Upload
others
View
3
Download
0
Embed Size (px)
Citation preview
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 1
Dragon TV Overview TIF Workshop 24. Sept. 2013
Reimund Schmald
mob: +49 171 5591906
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 2
Reinventing the relationship between people and technology
– Defining the next generation of human-computer interaction: Intelligent Systems
– Deeply invested in creating effortless and natural user experiences
– Best known for rapidly advancing voice-recognition technology
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 3
At Nuance we believe the greatest opportunities you face will only be realized through the power of intelligent systems.
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 4
What we mean by Intelligent Systems Natural user interface meets ambient intelligence
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 5
Fundamentally rethinking how technology adapts to people, not the other way around.
– People expect technology that understands natural input, and demand the shortest distance between “want” and “get.”
– Applications across enterprises and healthcare include radically effective customer service, clinical documentation and document management.
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 6
With leading global relationships, it’s rare to go a day without Nuance
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 7
5 billion mobile cloud transactions annually
3,900 patents & applications
65+ countries
12 billion customer calls served annually
800 million mobile keyboards shipped annually
13,000 mobile app developers
12,000 employees
70+ languages
1,200 voice and language scientists and engineers
5 billion lines of medical data transcribed annually
25 million voice-enabled cars sold annually
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 8
Healthcare Driving a revolution in patient care
We take clinical documentation, coding and
compliance to the next level
– Industry-leading speech and clinical understanding
technologies
– Disruptive solutions bridge documentation, CDI,
coding, compliance, and analytics; the only
end-to-end solution
– Easing transition for regulatory change of ICD-10
and Meaningful Use
– Deep customer and partner relationships, from
large IDNs to practices
– Strong growth and operating model in large
addressable markets
Upsides – Automates medical coding
– Creates detailed patient records for meaningful use
– Improve patient care
– Increase the quality of documentation
– Streamline medical coding and billing processes
– Achieve ICD-10 reimbursementthrough high specificity
– Reduce burden on clinicians by increasing efficiency
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 9
Customer Care Customer service, intelligently delivered
Automation meets extraordinary user experiences
– Consumers can quickly and easily get what they need from your business – anytime, anywhere
– Seamless experiences across IVR, mobile and web
– Easy, powerful self-service
– Identity verification
– Cloud-based service delivery
– Customer experience expertise
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 10
Imaging + Managed Print Services Take control of your content
More intuitive, powerful and meaningful interactions between people and the technology they use for creating and managing documents.
A fully integrated set of compatible and interoperable solutions
– Strong foundation in automating document processes
– A complete portfolio of Capture, Convert and Print Management solutions
– Deep industry and OEM expertise
– Rapid growth fueled by cloud and scan-to-enterprise services
Upsides
– Smooth workflows
– Powerful security features
– Waste reduction
– Access from any source, on any device
– Instantly convertible formats
– Collaboration, sharing, editing, printing
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 11
Mobile + Applications Intelligent interfaces for intuitive, personal experiences.
Nuance is driving mainstream demand for simpler devices that make life easier
– With mobile solutions that are revolutionizing life for on-the-go users
– Voice assistant-powered devices that are aware, listening, understanding
– Using touch, gesture, and ambient information
– Across all mobile platforms, channels and devices
– Deployed by leading global brands in consumer electronics
– Giving personality to the entire category
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 12
Automotive
Stability
Standards
Command & Control
Content Accessibility Noise Robustness
Eyes & Hands Free
Messaging
Dragon Drive
Confidential.
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 13
Dragon Assistant
Semantic Web
Device Control &
Communications
Languages Personalities
Human-like TTS
Conversational
Assistant-to-Assistant
Connections Customizable
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 14
Dragon TV
Premium User experience
Intuitively control your TV or STB with your voice
Directly search for content across VoD, EPG, web
Flexible integration concepts
Embedded integration into TV or STB devices
Cloud-based solutions for companion apps
Leading Technology Solution
Nuance is the leading supplier for voice technology
Dragon TV solution is optimized for the living room
Changing the way we interact with devices and content in the living room
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 15
Dragon TV Solution Overview
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 16
The TV Ecosystem is Evolving
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 17
Remotes are not fit for the challenge
In order to search for content remotes have become unwieldy.
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 18
The Solution: Operating TV by Voice
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 20
With Dragon TV you simply tell your TV what you want
“What’s on Sky this evening?”
“Sure.
Here is what I
found for you!”
