AT&T

AT&T TTS

AT&T Natural Voices TTS Engines System Developer’s Guide Server, Server-Lite, and Desktop Editions US English, Latin American Spanish, UK English, German and French

Цитата :

Contents
About this Guide .........vii
1 Introduction.........1-8
1.1. AT&T Natural Voices Text-To-Speech ......1-8
1.2 The Text-to-Speech Synthesis Problem......1-10
1.3 Release 1.4 Features........1-11
1.4 System Components and Features......1-13
1.5 Supported Languages ........1-14
1.6 This Guide........1-14
1.7 Other Sources of Information.......1-15
2 Installation.........2-16
2.1 Installing the AT&T Natural Voices TTS Software.....2-16
2.2 Disk Requirements ........2-17
2.3 Memory Requirements ........2-17
2.4 Installing AT&T Natural Voices TTS Engines on Microsoft Windows ...2-17
2.5 Installing the AT&T Natural Voices TTS Software on UNIX Machines ...2-20
2.5.1 Installing the AT&T Natural Voices Server-Lite and Desktop Editions... 2-21
2.5.2 Installing the Server Edition TTS Server on UNIX Servers .... 2-21
2.5.3 Installing the Server Edition TTS Client on UNIX Machines.... 2-21
3 Using the TTS Server Engines .......3-23
3.1 Server Command Line Arguments......3-23
3.2 Running the TTS Server as a Microsoft Service.....3-25
3.2.1 Installing the ATT_TTSService Service. ...... 3-25
3.2.2 Running the ATT_TTSService service ...... 3-26
3.2.3 Uninstalling the ATT_TTSService...... 3-26
3.2.4 Modifying the ATT_TTSService Parameters...... 3-26
3.3 Supporting Multiple Voices and Languages ......3-27
3.4 Running the Client ........3-28
3.4.1 Microsoft Windows SAPI 4.0 TTSApp ...... 3-28
3.4.2 Microsoft Windows SAPI 5.1 TTSApp ...... 3-30
3.4.3 Command Line TTS Clients....... 3-31
3.5 Server Output and Error Messages......3-33
3.5.1 Initialization Messages ........ 3-33
3.5.2 Shutdown Messages ........ 3-33
3.5.3 Voice Inventory Messages ....... 3-34
3.5.4 Client Messages........ 3-34
3.6 SNMP.........3-34
3.6.1 Configuring SNMP on Windows NT/2000/XP...... 3-34
3.6.2 Verifying that the Microsoft SNMP Service is installed.... 3-34
3.6.3 Configuring SNMP on Unix systems ...... 3-35
3.6.4 Configuring the snmpd.conf configuration file ...... 3-35
3.6.5 TTS MIB files ........ 3-35
3.7 Using the Server Edition with Nuance ...... 3-36
4 Running the Server-Lite and Desktop Edition...... 4-38
4.1 Microsoft Windows SAPI 4.0 TTSApp ...... 4-38
4.2 Microsoft Windows SAPI 5.1 TTSApp ...... 4-39
4.3 Command Line TTS Applications...... 4-40
5 Client C++ SDK ........ 5-45
5.1 Getting Started........ 5-45
5.1.1 SDK Headers ........5-46
5.1.2 Compiler Definitions ........5-46
5.1.3 SDK Libraries........5-47
5.2 Programming Conventions ....... 5-48
5.2.1 Return Codes ........5-48
5.2.2 CTTSRefCntObject ........5-48
5.2.3 UTF-8 Strings ........5-48
5.2.4 C++ Standard Template Library.......5-49
5.3 Creating An Engine ........ 5-49
5.3.1 Build A Configuration Structure .......5-49
5.3.2 Creating an Engine ........5-52
5.3.3 Creating an Engine for the Server Edition......5-52
5.3.4 Creating an Engine for the Server-Lite and Desktop Editions ....5-53
