Speech Processing 1 Introduction Waldemar Skoberla phone: +49 731 3994 110 fax: +49 731 3994 250 WWW:

Slides:



Advertisements
Similar presentations
GMD German National Research Center for Information Technology Darmstadt University of Technology Perspectives and Priorities for Digital Libraries Research.
Advertisements

Tuning Jenny Burr August Discussion Topics What is tuning? What is the process of tuning?
COMBASE: strategic content management system Soft Format, 2006.
COMOS Mobile Solutions 1.0 Simplified global collaboration
Automatic Switchboard Operator Luboš Šmídl, Tomáš Valenta Department of Cybernetics Faculty of Applied Sciences University of West Bohemia in Pilsen.
Using Asterisk to Implement Intelligent Call Center Solutions James Kleckner AMTELCO.
TECHNOLOGY FOR MOBILE ADVERTISING SEARCH & COMMERCE © 2007 Apptera Inc. Optimizing Software Architecture for Voice Search SpeechTek 2007.
Lecture 1 Introduction to the ABAP Workbench
Case Tools Trisha Cummings. Our Definition of CASE  CASE is the use of computer-based support in the software development process.  A CASE tool is a.
Introduction To System Analysis and Design
Ajay Joshi. Function  Simple opening screen with large icons for each ‘grouping’ (Efficient)  Opens through a web browser (Efficient)  First time you.
© 2009 Research In Motion Limited Methods of application development for mobile devices.
Introduction to VXML. What is VXML? Voice Extensible Markup Language Used in telephone-based speech applications voice browsing of the web.
Built on the Powerful Microsoft Azure Platform, EventsAIR Provides a Turnkey, Robust Technology Solution for Professional Event Organizers MICROSOFT AZURE.
© 2006 Pearson Addison-Wesley. All rights reserved2-1 Chapter 2 Principles of Programming & Software Engineering.
Knowledge Portals and Knowledge Management Tools
Executive Overview. PLEASE READ (hidden slide) To deliver this presentation effectively, you need to be familiar with Windows Server 2008 R2 management.
FIREWALL TECHNOLOGIES Tahani al jehani. Firewall benefits  A firewall functions as a choke point – all traffic in and out must pass through this single.
Virtual Marketing Manager Online marketing tool for our partners Graeme Armstrong Marketing Manager, HP and Sun.
Mobile Multimodal Applications. Dr. Roman Englert, Gregor Glass March 23 rd, 2006.
About AloTech…  Established in 2007, AloTech is a technology company aiming to provide all functions of a contact center as online “services” to businesses.
Notification Protocol in MMS June 2001 Erez Reinschmidt, Rami Neudorfer 3GPP TSG-T2 SWG3#7 Braunschweig, Germany June, 2001 T2M
© 2011 Autodesk Simplified 5-Axis Machining Ann Mazakas Manager of Technical Communications | DP Technology Corp.
Systems Analysis and Design in a Changing World, 6th Edition
VoiceXML Builder Arturo Ramirez ACS 494 Master’s Graduate Project May 04, 2001.
ITIS 1210 Introduction to Web-Based Information Systems Chapter 48 How Internet Sites Can Invade Your Privacy.
Introduction to the Enterprise Library. Sounds familiar? Writing a component to encapsulate data access Building a component that allows you to log errors.
Systems Analysis – Analyzing Requirements.  Analyzing requirement stage identifies user information needs and new systems requirements  IS dev team.
DonorDirect Offers a Donor Management System Made Specifically for Your Nonprofit Ministry and Delivered by the Powerful Microsoft Azure Platform MICROSOFT.
Lecture 12: 22/6/1435 Natural language processing Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
VMA - Paris, October 2001 Michaela Stuhrmann E-Plus Mobilfunk GmbH & Co. KG Voice Portals, Unified Messaging and other applications: Key factors for a.
11.10 Human Computer Interface www. ICT-Teacher.com.
Interaction Design Session 12 LBSC 790 / INFM 718B Building the Human-Computer Interface.
Chapter 4 – Slide 1 Effective Communication for Colleges, 10 th ed., by Brantley & Miller, 2005© Technology and Electronic Communication.