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 21
Natural Language Content Search How it works
“I want to see dramas with Judy Foster.” SEARCH &
DISPLAY LISTINGS
<Carnage> <The Beaver> <Inside> <Flightplan>
<Abby Singer> <Waking the Dead> <Contact ><Nell>
<Sommersby ><Shadows and Fog> <Little Man Tate>
<The Silence of the Lambs> <Catchfire> <The Accused>
<Stealing Home>
SPEECH
RECOGNITION
UNDERSTANDING
INTENT [filler] i want to [/filler]
[IntentPlay] see [/IntentPlay]
[Genre] dramas [/Genre]
[filler] with [/filler]
[Actor] jodie foster[/Actor]
CONTENT
LOOKUP N
uan
ce
Serv
er
Clie
nt A
pplic
ation
JSON results
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 22
Dragon TV Technology components
Automatic Speech Recognition - Optimized television language models for turning spoken words into text
Natural Language Understanding - Natural language framework for deep meaning extraction and enhanced discovery and control
Text-To-Speech Dialog-driven speech output for robust auditory feedback and guidance
Voice Biometrics – Seamless user authentication enabling multiple profiles on a single, shared device
Close and Distant Talk – Support close-talk audio via a remote or companion app and/or distant-talk with a microphone array in the TV bezel or external accessory
Ready-to-Integrate Solution Packages
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 23
Dragon TV Integration Scenarios
2nd screen
Smart Device
Close-talk audio
Microphone on Remote
Close-talk audio
Microphone on Phone/Tablet
1st screen
TV or Set-Top-Box
Distant-talk audio
Microphone array in TV bezel or
external accessory
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 24
Dragon TV solutions
for Companion apps
(2nd screen)
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 25
Dragon TV for 2nd-screen App
• Voice interaction for companion apps
• SDK supports iOS and Android phones and tablets
• Simple integration allows for quick time-to-market
• Application domains
• Command & control of TV or STB
• EPG Navigation
• Content Search
• Integration options:
• Thin client via cloud based search
• Simple embedded command & control
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 26
2nd screen Integration: Thin client for cloud NLU
Client Solution: Dragon TV Cloud SDK
– Small footprint local client (iOS, Android)
– Provides access to Nuance Speech Servers with powerful speech recognition and NLU
Use Cases
– Flexible Command & Control of TV or STB
– EPG Navigation
– Natural Language Movie Search (VoD, TV,...)
Benefit
– Simple integration of powerful server-based voice technology allows for fast time-to market
Nuance
Cloud Solutions
Reference: major US cable operators
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 27
Client Solution: VoCon Add voice enabled command & control through
integration of VoCon embedded speech recognition
Use Cases • Channel switching
• Device control and menu shortcuts
• EPG Navigation
Benefit • Low latency command & control
• Available for all VoCon languages (30+)
• Full flexibility of supported commands and domains
2nd screen Integration: Embedded Control
Reference:
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 28
Dragon TV solutions
for TV and STB
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 29
Dragon TV solution for TV or Set-Top Box
Combination of local and remote technologies
Embedded speech recognizer (VoCon)
Connection to full cloud-based solution (NCS)
Adaptive Speech Recognition
Natural Language Understanding
Option to integrate premium features
Text-To-Speech (Vocalizer Expressive)
Speaker identification (Voice Biometrics)
Voice input via microphone on
remote control
Nuance
Cloud Solutions
Hybrid approach provides the best of both worlds Low latency local recognition for command&control
Powerful cloud technology for flexible search
Local use cases are possible “offline”
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 30
Distant Talk for Hands-Free interaction
Nuance Speech Signal Enhancement (SSE) enables
distant-talk speech recognition in the living room
Hands-free interaction
No need to find remote control
SSE battles key acoustic challenges
TV sound
Disturbance from other speakers
Background Noise Sources
Option for integration with camera solution
Visual beam-steering
Combined user identification by voice + face
Combination of speech & gestures
Distant Talk audio input via Microphone Array
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 31
High-Level Architecture
Speech Signal
Enhancement
Internet Search LM Dictation LM TV Search LM
Network Interface TV
/ S
TB
N
uan
ce C
lou
d S
erv
er
Dra
go
n T
V
Hyb
rid
SD
K
Hybrid Recognition
Local
Recognition
Network
Interface
Voice
Biometrics
2nd screen app
TV (1st screen) app
NL
U
Sp
eech
Reco
gn
itio
n
TV
NLU Server
TTS
Ph
on
e /
Ta
ble
t
Dragon TV Cloud SDK
Network Interface
Entertainment
domain data
Client
TTS
Distant-Talk Acoustics Close-Talk Acoustics
ADK
Dialog
nightly update
Thin-client for phone or tablet
devic
e
clo
ud
Hybrid Solution for TV or Set-Top Box
Client
EPG data
© 2002-2013 Nuance Communications, Inc. All rights reserved. Page 32
Thank you