Pace VoiceXML Absentee System

nervousripSecurity

Nov 5, 2013 (3 years and 7 months ago)

141 views

Pace VoiceXML Absentee System

Paul Visokey, Ping Gallivan, Yani Mulyani,


Lisa Jordan, Elaine Li, George Mathew, Qisheng Hong


Presenter Name : Paul Visokey

CS616 Software Engineering


Project Goals


Bring web
-
based development and
content delivery to interactive voice
response applications


Create an application for tracking
student class absences


Convert application from TellMe portal
to Ascent Technology hardware to
enhance accessibility and reliability

Voice Applications:


Voice Recognition:
Voice recognition implies
only that the
computer

can take dictation, not
that it
understands

what is being said.



Natural language processing
:
C
omprehending
human
languages

falls under a different field of
computer science called
natural language

processing.



Speaker dependent systems:
-
These systems
generally require an extended training session
during which the computer system becomes
accustomed to a particular voice and accent.

Voice Applications Cont’


Discrete speech

systems:
Many systems
require that the speaker speak slowly and
distinctly and separate each word with a short
pause. These systems are called
discrete
speech

systems.


Continuous speech

systems:
These are voice
recognition systems that allow you to speak
naturally.
Speech Recognition

is the engine
that drives interactive voice applications






Voice applications in past and today


Traditionally, voice applications proprietary Voice
Response systems, text
-
to
-
speech conversion
software (TTS), and commercial automatic speech
recognition software (ASR)


Today, VoiceXML coders can employ free
VoiceXML gateways, such as :VoiceGenie and
TellMe, to speak the pages they are developing


The computer of the future

understands what we
say, will talk to us, show us images and movies,
and fit in a palm





XML and VoiceXML, HTML



Applications using XML technologies should
be accessible on three different devices: The
telephone (VoiceXML),

Mobile phone mini
browsers (WML),

PC browsers (HTML).



To realize this vision,

we will

create abstract
models and encode them in XML,

must
recognize the device, transform these models
into the appropriate rendering forma




Web Architecture

Visual Web Model

Voice Web Model

The user requests a page by
opening a browser, and
typing a URL

The user dials in to a
particular phone number

The browser makes an HTTP
Request to a server for an
HTML page

The voice browser sends an
HTTP Request for a
VoiceXML document to a
server determined by the
dialed number

The browser interprets the
HTML to create a visual page
that responds to user input
through the keyboard or
mouse

The voice browser renders
the VoiceXML as a sequential
dialog, consisting of output
prompts and input speech or
touch tones

Technology Analysis




Technology Analysis, Cont’


Voice Web Technology


VoiceXML : Schema of XML


Visual Web Technology:


PHP , HTML, JavaScript


Database: MySQL


FOR MORE INFO...

http://www.w3.org/2001/vxml

http://geocities.com/project_team4/

VoiceXML Architecture

VoiceXML Concepts


Dialogs ( 2 Kinds): forms and menus


Subdialogs: a mechanism for invoking
a new interaction, and returning to the
original form


Sessions: begins when the user starts
to interact with a VoiceXML interpreter
and continues as VoiceXML
documents are loaded and unloaded.

VoiceXML Grammars


They specify what spoken words to listen
for and how to interpret them,
Grammar
defines what is valid user input


Each dialog has one or more speech
and/or DTMF grammars associated with it


Grammars can be active for the entire
application, a document, a form, or a field,
and active only when the user is in that
dialog


Grammars Cont’






In a VoiceXML application, grammar
represents the point

where the user's voice
or input is compared against a set of
acceptable responses



The default scope for a grammar is the
element in which it is defined.



Grammars are either defined in the
application or called from an external file


Grammar Example


<field name="courseid">



<prompt>Please say the course i d</prompt>

<grammar>

<![CDATA[

[

(Char_speak:d1 Char_speak:d2 Dig_speak:d3 Dig_speak:d4 Dig_speak:d5)

{<option strcat($d1 strcat($d2 strcat($d3 strcat($d4 $d5))))>}

(cancel) {<option "cancel">}

]

Char_speak

[c{return(c)}

s{return(s)}]

Dig_speak

[

one {return(1)}

two {return(2)}

…………………

]

]]>

</grammar>






<filled>




<prompt>




You said <value expr="courseid"/>




</prompt>








</filled>

VoiceXML documents



Execution within one

document




Documents define applications as a set of
named dialog states , document execution
begins at the first dialog by default


As each dialog executes, it determines the
next dialog.


When a dialog doesn't specify a successor
dialog, document execution stops.



VoiceXML documents



Executing a multi
-
document application


Transition of
documents in an
application that
sharing the same
root document, and
refer it in the other
documents <vxml>
elements

VoiceXML Documents Cont’


A VoiceXML document
contains a single
<vxml> element, which
is the root element.


Each <field> element
should contain a
<grammar> element.






VoiceXML Example

<? XML version= “1.0”?>

< vxml version=“1.0”>

<form>


<field name=“drink” >


<prompt>would you like coffee,tea,milk? </prompt>


<grammar src=“drink.gram”


type=“application/x
-
jsgf”/>


</field >


<block>


<submit next=
http://www.drink.example/drink2.asp
/>


</block>


</form>

</vxml>


Tellme Studio


Platform

TellMe Studio Grammars



TellMe Studio Grammar Library



Define Own Grammar using:

a) Nuance Grammar Specification Language

b) Speech Grammar Markup Language


(GRXML)


Description of Application


VoiceXML Absentee system will receive
and track student absences via phone
calls and /or website entries.


The system provides the instructor and
other administrators with a permanent
record of absentees that can be accessed
and displayed through a Web interface

FOR MORE INFO...

http://www.csis.pace.edu/~ctappert/cs615
-
01/default.htm

Work Flow of Absentee System

Student

PSTN

VoiceXML

Browser

Internet

Student

Database

VoiceXML

VoiceXML

HTTP

HTTP

Student ID etc

Automatic
Dialog

Web server

Technology
---
Absentee System


TellMe Studio technology platform
being used (1800
-
555
-
VXML)


VoiceXML 1.0 Standards being
adopted


demo


Current Status


VoiceXML Testing Based TellMe Studio
in CS616


Behind in Ascent Technology Portal
Facility


Terminate Absentee phone number on
browser


Point browser to Pace Utopia server


Test browser compatibility with VoiceXML
version 1.0 Absentee application

Voice Absentee System
Resources


Equipment,

ASCENT hardware, PACE VoiceXML Lab


_ Support & outside services


TellMe Studio

Related Documents


http://csis.pace.edu/~ctappert/cs616
-
02/default.htm


http://studio.tellme.com/


http://www.voicexml.org

Questions?