The Microsoft Speech platform is used by Voice Elements for Text-To-Speech (TTS) and for Speech Recognition. Many languages are supported. License to use Microsoft Speech for TTS and Speech Recognition is included with your Windows OS license.
The Microsoft Speech Platform is comprised of the following:
Microsoft Speech Platform Runtime
You should have this installed on your server in order to perform Speech Recognition functions within Voice Elements. Voice Elements has built out support for Microsoft Speech platform, as long as you use Microsoft Compatible grammar files. These are easy to create using the methods outlined in this article: Create Microsoft Speech Compatible Grammar Files
Microsoft Speech Language Packs
The Microsoft Speech Platform relies on different language packs in order to provide Speech Recognition capabilities for different languages. Microsoft Speech Platform supports 18 different languages and accents. For a complete list, please refer to Microsoft Article Microsoft Speech Platform – Runtime Languages
Please note, for US English, you will need to install this language pack: MSSpeech_SR_en-US_TELE.msi
Microsoft Speech SDK
The SDK is the tookit provided by Microsoft to use the Microsoft Speech Platform. All of this functionality is built into Voice Elements. You will not need to have this installed, unless you would like to use it to create Microsoft Compatible Grammar files.
The SDK can be downloaded at Microsoft Speech Platform – Software Development Kit (SDK).
How to Install and Configure
You will need to follow the steps below to run the Microsoft Speech Platform with Voice Elements:
1) Download and install the Speech Platform Runtime.
2) ‘Download and install the appropriate Language Pack.
3) Add the settings below to your HmpElementsServer.exe.config:
<setting name="SpeechRecognitionDll" serializeAs="String"> <value>HmpElementsMicrosoftSpeech.Dll</value> </setting> <setting name="SpeechRecognitionType" serializeAs="String"> <value>HmpElements.Server.MicrosoftSpeech</value> </setting> <setting name="SpeechRecognitionNumberOfPorts" serializeAs="String"> <value>1</value> </setting> <setting name="SpeechRecognitionLicenseType" serializeAs="String"> <value>en-US</value> </setting> <setting name="SpeechEngineIpAddress" serializeAs="String"> <value>127.0.0.1</value> </setting>
Please note that SpeechRecognitionNumberOfPorts should be set to a number that is equal to or less than the number of Speech Recognition Ports you are licensed for.
SpeechRecognitionLicenseType is the culture-Info for the language pack that you are using. For example, If you would like to use Mexican Spanish, this value should be set to es-MX.