Upload
dan-rose
View
215
Download
0
Embed Size (px)
Citation preview
8/7/2019 Presentation_W3C_VoiceXML
1/14
New Standards Simpl
Speech-Enabled Web Applications
The Speech Interface Languages
8/7/2019 Presentation_W3C_VoiceXML
2/14
Brief HistoryIn the 1950s, Bell Laboratories developed the first effective speech
recognizer for numbers.
In the 1970s, the ARPA Speech Understanding Research project developed
the objective of automatic speech recognition as the understanding of
speech not merely the recognition of words.
By the 1980s, two distinct types of commercial products were available:
The first offered speaker-independent recognition of
small vocabularies useful for telephone transaction processing.
The second focused on the development of large-vocabulary
voice recognition systems so that text documentscould be created by voice dictation.
Over the past two decades, voice recognition technology
has developed to the point of real-time, continuous speech
systems that augment command, security, and content
creation tasks with exceptionally high accuracy.
SIL
8/7/2019 Presentation_W3C_VoiceXML
3/14
BackgroundSIL
In March of 1999, AT&T, IBM, Lucent and Motorola founded
the VoiceXML Forum, to promote and to accelerate theadoption of VoiceXML-based applications worldwide.
The Voice Browser Working Group
, first established on 26March 1999, is charged with managing the W3C efforts in this area
and is currently chartered through 31 January 2009.
The W3C Speech Interface Frameworkisa suite of markup specifications addressing
the convergence of telecommunications
and the Web with the goal of bringing the
benefits of Web technology to the telephone.
8/7/2019 Presentation_W3C_VoiceXML
4/14
the Framework
W3C Speech Interface Framework
SIL
ASRLanguage
UnderstandingContext
Interpretation
& Multimedia
Integration
Dialog
Manager
Media
Planning
DTMF Tone Recognizer
Prerecorded Audio Player
TTS LanguageGeneration
8/7/2019 Presentation_W3C_VoiceXML
5/14
the W3C StandardSIL
VoiceXML 2.0 & 2.1
Defines dialogs, for specifying the
exchange of information between the
user and a speech application.
Voice Browser Call Control (CCXML)Specifies call control functions.
State Chart XML (SCXML)
Generic state-machine based execution
environment based on CCXML and Harel
State Tables.
Speech Recognition Grammar
Specification (SRGS) 1.0
Specifies grammars of each user input to a
speech application.
Semantic Interpretation for Speech
Recognition(SISR) 1.0
Specifies the extraction and possible
translation of text from the output of a
speech recognizer.Speech Synthesis Markup Language
(SSML) 1.0 & 1.1
Specifies the rendering of synthesized
speech to the user.
Pronunciation Lexicon Specification
(PLS) 1.0
Syntax for specifying pronunciation
lexicons to be used by Speech Recognition
and Speech Synthesis.
XML-based Languages:
1. VoiceXML 2.0 & 2.1
2. Voice Browser Call Control (CCXML)
3. State Chart XML (SCXML)4. Speech Recognition Grammar Specification (SRGS) 1.0
5. Speech Synthesis Markup Lang
uage (SSML) 1.0 & 1.1
6. Pronunciation Lexicon Specification (PLS) 1.0
ECMAScript-based Language:
7. Semantic Interpretation for Speech Recognition(SISR) 1.0
8/7/2019 Presentation_W3C_VoiceXML
6/14
Standards ProgressSIL
Document RequirementsFirst Public
WorkingDraftLast Call
Working DraftCandidate
RecommendationProposed
RecommendationRecommendation
CCXML 1.0 Completed Completed Completed 3Q 2008 4Q 2008 1Q 2009
PLS 1.0 Completed Completed Completed Completed Completed Completed
SISR 1.0 Completed Completed Completed Completed Completed Completed
SSML 1.1 Completed Completed Completed 3Q 2008 4Q 2008 1Q 2009
VoiceXML 2.1 Completed Completed Completed Completed Completed Completed
VoiceXML 3.0 Completed 3Q 2008 TBD TBD TBD TBD
SCXML 1.0 TBDCompleted
4Q09 1Q10 2Q10 3Q10
8/7/2019 Presentation_W3C_VoiceXML
7/14
accont
a: k au t
Which account savings or checking?