This presentation outlines the following: How we believe we can help Electronic Marketing Strategy Marketing Overview SMS Marketing Overview Electronic.
Spoken dialog for e-learning supported by domain ontologies Dario Bianchi, Monica Mordonini and Agostino Poggi Dipartimento di Ingegneria dell’Informazione.
AGENDA Introduction to Virtual Mechanic Demo Architectural diagram and summary QA steps and user acceptance testing Bugs in the software Feedback from.
Integrating VoiceXML with SIP services
© 2008 SpeechCycle, Inc. More Than Call Steering Managing Dynamic Contextual Complexity Phillip Hunter VP, Application Design/Development SpeechTek NYC.
IB ITGS Case Study. Introduction: Serving thousands of clients, it is method of environment-friendly green ticketing. User friendly system which minimizes.
KNOVADA – CUSTOMERSOFT SOLUTIONS Maximizing The Business Value Of Your Employees.
The huge amount of resources available in the Grids, and the necessity to have the most up-to-date experimental software deployed in all the sites within.
Submitted By: A.Anjaneyulu INTRODUCTION Near Field Communication (NFC) is based on a short-range wireless connectivity, designed for.
User Support Chapter 8. Overview Assumption/IDEALLY: If a system is properly design, it should be completely of ease to use, thus user will require little.
Copenhagen, 7 June 2006 Toolkit update and maintenance Anton Cupcea Finsiel Romania.
Writing Requirements the Use-Case Way Sreeram Kishore Chavali.
WHAT OUR CUSTOMERS ARE SAYING “After thorough market research and a review process, Qorus Breeze Proposals stood out from the competitors because of its.
Input Design Lecture 11 1 BTEC HNC Systems Support Castle College 2007/8.
Silberschatz, Galvin and Gagne  Operating System Concepts UNIT II Operating System Services.
== Enovatio Delivers a Scalable Project Management Solution Minus Large Upfront Infrastructure Costs, Thanks to the Powerful Microsoft Azure Platform MICROSOFT.
© 2006 Pearson Addison-Wesley. All rights reserved2-1 Chapter 2 Principles of Programming & Software Engineering.
© 2006 Pearson Addison-Wesley. All rights reserved 2-1 Chapter 2 Principles of Programming & Software Engineering.
An SAIC Company Rich Fialkoff Executive Director Customer Care and Billing Solutions (732) March 15, 2001 Operations Support.
Service Management Status 101 th ACCU Meeting Wednesday, September 11, 2013.
Copyright © 2007, Oracle. All rights reserved. Managing Items and Item Catalogs.
Accurate  Consistent  Compliant Contact: i4i the structured content company the structured content company.
Total control software for Breton fabshop equipment.
Coupling and Cohesion Schach, S, R. Object-Oriented and Classical Software Engineering. McGraw-Hill, 2002.
How Sage ERP X3 Systems Can Benefit Businesses.  Sage X3 is an affordable and flexible ERP solution designed to help mid-sized companies manage business.
Software Project Configuration Management
Human Computer Interaction Lecture 21,22 User Support
Simple and intuitive fare conditions
Sourcing Event Tool Kit Multiline Sourcing, Market Baskets and Bundles
11.10 Human Computer Interface
Mentors: Christine Lisetti and Ugan Yasavur
Evaluation of a multimodal Virtual Personal Assistant Glória Branco
Object Oriented Design Patterns - Structural Patterns
TECHNOLOGICAL PROGRESS
VoiceXML An investigation Author: Mya Anderson
Evaluation of a multimodal Virtual Personal Assistant Glória Branco
Presentation transcript:

Speech Processing 1 Introduction Waldemar Skoberla phone: fax: WWW:

Speech Processing 2 Contents 1.Introduction 2.The Purpose of Voice Portals 3.The Expectations of the Performance 4.The Reality 5.Challenges and Problems 6.The Solution 7.Summary

Speech Processing 3 Communication Saying is not listening Listening is not understanding Understanding is not accepting Introduction

Speech Processing 4 The purpose of a dialogue is to ensure that the user gets what he wants Introduction There is a long way between an utterance and its acceptance.

