Deploying Speech Recognition

VoiceGuide v7 supports any MRCPv2 compliant speech recognition engine.

Speech Recognition is supported when any current Dialogic card  is used - except the low end D/4PCIUF. Speech Recognition is also supported on HMP3.0 VoIP systems.

At this stage we recommend using one of the following speech recognition engines:

• LumenVox - priced at $50 for single line license. Multiple lines priced at around $180 per line (for a "Lite" license).
• Nuance - priced at $800+ per line.

Step 1 : Install the speech recognition engine

It is recommended that the Speech Recognition engine be installed on a separate server. Speech Recognition engines have high resource and CPU requirements and the high CPU load can degrade overall IVR performance if the Speech Recognition engine is installed on the same system.

• Installing LumenVox

Step 2 : Configure Dialogic cards

If using Analog Dialogic cards then a special "CSP Enabled" Firmware file will need to be selected. Go the Dialogic Configuration Manager, bring up the properties page for the analog card and on the Misc tab select the following Firmware file:

D/41JCT : d41jcsp.fwl

D/120JCT : d120csp.fwl
 

Similarly, when using the Dialogic JCT series T1 and E1 cards the "CSP Enabled" Firmware needs to be selected in the Dialogic Configuration Manager.

No special settings are needed for the DMV cards.

Step 3 : Configure VoiceGuide

Add the Devices_MRCPv2 entry to the config.xml file:

<VoiceGuideConfig>

...

<Devices_ASR>
<Server_MRCPv2>
<ResourceType>speechrecog</ResourceType>
<ClientIP>10.1.1.9</ClientIP>
<ClientPort>8062</ClientPort>
<ServerIP>10.1.1.8</ServerIP>
<ServerPort>5060</ServerPort>
<RtpMin>49200</RtpMin>
<RtpMax>65300</RtpMax>
</Server_MRCPv2>
</Devices_ASR>

</VoiceGuideConfig>

Use the above as a template. Place the IP of the machine on which VoiceGuide is installed in the <ClientIP> section, and place the IP address of the machine on which the speech recognition server is installed in the <ServerIP> section.

Step 4 : Test with Provided Sample Scripts

Some sample scripts have been provided as starting point. They can be downloaded from the Example Scripts section of the WWW.

Step 5 : Create Your Own Grammars

Speech recognition is right now enabled within VoiceGuide's Play modules only. To have VoiceGuide recognize speech during a play, a grammar associated with this play module must be defined. A grammar is defined by creating a text file which contains the grammar for the particular play module, and placing this file in the same directory where the script is located. The filename can be:

srgs_ModuleTitle.gram

srgs_ModuleTitle_PortNumber.gram

srgs_ModuleTitle.txt

srgs_ModuleTitle_PortNumber.txt

The ModuleTitle identifies for which play module the grammar file is for and the PortNumber can also be used to specify that this grammar should be used by this particular port only. The grammar files' contents are read in when when the Play module starts. This approach allows user to dynamically update grammars as required. The order in which VoiceGuide searches for the grammar files is as listed above.

Also see: Specifying Grammars

Step 5 : Modify Your Own Scripts to Handle Speech Recognition Responses

When VoiceGuide receives the response from the Speech Recognition Engine it will create the following Result Variables:

VoiceGuide will first see if a path matching the value stored in $RV[ModuleTitle_ASR_Instance] is found. If the matching path is found then that path is taken.
Next VoiceGuide will first see if a path matching the value stored in $RV[ModuleTitle_ASR_Input] is found. If the matching path is found then that path is taken.
Otherwise the Success path is taken if some response was returned, and a Fail path is taken if no response was returned or the response was <nomatch/>