SEMINAR PRESENTATION
ON
Under Guidance of
VoiceXML
Mr.B.R.Mandre
Submitted By
Tanushree Chakravarty
Department of computer Engineering
S.S.V.P.S.B.S DEORE College Of
Engineering,Dhule
2003-2004
September10th,2003
1 /30
B.E.Computer Seminar
Overview
1)Introduction
2)Evolution
3)Graphical Browser V/s Voice Browser
4)VoiceXML concepts
5)VoiceXML Features
6)VoiceXML Goals
7)VoiceXML Architechture
8)VXML Interpreter
9)VXML as a Language
10)Practical Applications
11)Commercial Applications
12)Conclusion
September10th,2003
Tanushree Chakravarty
2/30
B.E.Computer Seminar
INTRODUCTION
Overview
What is XML?
XML = Extensible Markup Language
A flexible way to create common
information
formats and share both the
September10 ,2003
Tanushree Chakravarty
3/30
format and the data on the web
th
B.E.Computer Seminar
INTRODUCTION (Contd..)
What is VoiceXML?
VoiceXML = Voice eXtensible Markup Language:
is a Web-based dialog markup language for
human-computer voice dialogs, a derivative of XML.
HTML assumes a graphical web browser, with
keyboard, display and mouse
VoiceXML extends the web to voice-based devices:
audio input and output
VoiceXML can be thought of as a markup language
for voice, like HTML is for text.
VoiceXML is used extensively for speech recognition
and application development.
September10th,2003
Tanushree Chakravarty
4/30
B.E.Computer Seminar
Evolution of VoiceXML
VXML was introduced with collaboration
between IBM, Motorola, Lucent and AT&T
VXML 1.0 is a specification of VXML Forum
September10th,2003
Tanushree Chakravarty
5/30
B.E.Computer Seminar
Graphical Browser V/s Voice
Browser
September10th,2003
Tanushree Chakravarty
6/30
B.E.Computer Seminar
VoiceXML Concepts.
VXML Concepts
A VoiceXML application consists of a set of
documents that describe a conversational
finite state machine.
The user is always in one conversational
state, or dialog,at a time.
September10th,2003
Tanushree Chakravarty
7/30
B.E.Computer Seminar
VoiceXML Features.
The notable features in VXML are:
Recognition of spoken/DTMF (Dual Tone Multiple
Frequency) input. Here DTMF refers to pressing Telephone
keys.
Assigning spoken input to variables in the document and
making decisions based on the assigned values to the
variables.
Playing synthesized speech, audio files with the help of
Text-to-Speech (TTS) converter.
Linking to other documents/other areas of the same
document as an HTML file would do.
September10th,2003
Tanushree Chakravarty
8/30
B.E.Computer Seminar
Goals of VoiceXML
VoiceXML is a markup language that:
Minimizes client/server interactions by specifying multiple
interactions per document.
Shields application authors from low-level, and platformspecific details.
Separates user interaction code (in VoiceXML) from service
logic (CGI scripts).
Promotes service portability across implementation platforms.
VoiceXML is a common language for content providers, tool
providers, and platform providers.
Is easy to use for simple interactions, and yet provides
language features to support complex dialogs.
September10th,2003
Tanushree Chakravarty
9/30
B.E.Computer Seminar
VoiceXML Architechture
September10th,2003
Tanushree Chakravarty
10/30
B.E.Computer Seminar
VoiceXML Architechture
(Contd)
September10th,2003
Tanushree Chakravarty
11/30
B.E.Computer Seminar
VXML Interpreter
The heart of this system is a
VXML interpreter
Dialog is initiated when the
Telephone Resource Manager
receives an incoming call
September10th,2003
Tanushree Chakravarty
12/30
B.E.Computer Seminar
VXML Interpreter (Contd)
September10th,2003
Tanushree Chakravarty
13/30
B.E.Computer Seminar
Example of VXML
September10th,2003
Tanushree Chakravarty
14/30
B.E.Computer Seminar
VoiceXML as a Language
Output of synthesized speech (text-to-speech).
Output of audio files.
Recognition of spoken input.
Recognition of DTMF input (touch tone).
Recording of spoken input.
Telephony features such as call transfer and
disconnect.
September10th,2003
Tanushree Chakravarty
15/30
B.E.Computer Seminar
Dialogs & Sub dialogs
Dialogs are basically a set of executable commands in
VoiceXML
There are two kinds of dialogs: forms and menus.
Forms define an interaction that collects values for a set
of field item variables.
Fields are the major building blocks of forms.
A menu presents the user with a choice of options and
then transitions to another dialog based on that choice.
A sub-dialog is like a function call, in that it provides a
mechanism for invoking a new interaction, and returning
to the original form.
September10th,2003
Tanushree Chakravarty
16/30
B.E.Computer Seminar
Sessions
A session begins when the user starts to interact with a
VoiceXML interpreter context, continues as documents are
loaded and processed, and ends when requested by the
user, a document, or the interpreter context .