5.4 Receiving Engine Notifications And Messages..... 5-54
5.4.1 CTTSSink Notifications .......5-54
5.4.2 CTTSNotification Object.......5-56
5.4.3 TTSWordNotification structure.......5-57
5.4.4 TTSPhonemeNotification structure ......5-57
5.4.5 CTTSErrorInfoObject........5-57
5.5 Initializing And Shutting Down The Engine ...... 5-59
5.6 Setting The Voice ........ 5-60
5.6.1 TTSVoice Structure ........5-60
5.6.2 Enumerating The Voices .......5-60
5.6.3 Setting The Voice ........5-61
5.7 Setting The Audio Format ....... 5-61
5.7.1 TTSAudioFormat Structure .......5-61
5.7.2 Enumerating The Audio Formats .......5-62
5.7.3 Setting the Audio Format.......5-62
5.8 Speaking Text ........ 5-62
5.8.1 Speaking Text ........5-63
5.8.2 Speaking CTTSTextFragment objects......5-63
5.9 Setting Volume and Rate ....... 5-65
5.10 Stopping The Engine ........ 5-66
5.11 Retrieving Phonetic Transcriptions ...... 5-66
5.12 Custom Dictionaries ........ 5-66
5.12.1 Creating a Dictionary........5-67
5.12.2 Updating a Dictionary........5-67
5.12.3 Clearing and Deleting a Dictionary ......5-67
5.12.4 Changing Search Order ........5-67
5.13 Optional Operating System Specific Classes...... 5-68
5.13.1 CTTSWin32AudioPlayer .......5-68
5.13.2 CTTSWin32AudioWriter .......5-68
5.13.3 CTTSUnixAudioPlayer ........5-68
5.13.4 CTTSUnixAudioWriter ........5-68
5.14 Changes from AT&T Natural Voices 1.0 Release ..... 5-68
5.14.1 New Engine Models ........ 5-68
5.14.2 Library names have changed.......5-68
6 Java Speech API Implementation.......6-69
6.1 Requirements........6-69
6.2 Installation........6-69
6.3 Compiling the Examples .......6-69
6.4 Running the Examples ........6-70
6.5 Using AT&T Natural Voices JSAPI Implementation .....6-70
6.6 Available Synthesizer Voices.......6-70
6.7 Available Synthesizer Modes.......6-71
6.8 Differences Between the JSAPI Specification and the AT&T Implementation..6-71
6.8.1 Audio......... 6-71
6.8.2 Vocabulary ........ 6-71
6.8.3 Queuing ........ 6-71
6.8.4 XML......... 6-72
6.8.5 Voices......... 6-72
6.8.6 Synthesizer ........ 6-72
6.8.7 Engine ......... 6-73
6.8.8 Permissions........ 6-73
7 SAPI 4 Text Markup ........7-74
7.1 Com.........7-76
7.2 Ctx..........7-76
7.2.1 Address Context ........ 7-76
7.2.2 Document Context........ 7-76
7.2.3 Email Context........ 7-76
7.2.4 Numbers Context........ 7-76
7.2.5 Unknown Context ........ 7-77
7.2.6 Normal Context ........ 7-77
7.3 Mrk.........7-77
7.4 Pau..........7-78
7.5 Prn ..........7-78
7.6 RmS.........7-78
7.7 RmW.........7-79
7.8 RSpd.........7-79
7.9 Rst ..........7-79
7.10 Spd .........7-79
7.11 Vce .........7-80
7.12 Vol..........7-81
8 Microsoft SAPI 5.1 Control Tags .......8-82
8.1 ATT_Div........8-84
8.2 ATT_Ignore_case........8-84
8.3 Bookmark........8-84
8.4 Context ........8-85
8.4.1 Address Context ........ 8-85
8.4.2 Address_postal Context........ 8-85
8.4.3 ATT_Literal Context ........ 8-86
8.4.4 ATT_Math Context ........ 8-86
8.4.5 ATT_Measurement Context ....... 8-86
8.4.6 Currency Context ........ 8-86
8.4.7 Date_MD Context ........ 8-87
8.4.8 Date_MDY Context ........ 8-87
8.4.9 Date_Year Context ........ 8-87
