1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
|
using
System;
using
System.Collections.Generic;
using
System.ComponentModel;
using
System.Data;
using
System.Drawing;
using
System.Linq;
using
System.Text;
using
System.Windows.Forms;
using
System.Threading;
using
SpeechLib; //NET2.0 引用 Speech sdk 5.1 在COM选项卡里面的Microsoft Speech object library引用 已经有11.0版本
using
System.Speech;
using
System.Speech.Recognition;
using
System.Speech.Synthesis;
namespace
Speech
{ /// <summary>
/// 20140427
/// 涂聚文
///
/// </summary>
public
partial class Form1 : Form
{
private
enum State
{
Idle = 0,
Accepting = 1,
Off = 2,
}
private
State RecogState = State.Off;
private
SpeechRecognitionEngine recognizer;
private
SpeechSynthesizer synthesizer = null ;
private
int Hypothesized = 0;
private
int Recognized = 0;
/// <summary>
///
/// </summary>
public
Form1()
{
InitializeComponent();
}
/// <summary>
///
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private
void Form1_Load( object
sender, EventArgs e)
{
// SpVoice voice = new SpVoice();//SAPI 5.4
//SpeechLib.ISpeechObjectTokens obj = voice.GetVoices(string.Empty, string.Empty);
//int count = obj.Count;//获取语音库总数
//bool result = false;
//for (int i = 0; i < count; i++)
//{
// string desc = obj.Item(i).GetDescription(i);//.GetDescription(); //遍历语音库
// comboBox1.Items.Add(desc);
//}
//SpVoiceClass voice = new SpVoiceClass();//SAPI 5.1
////voice.Voice = voice.GetVoices(string.Empty, string.Empty).Item(0);
////voice.Speak("你要说的话",SpeechVoiceSpeakFlags.SVSFlagsAsync);
//SpVoice voice1 = new SpVoice();//SAPI 5.4
//voice1.Volume = 100;//音量
//voice1.Voice = voice1.GetVoices(string.Empty, string.Empty).Item(0);
//voice1.Rate = 2;//速度语音朗读速度
// voice1.Speak("你要说的话", SpeechVoiceSpeakFlags.SVSFlagsAsync);
//voice1.Speak("speech sdk 5.1", SpeechVoiceSpeakFlags.SVSFlagsAsync);
//SpeechSynthesizer syn = new SpeechSynthesizer();
//syn.SelectVoice("Microsoft Lili");
//initialize recognizer and synthesizer
InitializeRecognizerSynthesizer();
//if input device found then proceed
if
(SelectInputDevice())
{
LoadDictationGrammar();
ReadAloud( "*" ); //中文方式Speech Engine Ready for Input
}
}
/// <summary>
/// 中文
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private
void button1_Click( object
sender, EventArgs e)
{
SpVoiceClass voice = new
SpVoiceClass();
voice.Voice = voice.GetVoices( string .Empty, string .Empty).Item(0); //0,为系统默认,中文
voice.Speak( this .textBox1.Text.Trim(), SpeechVoiceSpeakFlags.SVSFlagsAsync);
}
/// <summary>
/// 英文
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private
void button2_Click( object
sender, EventArgs e)
{
SpVoiceClass voice = new
SpVoiceClass();
voice.Voice = voice.GetVoices( string .Empty, string .Empty).Item(1); //
voice.Speak( this .textBox2.Text.Trim(), SpeechVoiceSpeakFlags.SVSFlagsAsync);
}
/// <summary>
/// 输入中文语音输出中文文字
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private
void button3_Click( object
sender, EventArgs e)
{
switch
(RecogState)
{
case
State.Off:
RecogState = State.Accepting;
button3.Text = "Stop" ;
recognizer.RecognizeAsync(RecognizeMode.Multiple);
break ;
case
State.Accepting:
RecogState = State.Off;
button3.Text = "Start" ;
recognizer.RecognizeAsyncStop();
break ;
}
}
/// <summary>
/// pause recognition and speak the text sent
/// </summary>
/// <param name="speakText"></param>
public
void ReadAloud( string
speakText)
{
try
{