September10th,2003
Tanushree Chakravarty
17/30
B.E.Computer Seminar
Application
An application is a set of documents sharing the same
Application root document.
September10th,2003
Tanushree Chakravarty
18/30
B.E.Computer Seminar
Grammars
Each dialog has one or more speech and/or DTMF
grammars associated with it.
In machine directed applications, each dialog grammars
are active only when the user is in that dialog.
In mixed initiative applications, where the user and the
machine alternate in determining what to do next, some of
the dialogs are flagged to make their grammars active
September10th,2003
Tanushree Chakravarty
19/30
B.E.Computer Seminar
Events
include explicit mechanisms for handling events not
covered by the form mechanism
Events are thrown due to:
Unexpected user response.
Network anomalies.
Hardware/Software platform errors
Events are caught by:
Catch elements or their syntactic shorthand.
September10th,2003
Tanushree Chakravarty
20/30
B.E.Computer Seminar
Links
A link supports mixed initiatives.
Example :
Menus
Computer: For Maharashtra, press 1. For Gujrat, press 2
Human: 1
Computer: For Mumbai, press 1, For Dhule, press 2
Forms
Directed Dialogs
C: Please say the state for which you want the weather.
H: Maharashtra
C: Please say the city for which you want the weather.
H: Dhule
Mixed Initiative Dialogs
C: For which city and state would you like the weather?
H: Dhule, Maharashtra
September10th,2003
Tanushree Chakravarty
21/30
B.E.Computer Seminar
Form Interpretation Algorithm
drives the interaction between the user and a VoiceXML form or
menu.
The FIA must handle:
Form initialization.
Prompting, including the management of the prompt counters needed for
prompt tapering.
Grammar activation and deactivation at the form and form item levels.
Entering the form with an utterance that matched one of the forms
document-scoped grammars while the user was visiting a different
form or menu.
Leaving the form because the user matched another form, menu, or
links document-scoped grammar.
Processing multiple field fills from one utterance, including the execution
of the relevant <filled> actions.
Selecting the next form item to visit, and then processing that form item.
Choosing the correct catch element to handle any events thrown while
th
September10
,2003
22/30
processing
a form
item. Tanushree Chakravarty
B.E.Computer Seminar
Practical Applications of
VoiceXML.
1) Absentee System application
In this a VoiceXML absentee system is shown that enables
students to telephone in their class about their absence that is
recorded in a university database.
This application is suitable for any reasonably sized organization
for a cost- effective and convenient way to record employee
absences by having them interact directly with a computer with
a telephone.
The Absentee System application was developed basically for
Pace University students to report class absences, using PHP on
mySQL database at Pace University.
September10th,2003
Tanushree Chakravarty
23/30
B.E.Computer Seminar
Practical Applications of
VoiceXML ( Contd)
2) THE PITTSBURGH BUSLINE
The Pittsburgh Busline application is a telephone-based
system that provides schedule information about buses
traveling in and out of Pittsburghs University neighborhood.
The Busline systems were primarily developed using an early
implementation of VoiceXML 1.0.
Two Pittsburgh Busline systems were developed concurrently
and independently.
September10th,2003
Tanushree Chakravarty
24/30
B.E.Computer Seminar
Practical Applications of
VoiceXML ( Contd)
2) THE PITTSBURGH BUSLINE
Sample dialog using Busline A.
September10th,2003
Tanushree Chakravarty
Sample Busline B dialog.
25/30
B.E.Computer Seminar
Commercial Applications
of VXML
Information retrieval applications
Electronic commerce
Telephone services
Unified messaging applications
Intranet applications
September10th,2003
Tanushree Chakravarty
26/30
B.E.Computer Seminar
CONCLUSION
effective exploration of dialog system design.
can bring high efficiency to call center and intranet
development.
cost-effective and convenient to interact with a
software application without human interaction
or any expensive computing devices.
Commercial VoiceXML development environments
offer a relatively easy entry point that allows diverse
dialog systems to be built.
September10th,2003
Tanushree Chakravarty
27/30
B.E.Computer Seminar
Bibliography
1)VoiceXML Absentee System,
http://csis.pace.edu/csis/masplas/plo.pdf
2)Mixed-Initiative Interaction = Mixed Computation,
http://perez.cs.vt.edu/publications/2002/miimc.pdf
3)Aural Interfaces To Databases Based On VOICEXML
www.globis.ethz.ch/publications/docs/2002a-sngh-vdb.pdf
4)BeVocal: http://cafe.bevocal.com
5)VoiceXML: http://www.w3.org/TR/VoiceXML2.0
6)Tellme: http://studio.tellme.com
7)Periphonics: http://nortelnetworks.com/products/04/oscar
September10th,2003
Tanushree Chakravarty
28/30
B.E.Computer Seminar
F
A
Search
Q
QUESTIONS
September10th,2003
ANSWER
Tanushree Chakravarty
29/30
B.E.Computer Seminar
THANK YOU
September10th,2003
Tanushree Chakravarty
30/30