8.4.10 Number_Cardinal Context .......8-87
8.4.11 Number_Decimal Context .......8-87
8.4.12 Number_Fraction Context .......8-87
8.4.13 Phone_Number Context........8-88
8.4.14 Time Context ........8-88
8.4.15 Web Context ........8-88
8.4.16 Web_url Context........8-88
8.4.17 Email Context ........8-89
8.4.18 Email_address Context ........8-89
8.5 Pron......... 8-89
8.6 Rate......... 8-89
8.7 Silence ........ 8-90
8.8 Spell ......... 8-91
8.9 Voice......... 8-91
8.10 Volume ........ 8-92
9 SSML Control Tags........ 9-93
9.1 ATT_Ignore_Case ........ 9-96
9.2 Break......... 9-96
9.3 Mark ......... 9-97
9.4 Paragraph........ 9-97
9.5 Phoneme ........ 9-98
9.6 Prosody........ 9-98
9.6.1 Rate.........9-99
9.6.2 Volume ........9-99
9.7 Say-As ........ 9-100
9.7.1 Acronym........9-100
9.7.2 Address ........9-100
9.7.3 ATT_Literal ........9-100
9.7.4 ATT_Math ........9-101
9.7.5 ATT_Measurement........9-101
9.7.6 Currency ........9-101
9.7.7 Date.........9-101
9.7.8 Name.........9-102
9.7.9 Net .........9-102
9.7.10 Number ........9-103
9.7.11 Sub.........9-103
9.7.12 Telephone ........9-103
9.7.13 Time.........9-104
9.8 Sentence........ 9-104
9.9 Speak ........ 9-104
9.10 Voice......... 9-105
10 JSML Control Tags ........ 10-107
10.1 jsml ......... 10-108
10.2 div......... 10-109
10.3 voice ........ 10-109
10.4 sayas ........ 10-111
10.4.1 literal ........10-111
10.4.2 date.........10-111
10.4.3 time .........10-112
10.4.4 name.........10-112
10.4.5 phone ........10-112
10.4.6 net .........10-113
10.4.7 address........ 10-113
10.4.8 currency........ 10-113
10.4.9 measure........ 10-114
10.4.10 number........ 10-114
10.5 phoneme ........10-114
10.6 break........10-114
10.7 prosody........10-115
10.7.1 rate......... 10-115
10.7.2 volume........ 10-116
10.8 marker ........10-117
10.9 engine ........10-117
11 Custom Dictionaries ........11-118
11.1 Defining Custom Pronunciations ......11-118
11.2 Using the Win32 WinDictEdit Tool......11-119
11.2.1 Defining Replacements ....... 11-120
11.2.2 Changing the default pronunciation of a word..... 11-121
11.3 Adding Custom Pronunciations to Your Application ....11-122
12 Performance Guidelines .......12-124
12.1 TTS Memory Requirements .......12-124
12.2 Definitions........12-124
12.3 Performance Results........12-125
12.4 Recommendations ........12-126
Appendix A: Phonetic Alphabets.......12-128
A.1. IPA Phonetic Alphabets .......12-128
A.1.1 US English SAPI 4/IPA Phonetic Alphabet......12-129
A.1.2. Spanish SAPI 4/IPA Phonetic Alphabet ......12-131
A.1.3. German SAPI 4/IPA Phonetic Alphabet ......12-133
A.1.4 French SAPI 4/IPA Phonetic Alphabet ......12-136
A.1.5 UK English SAPI 4/IPA Phonetic Alphabet ......12-138
A.2.1 The SAPI 5 and DARPA US English Phonetic Alphabets ....12-140
A.2.2. SAPI 5 SAMPA Spanish Phonetic Alphabet ......12-142
A.2.3. SAPI 5 SAMPA German Phonetic Alphabet ......12-144
A.2.4. SAPI 5 SAMPA French Phonetic Alphabet......12-147
A.2.5. SAPI 5 SAMPA UK English Phonetic Alphabet .....12-150
Appendix B: SAPI 5.1 Compliance .......12-152
B.1. Support for SAPI 5.1 ........12-152