====== Verbio ASR ======

===== About =====

**Verbio Technologies **

Loreto 44\\
08029 Barcelona\\
Spain

Website: __[[http://www.verbio.com/|http://www.verbio.com]]__

===== Definition =====

Verbio is a company based in Barcelona (Spain), specializing in speech technologies, aimed basically at the Spanish, Portuguese and Latin American markets.

===== Languages =====

English (US) · French · Portuguese · Portuguese (Brazil) · Spanish(Argentina) · Spanish (Chile) · Spanish (Venezuela) · Spanish (Colombia) · Spanish (Cuba) · Spanish (Santo Domingo) · Spanish (Puerto Rico) · Spanish (Paraguay) · Spanish (Uruguay) · Spanish(Mexico) · Spanish (North America) · Spanish (Catalan) · Spanish (Valencia) · Spanish (Galician) · Spanish (Euskera)

===== Installation =====

If your distribution does not use 'rpm' nor 'deb' please contact Verbio Technologies staff (support@verbio.com). 
Download the package after contacting the Verbio sales.

1. Check that your system is up to date 
For example, on CentOS environments:

<code>
#yum update
</code>

2. Install 32bit compatibility libs (on 64 bits platforms) if using MRCP protocol:
For example, on CentOS environments:

<code>
# yum install glibc.i686 glibc-devel.i686
# yum install libstdc++.i686 libstdc++-devel.i686
</code>

3. Install the “Engines” package.
DEB packages:

<code>
# dpkg -i verbio-engines-X.Y.ZZZZZZZZ.deb
RPM packages:
# rpm -ivh verbio-engines-X.Y.ZZZZZZZ.rpm
</code>

4. Install TTS and ASR packages, as needed:
DEB packages:

<code>
# dpkg -i verbio-tts-*-X.Y.ZZZZZZ.deb
# dpkg -i verbio-asr-*-X.Y.ZZZZZZ.deb
RPM packages:
#rpm -ivh verbio-tts-*-X.Y.ZZZZZZ.rpm
#rpm -ivh verbio-asr-*-X.Y.ZZZZZZ.rpm
</code>

5. If MRCP protocol is required, install the following package:
DEB packages:

<code>
# dpkg -i verbio-mrcp-cert-X.Y.ZZZZZZZZ.deb
RPM packages:
#rpm -ivh verbio-mrcp-cert-X.Y.ZZZZZZZZ.rpm
</code>





===== Configuration =====

To enable speech recognition, change the main speech parameter.
The “speech” parameter can get three values, “yes”, “automatic”, “no” or “emulation” (don’t generate errors if you enable speech grammars).

</code>
[general]
…
speech=automatic
speechprovider=verbio
…
</code>

Don't set the speechdirectory parameter.

<code>
In the VoiceXML browser configuration file :
############################
# ASR server configuration #
############################

client.rec.resource.0.cacheDir              VXIString   /tmp/cacheContent
client.rec.resource.0.format                VXIString   txt
</code>

The following VoiceXML example uses the speech recognition, with the built in grammar, ‘digits.’
<code>
<?xml version="1.0" encoding="iso-8859-1"?>
<vxml version="2.0" xmlns="http://www.w3.org/2001/vxml" xml:lang="en-UK">
 <form>
  <property name="inputmodes" value="voice"/>
  <property name="timeout" value="30s"/>
  <field name="text" type="digits">
   <catch event="noinput nomatch">
    <reprompt/>
   </catch>
   <prompt>
    Speak to me:
   </prompt>
  </field>
  <filled>
   <prompt>
    You say me:
    <value expr="text" />
   </prompt>
   <clear namelist="text" />
  </filled>
 </form>
</vxml>
</code>