recognizer.RecognizeAsyncCancel();
synthesizer.SpeakAsync(speakText);
}
catch
{ }
}
/// <summary>
/// initialize recognizer and synthesizer along with their events
/// /// </summary>
private
void InitializeRecognizerSynthesizer()
{
var
selectedRecognizer = ( from
e in
SpeechRecognitionEngine.InstalledRecognizers()
where
e.Culture.Equals(Thread.CurrentThread.CurrentCulture)
select
e).FirstOrDefault();
recognizer = new
SpeechRecognitionEngine(selectedRecognizer);
recognizer.AudioStateChanged += new
EventHandler<AudioStateChangedEventArgs>(recognizer_AudioStateChanged);
recognizer.SpeechHypothesized += new
EventHandler<SpeechHypothesizedEventArgs>(recognizer_SpeechHypothesized);
recognizer.SpeechRecognized += new
EventHandler<SpeechRecognizedEventArgs>(recognizer_SpeechRecognized);
synthesizer = new
SpeechSynthesizer();
}
#region Recognizer events
private
void recognizer_AudioStateChanged( object
sender, AudioStateChangedEventArgs e)
{
switch
(e.AudioState)
{
case
AudioState.Speech:
LabelStatus.Text = "Listening" ;
break ;
case
AudioState.Silence:
LabelStatus.Text = "Idle" ;
break ;
case
AudioState.Stopped:
LabelStatus.Text = "Stopped" ;
break ;
}
}
/// <summary>
///
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private
void recognizer_SpeechHypothesized( object
sender, SpeechHypothesizedEventArgs e)
{
Hypothesized++;
LabelHypothesized.Text = "Hypothesized: "
+ Hypothesized.ToString();
}
/// <summary>
///
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private
void recognizer_SpeechRecognized( object
sender, SpeechRecognizedEventArgs e)
{
Recognized++;
string
s = "Recognized: "
+ Recognized.ToString();
if
(RecogState == State.Off)
return ;
float
accuracy = ( float )e.Result.Confidence;
string
phrase = e.Result.Text;
{
if
(phrase == "End Dictate" )
{
RecogState = State.Off;
recognizer.RecognizeAsyncStop();
ReadAloud( "Dictation Ended" );
return ;
}
textBox1.AppendText( " "
+ e.Result.Text);
}
}
#endregion
/// <summary>
/// select input device if available
/// </summary>
/// <returns></returns>
private
bool SelectInputDevice()
{
bool
proceedLoading = true ;
//if OS is above XP
if
(IsOscompatible())
{
try
{
recognizer.SetInputToDefaultAudioDevice();
}
catch
{
proceedLoading = false ; //no audio input device
}
}
//if OS is XP or below
else
ThreadPool.QueueUserWorkItem(InitSpeechRecogniser);
return
proceedLoading;
}
/// <summary>
/// Findout if OS is compatible.
/// </summary>
/// <returns>true if greater than XP otherwise false</returns>
private
bool IsOscompatible()
{
OperatingSystem osInfo = Environment.OSVersion;
if
(osInfo.Version > new
Version( "6.0" ))
return
true ;
else
return
false ;
}
/// <summary>
///
/// </summary>
/// <param name="o"></param>
private
void InitSpeechRecogniser( object
o)
{
recognizer.SetInputToDefaultAudioDevice();
}
/// <summary>
/// Load grammars, one for command and other for dictation
/// </summary>
private
void LoadDictationGrammar()
{
GrammarBuilder grammarBuilder = new
GrammarBuilder();
grammarBuilder.Append( new
Choices( "End Dictate" ));
Grammar commandGrammar = new
Grammar(grammarBuilder);
commandGrammar.Name = "main command grammar" ;
recognizer.LoadGrammar(commandGrammar);
DictationGrammar dictationGrammar = new
DictationGrammar();
dictationGrammar.Name = "dictation" ;
recognizer.LoadGrammar(dictationGrammar);
}
}
} |
Csharp: speech to text, text to speech in win,布布扣,bubuko.com