What is the current time", "Thank You" });

Erratic behaviour of voice synthesis in WinRT

I have a universal app the uses voice synthesis. Running under WP8.1, it works fine, but as soon as I try Win8.1 I start getting strange behaviour. The actual voice seems to speak once, however, on the second run (within the same app), the following code hangs:
string toSay = "hello";
System.Diagnostics.Debug.WriteLine("{0}: Speak {1}", DateTime.Now, toSay);
using (SpeechSynthesizer synth = new SpeechSynthesizer())
{
System.Diagnostics.Debug.WriteLine("{0}: After sythesizer instantiated", DateTime.Now);
var voiceStream = await synth.SynthesizeTextToStreamAsync(toSay);
System.Diagnostics.Debug.WriteLine("{0}: After voice stream", DateTime.Now);
The reason for the debug statements is that the code seems to have an uncertainty principle to it. That is, when I debug through it, the code executes and passes the SynthesizeTextToStreamAsync statement. However, when the breakpoits are removed, I only get the debug statement preceding it - never the one after.
The best I can deduce is that during the first run through something bad happens (it does claim to complete and actually speaks the first time), then it gets stuck and can't play any more. The full code looks similar to this:
string toSay = "hello";
System.Diagnostics.Debug.WriteLine("{0}: Speak {1}", DateTime.Now, toSay);
using (SpeechSynthesizer synth = new SpeechSynthesizer())
{
System.Diagnostics.Debug.WriteLine("{0}: After sythesizer instantiated", DateTime.Now);
var voiceStream = await synth.SynthesizeTextToStreamAsync(toSay);
System.Diagnostics.Debug.WriteLine("{0}: After voice stream", DateTime.Now);
MediaElement mediaElement;
mediaElement = rootControl.Children.FirstOrDefault(a => a as MediaElement != null) as MediaElement;
if (mediaElement == null)
{
mediaElement = new MediaElement();
rootControl.Children.Add(mediaElement);
}
mediaElement.SetSource(voiceStream, voiceStream.ContentType);
mediaElement.Volume = 1;
mediaElement.IsMuted = false;
var tcs = new TaskCompletionSource<bool>();
mediaElement.MediaEnded += (o, e) => { tcs.TrySetResult(true); };
mediaElement.MediaFailed += (o, e) => { tcs.TrySetResult(true); };
mediaElement.Play();
await tcs.Task;

Okay - I think I managed to get this working... although I'm unsure why.
using (SpeechSynthesizer synth = new SpeechSynthesizer())
{
var voiceStream = await synth.SynthesizeTextToStreamAsync(toSay);
MediaElement mediaElement;
mediaElement = rootControl.Children.FirstOrDefault(a => a as MediaElement != null) as MediaElement;
if (mediaElement == null)
{
mediaElement = new MediaElement();
rootControl.Children.Add(mediaElement);
}
mediaElement.SetSource(voiceStream, voiceStream.ContentType);
mediaElement.Volume = 1;
mediaElement.IsMuted = false;
var tcs = new TaskCompletionSource<bool>();
mediaElement.MediaEnded += (o, e) => { tcs.TrySetResult(true); };
mediaElement.Play();
await tcs.Task;
// Removing the control seems to free up whatever is locking
rootControl.Children.Remove(mediaElement);
}

I am not sure what program language you are using. However this may help. This is in C# so this could help lead you in the right direction.
namespace Alexis
{
public partial class frmMain : Form
{
SpeechRecognitionEngine _recognizer = new SpeechRecognitionEngine();
SpeechSynthesizer Alexis = new SpeechSynthesizer();
SpeechRecognitionEngine startlistening = new SpeechRecognitionEngine();
DateTime timenow = DateTime.Now;
}
//other coding such as InitializeComponent and others.
//
//
//
//
private void frmMain_Load(object sender, EventArgs e)
{
_recognizer.SetInputToDefaultAudioDevice();
_recognizer.LoadGrammarAsync(new Grammar(new GrammarBuilder(new Choices(File.ReadAllLines(#"Default Commands.txt")))));
_recognizer.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(Shell_SpeechRecognized);
_recognizer.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(Social_SpeechRecognized);
_recognizer.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(Web_SpeechRecognized);
_recognizer.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(Default_SpeechRecognized);
_recognizer.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(AlarmClock_SpeechRecognized);
_recognizer.LoadGrammarAsync(new Grammar(new GrammarBuilder(new Choices(AlarmAM))));
_recognizer.LoadGrammarAsync(new Grammar(new GrammarBuilder(new Choices(AlarmPM))));
_recognizer.SpeechDetected += new EventHandler<SpeechDetectedEventArgs>(_recognizer_SpeechDetected);
_recognizer.RecognizeAsync(RecognizeMode.Multiple);
startlistening.SetInputToDefaultAudioDevice();
startlistening.LoadGrammarAsync(new Grammar(new GrammarBuilder(new Choices("alexis"))));
startlistening.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(startlistening_SpeechRecognized);
//other stuff here..... Then once you have this then you can generate a method then with your code as follows
//
//
//
private void Default_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
{
int ranNum;
string speech = e.Result.Text;
switch (speech)
{
#region Greetings
case "hello":
case "hello alexis":
timenow = DateTime.Now;
if (timenow.Hour >= 5 && timenow.Hour < 12)
{ Alexis.SpeakAsync("Goodmorning " + Settings.Default.User); }
if (timenow.Hour >= 12 && timenow.Hour < 18)
{ Alexis.SpeakAsync("Good afternoon " + Settings.Default.User); }
if (timenow.Hour >= 18 && timenow.Hour < 24)
{ Alexis.SpeakAsync("Good evening " + Settings.Default.User); }
if (timenow.Hour < 5)
{ Alexis.SpeakAsync("Hello " + Settings.Default.User + ", it's getting late"); }
break;
case "whats my name":
case "what is my name":
Alexis.SpeakAsync(Settings.Default.User);
break;
case "stop talking":
case "quit talking":
Alexis.SpeakAsyncCancelAll();
ranNum = rnd.Next(1, 2);
if (ranNum == 2)
{ Alexis.Speak("sorry " + Settings.Default.User); }
break;
}
}
instead of using the commands in the code. I recommend that you use a text document. once you have that then you can add your own commands to it then put it in code. Also reference the System.Speech.
I hope this helps on getting you on the right track.