Speech Processing 5 The Purpose of Voice Portals e.g. Unified Messaging e.g. Time Information e.g. Ticket Reservation Voice Portal Instant access to services like news, traffic, weather, stocks, Sports, etc. over the phone User Profile: e.g. personal address book or calendar Access through unique phone number

Speech Processing 6 Comfortable phone access to any kind of information and services (Simple search and find strategy). Quick access to preferred services and information (personalized services). No restrictions to the user’s input (natural language understanding).  Voice Portals should open the access to information and services and not prevent it. The Purpose of Voice Portals

Speech Processing 7  Does the user get what he wants? The Expectation

Speech Processing 8 The Expectation Easy to use (intuitive dialogues, natural language understanding). Flat menu structures with cross connections to all available services. Guidance through the dialogue and context sensitive online help. Easy to maintain and to extend (new services) Easy to find one’s way through the dialogue structure (homogenous user interface in all available services).  Possible? Practicable?

Speech Processing 9 Voice Portal Service 1 Service 2 Service N Phone Access The Reality VP Application (ASR) S1 Application (ASR) S1 Application (ASR & DTMF) S2 Application (DTMF)

Speech Processing 10 The Reality Different approach for Dialogue Design within available services (system driven call flow, mixed initiative approach, with/without Barge In) The voice in System Prompts changes from one service to another (sometimes demanded but usually disturbing). Usage of different technologies (speech recognition, DTMF, Barge In)  Confusion for the user

Speech Processing 11 The Challenge Vocabularies become bigger and grammars more complex (due to new services, natural language understanding, …) Continuous modification of available services and adding of new services Growing number of cross connections among all services Implementation of Text-To-Speech more and more necessary  fast growing complexity of the Voice Portal application

Speech Processing 12 The Problems Big vocabularies may cause recognition confusions, speech recognizer do not offer100% accuracy (higher possibility of similar sounding words) Adding new applications cause increasing maintenance efforts (pre-recording of system prompts, establishment of cross connections, updating of online help, adding new words for the recognizer) Increased misunderstandings due to involved Text-To-Speech engines. (the state of the art quality of TTS is not as good as pre-recorded prompts)  nothing and nobody is perfect

Speech Processing 13 The Problems Does the user always know what he can say and do? (clear structure and prompting) People sometimes do not say what they mean. Is the user always able to handle new and sophisticated features? (natural language understanding)  sometimes less is more (simple applications increase the acceptance)

Speech Processing 14 Voice Portal Service 1 Service 2 Service N Phone Access The Solution? VP Application (ASR) S1 Application (ASR) S1 Application (ASR) S2 Application (ASR) Application Data Exchange

Speech Processing 15 The Solution User adapted guidance and online support (tracing of user behavior and storing of the profile ) Support through natural language understanding (no limits to what the user can say) Hidden user guidance (intelligent prompting) Design to Error  virtually (for the user ) no limitation to the flexibility

Speech Processing 16 The Solution Easier dialogue design through predefined and approved dialogue modules for standardized tasks (input of phone number, requesting time and date, etc.) Support through sophisticated dialogue development tools (no limits to what the user can say)  intelligent tools and predefined dialogue modules reduce development efforts but do not replace human creativity

Speech Processing 17 The Future Fast growing number of speech enabled services. Users become more and more familiar with new technologies. Consideration of Multiple Modes of operation. (e.g. speech input combined with graphical output) Automatic creation of new applications. (research status)

Speech Processing 18 The Summary The complexity of voice portal applications will grow very fast in future. The quality of the services will be improved (sophisticated methods and ASR). Short time to market through dialogue tools and modules support

Speech Processing 19 Since Dialogues are human … … they cannot be completely designed by machines.