TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. Optimizing Software Architecture for Voice Search SpeechTek 2007.

Slides:



Advertisements
Similar presentations
Institut Software- und Systemtechnik Fraunhofer ISS T 1 Current Service Platform and Architecture Design Personalization and Context-Awareness Bernhard.
Advertisements

Extended Enterprise Laboratory, Hewlett-Packard Laboratories, Bristol Keryx: Internet Notification Service for Dynamic Web Applications Søren Brandt Anders.
Data Mining and Text Analytics Advertising Laura Quinn.
Automatic Switchboard Operator Luboš Šmídl, Tomáš Valenta Department of Cybernetics Faculty of Applied Sciences University of West Bohemia in Pilsen.
With the BlueAnt S4 you no longer have any need to touch your mobile phone or car speakerphone while driving With the S4 you are truly hands-free. Use.
A PowerPoint Presentation
Rob Marchand Genesys Telecommunications
Google Chrome & Search C Chapter 18. Objectives 1.Use Google Chrome to navigate the Word Wide Web. 2.Manage bookmarks for web pages. 3.Perform basic keyword.
Leveraging Your Taxonomy to Increase User Productivity MAIQuery and TM Navtree.
A Practical Solution to the Challenges of Mobile Access The Power Interface Adam Cheyer VP, Engineering Dejima, Inc.
Dialogue – Driven Intranet Search Suma Adindla School of Computer Science & Electronic Engineering 8th LANGUAGE & COMPUTATION DAY 2009.
6/2/ An Automatic Personalized Context- Aware Event Notification System for Mobile Users George Lee User Context-based Service Control Group Network.
Web- and Multimedia-based Information Systems. Assessment Presentation Programming Assignment.
Ford’s Sync Software Ashley Thomas. What is Sync Software? a digital interface that uses specialized software that allows drivers and passengers to control.
1 CS 430: Information Discovery Lecture 22 Non-Textual Materials 2.
Speech recognition, understanding and conversational interfaces Alexander Rudnicky School of Computer Science
Semantic Web and Web Mining: Networking with Industry and Academia İsmail Hakkı Toroslu IST EVENT 2006.
Overview of Web Data Mining and Applications Part I
Best Practices Using Enterprise Search Technology Aurelien Dubot Consultant – Media and Entertainment, Fast Search & Transfer (FAST) British Computer Society.
Computational Advertising Duygu Gunaydin Lu Li Shuanglong Wei.
Presented by Jacob Wilson SharePoint Practice Lead/Principal Bross Group 1.
© 2012 Cisco and/or its affiliates. All rights reserved. CDN-4698 Cisco Public Collaboration Enabled Business Transformation (CEBT) Integration Platform.
1 A Practical Rollout & Tuning Strategy Phil Shinn 08/06.
Machine Learning at Orbitz Robert Lancaster and Jonathan Seidman Strata 2011 February 02 | 2011.
Should Intelligent Agents Listen and Speak to Us? James A. Larson Larson Technical Services
VoiceXML Builder Arturo Ramirez ACS 494 Master’s Graduate Project May 04, 2001.
Using the NASA Thesaurus to Support the Indexing of Streaming Media Gail Hodge Information International Associates, Inc. Janet Ormes & Patrick Healey.
MBL393 Location Aware Devices Chung Webster Application Development Consultant.
Improving Customer Experience through Personalization Ron Owens Wednesday, August 9, 2006.
SOA in Telecommunications September 30, 2008 Speaker: Mike Giordano.
1 Advertising & The Telephone SpeechTEK West ’07 B204 – Randy Haldeman.
Leveraging The Telecom Transition to IP Communications Infrastructure CANTO June 2005 Dennis Haar President & CEO.
Turbulent change drives Communications and the Voice User Interface Bill Meisel President, TMA Associates Editor, Speech Strategy News
Super-charge Your Speech Application With Cross- Functional Reporting Techniques Bjorn Austraat Director, Solution Delivery TuVox, Inc. August 9 th, 2006.
Automation in Directory Assistance – How to Improve Profitability Brad Schorer - VoltDelta SpeechTEK West February 22, 2007.
» Jun 9, 2003 Speaker Verification Secure AND Efficient, Deployments in Finance and Banking Jonathan Moav Director of Marketing
Web Searching Basics Dr. Dania Bilal IS 530 Fall 2009.
Display & Remarketing What You Need to Know. PROPRIETARY AND CONFIDENTIAL / COPYRIGHT © 2013 BE FOUND ONLINE, LLC 2 WHAT IS DISPLAY?
Dixon Jones Receptional Internet Marketing. WWW: Machine or Alive?
© 2008 SpeechCycle, Inc. More Than Call Steering Managing Dynamic Contextual Complexity Phillip Hunter VP, Application Design/Development SpeechTek NYC.
XP New Perspectives on The Internet, Sixth Edition— Comprehensive Tutorial 3 1 Searching the Web Using Search Engines and Directories Effectively Tutorial.
Page 1www.sitecore.net Behavioral Targeting – Live!  The importance of understanding and attaching engagement value  to each visitor interaction Presented.
Page 1 Alliver™ Page 2 Scenario Users Contents Properties Contexts Tags Users Context Listener Set of contents Service Reasoner GPS Navigator.
Context Awareness: From Dream to Reality Norman M. Sadeh School of Computer Science Carnegie Mellon University Research Sponsors: DARPA/DAML, IBM, Boeing,
Ivan Elhart - ECE 992 Ubiquitous Computing University of New Hampshire 10/09/2008.
Speech Interfaces User Interfaces Spring 1998 Drew Roselli.
Research Topics/Areas. Adapting search to Users Advertising and ad targeting Aggregation of Results Community and Context Aware Search Community-based.
1 comedycentral.com in the world of contextual advertising Don Steele Search Engine Strategies Conference Chicago, 12/5/06.
Intelligent Robot Architecture (1-3)  Background of research  Research objectives  By recognizing and analyzing user’s utterances and actions, an intelligent.
DAWN: Dynamic Aural Web Navigation Gopal Gupta, S. Sunder Raman, Mike Nichols, H. Reddy, N. Annamalai Department of Computer Science University of Texas.
DIGITAL ADVERTISING Standard 4. THE ROLE OF DIGITAL ADVERTISING IS TO INCREASE SALES OR IMPROVE BRAND AWARENESS.
Toward Semantic Search: RDFa based facet browser Jin Guang Zheng Tetherless World Constellation.
August 2013 The Rise of Voice Search James Turner Account Executive Bing Ads.
NEM – How to implement Convergence! SRA Presentation – Update May 2006
Behrooz ChitsazLorrie Apple Johnson Microsoft ResearchU.S. Department of Energy.
Speech Processing 1 Introduction Waldemar Skoberla phone: fax: WWW:
W3C Multimodal Interaction Activities Deborah A. Dahl August 9, 2006.
1 DATA-DRIVEN SOLUTIONS. 2 KEYWORD-LEVEL SEARCH RETARGETING TARGET USERS BASED ON THEIR RECENT SEARCH HISTORY AND SEARCH QUERIES. A user performs a search.
1 Multimedia services over networks Service provider Service client Service registry Publish Discovery Bind Multimedia system Review/background Framework/
Semantic Web Technologies Readings discussion Research presentations Projects & Papers discussions.
Sitecore. Compelling Web Experiences Page 1www.sitecore.net Customer Engagement Platform Presented by.
A seminar by Ramesh Kumar Raju S CSSE 07121A1547.
Siri Voice controlled Virtual Assistant Haroon Rashid Mithun Bose 18/25/2014.
15 free things you can do to climb higher on Google
Contents 1.What is Digital Marketing? 2.Vmayo Digital Marketing Solutions 3.Why Vmayo Technologies?? 4.Application of Digital Marketing.
Continuous Automated Chatbot Testing
Global Enterprise Search
11/23/2018 8:30 AM BRK3037 BRK3037: Dive deep on building apps and services with the Office 365 Communications Platform David Newman Senior Program Manager.
Core Platform The base of EmpFinesse™ Suite.
Agenda What is SEO ? How Do Search Engines Work? Measuring SEO success ? On Page SEO – Basic Practices? Technical SEO - Source Code. Off Page SEO – Social.
Presentation transcript:

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. Optimizing Software Architecture for Voice Search SpeechTek 2007

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 2 Agenda  What is Voice Search?  Example of Voice Search applications  Different types of Voice Search Designs  Challenges of developing a Voice Search Application  Solutions to tackle those challenges  Technique for building an ad-based Voice Search Application  Demo

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 3 What is Voice Search? Speak the Query & Get the Search Result

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 4 Voice Search Applications  Directory Assistance  Business Name or Category Search  Locator & Driving Direction  Information Search  News or sports query  Stock quotes  Traffic & weather  Content Search  Music & Ring tones  Video Clips  Web Search with Voice Control

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 5 Voice Search Designs  Pure Voice Search  User speaks the query and the system returns the query result through voice  Best use for telematics or any hands-free non-visual environment  Multi-modal Voice Search  User speaks the query and the system returns the query result to the delivery channels other than voice  Best use for lookup service that returns long or hard-to-remember result set

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 6 Voice Search Approaches  Open-end voice search  Natural language based connotative queries  High word error rates for large vocabulary sizes  Limited context to leverage for improving speech recognition  Multi-step hierarchical voice search  Keyword based denotative queries  Dialog driven  High word error rates for large vocabulary sizes  Takes longer to navigate through the dialogs to get result

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 7 Voice Search Nirvana  Open-end voice search interface  Support a wide-range of voice vocabulary and phrases  Low recognition error rate  Able to leverage contextual information to improve speech recognition  Real-time performance

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 8 Voice Search Challenges  Really Short Query  Really Long Query  Dealing with Homonyms  Ad vs. Add  Oral vs. Aural  Dealing with Acronyms  DOS  NASA

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 9 Voice Search Solution  Intent Identification technology  Match recognized raw user utterance against a context sensitive semantic index  Identify a short list of the most likely intents  Prompt the user with intelligent follow-up question to narrow down the intent identification Consumer utterance: “Closing costs” System question: “Are you searching for mortgage information?”  Formulate the query once the intent is locked  Render the query result to the preferred channel for delivery

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 10 Voice Search Design  Understand the application  Front-end Interface  Backend Search Engine  Identify the target users  Collect the possible utterances and build the grammar around it  Open-end vs. Dialog driven  Coverage vs. Predictive power

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 11 Voice Search Design -- A Level Deeper  Leverage the historical dataset from existing web query infrastructure to increase the speech recognition accuracy  Develop grammar based upon the web query logs  Expand the grammar with ontology for connotative recognition  Leverage contextual & profiling data  Caller ID, device type  DNIS, LBS, CRM lookup,  Search keywords, search result and call flow history For ad targeting

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 12 Voice Search Design -- A System Architecture Apptera Application Server

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 13 Voice Search Demo Free-411 “Category” Example

TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. 14 Free-411 Demo: Category Ad with Directions $1.25 Bid $1.00 Bid What city and state? __________ What listing? ____________ Restaurants Denver, CO __ Business __ Residence  $1.50 Bid