savings
checking
CD
certificate of deposit new.account = "CD"
`
accont
a: k au t
Which account
savings or
checking?
savings
checking
CD
certificate of deposit new.account = "CD"
accont
a: k au t
Which account
savings or checking?
savings checking
CD
certificate of deposit new.account = "CD"
accont
a: k au t
Which account
savings or checking?
savings
checking
CD
certificate of deposit new.account = "CD"
accont
a: k au t
Which account
savings or checking?
savings
checking
CD
certificate of deposit new.account = "CD"
`
the MarkupSIL
SSML (in Green)
VoiceXML (in Black)
SRGS (in red)
SPL (in Brown)
SISR (in blue)
8/7/2019 Presentation_W3C_VoiceXML
8/14
the Voice BrowserSIL
DialogManager
8/7/2019 Presentation_W3C_VoiceXML
9/14
the ImpactSIL
open-source platform creates a more flexible architecture that minimizes
integration and customization and enables multimodal communication
development is greatly simplifieddeveloper only needs to use the SILs thatcontain features required by a specific application
decreasing the programming time and effortlowers the entry
barrier for creating Web-based telephony applications.
on Web Development
on Mobile SolutionsThe convergence of telecommunications and the Web is now bringing the benefits
of Web technology to the telephone, enabling Web developers to create
applications that can be accessed via any telephone, and allowing people to
interact with these applications via speech and telephone keypads.
8/7/2019 Presentation_W3C_VoiceXML
10/14
the MarketSIL
The overall market for voice-recognition
technology jumped 100% in just two years
-Opus Research
The market for speech technology embedded in
devices is expected to quadruple by 2010
-DataMonitor
2008 will be the first year that
VoiceXML-based IVR shipments will
exceed more traditional applications.
-DataMonitor
Projected Evolution for the
Speech-Enabled Web Applications Market
Voice Browser
MultiModal
The Voice Web
Voice Browsing Internet
Voice Browser
8/7/2019 Presentation_W3C_VoiceXML
11/14
ApplicationsSIL
Speech is inevitableand can be anywhere!
Multimodal Communication
Location-Based Solutions
Voice Portals
Voice Transactions
Innovation
8/7/2019 Presentation_W3C_VoiceXML
12/14
ReferencesSIL
The W3C Voice Browser Working Group Home Page
http://www.w3.org/TR/voice-intro/
The VoiceXML Forum Home Page
http://www.voicexml.org/index.html
Speech Technology Magazine Home Page
http://www.speechtechmag.com/
W3C Speech Interface Languages: VoiceXML, by James A. Larson, IEEE
Signal Processing Magazine, May 2007, Pgs 126-130
Who Will Win the GUI-VUI Race?
By James A. Larson - Posted Aug 22, 2008
http://www.speechtechmag.com/Articles/Column/Forward-
Thinking/Who-Will-Win-the-GUI-VUI-Race-50396.aspx
8/7/2019 Presentation_W3C_VoiceXML
13/14
ReferencesSIL
An Introduction To VoiceXML
http://www.wirelessdevnet.com/channels/voice/training/voicexmloverview.html
VoiceXML Provides Compelling Case for Adoption
By Susan J. Campbell, March 09, 2007
http://www.tmcnet.com/news/2007/03/09/2405533.htm
The 2008 Star Performers
By Leonard Klie - Posted Aug 22, 2008
http://www.speechtechmag.com/Articles/Editorial/Feature/The-2008-Star-
Performers-50404.aspx
The 2008 Market Leaders
By Leonard Klie, Ryan Joe - Posted Aug 22, 2008
http://www.speechtechmag.com/Articles/Editorial/Cover-Story/The-2008-Market-
Leaders-50419.aspx
8/7/2019 Presentation_W3C_VoiceXML
14/14
SIL
Beyond the virtual
toward reality computing.
endnote