W3C Speaker Identification and Verification Workshop



Similar documents
TECHNOLOGY WHITEPAPER

Hitachi ID Password Manager Telephony Integration

Biometrics and National Strategy for Trusted Identities in Cyberspace Improving the Security of the Identity Ecosystem September 19

customer care solutions

Measuring Performance in a Biometrics Based Multi-Factor Authentication Dialog. A Nuance Education Paper

customer care solutions

Shared VRU. A Key Link in Your Customer Service Chain Kyle Shadday, Director, Voice Response Strategy

I. Application Development

BFC Product Evaluation and Selection Process DoD Biometrics Fusion Center. Executive Officer

INCITS 456 Speaker Recognition Format for Raw Data Interchange (SIVR-1)

Cisco IOS Voice XML Browser

Configuration and Management of Speaker Verification Systems

Out-Of-Band Authentication Using a Real-time, Multi-factor Service Model

PRODUCT GUIDE Version 1.2 HELPDESK EXPRESS 1.0

Security aspects of e-tailing. Chapter 7

SECURITY AND PRIVACY ISSUES IN A KNOWLEDGE MANAGEMENT SYSTEM

Voice biometrics. Advait Deshpande Nuance Communications, Inc. All rights reserved. Page 1

PRIME IDENTITY MANAGEMENT CORE

Integrating Biometrics into the Database and Application Server Infrastructure. Shirley Ann Stern Principal Product Manager Oracle Corporation

Federation Are We Ready? Alec Cartwright Authentication Common Capability Design Authority

Cisco IOS Voice XML Browser

101 Things to Know About Single Sign On

Voice Processing Standards. Mukesh Sundaram Vice President, Engineering Genesys (an Alcatel company)

Digital Identity Management

In this Profile. USA Tel: Fax:

Online Identity Attribute Exchange Initiatives

Decision Matrix: Selecting an IVR Vendor in the Enterprise (Competitor Focus)

Biometric SSO Authentication Using Java Enterprise System

ARMORVOX IMPOSTORMAPS HOW TO BUILD AN EFFECTIVE VOICE BIOMETRIC SOLUTION IN THREE EASY STEPS

Agenda. Announcement: Verint Acquires Victrio Victrio Solutions Client Results in Deployment Critical Success Factors Verint + Victrio Synergy

Adaptive HTTP streaming and HTML5. 1 Introduction. 1.1 Netflix background. 1.2 The need for standards. W3C Web and TV Workshop, 8-9 February 2011

Arkansas Department of Information Systems Arkansas Department of Finance and Administration

VoiceSign TM Solution. Voice Signature Overview

Online Identity Attribute Exchange Initiatives

customer care solutions

solutions Biometrics integration

Physical Security: A Biometric Approach Preeti, Rajni M.Tech (Network Security),BPSMV preetytushir@gmail.com, ratri451@gmail.com

AUTHENTIFIERS. Authentify Authentication Factors for Constructing Flexible Multi-Factor Authentication Processes

Using Voice Biometrics in the Call Center. Best Practices for Authentication and Anti-Fraud Technology Deployment

Disaster Recovery Allowance South Australia Pinery Bushfire November 2015

State of Oregon. State of Oregon 1

Chapter 1: Introduction

GET A DOT YOU CAN BANK ON.

This method looks at the patterns found on a fingertip. Patterns are made by the lines on the tip of the finger.

DEA's New Proposed Regulations For E-Prescribing

VoiceXML Data Logging Overview

NISTIC Pilot - Attribute Exchange Network. Biometric Consortium Conference

Top Authentication & Identification Methods to Protect Your Credit Union

See Appendix A for the complete definition which includes the five essential characteristics, three service models, and four deployment models.

Voic . Advanced User s Guide. Version 2.0

Software Only Biometrics to Authenticate Student ID

KEYSTROKE DYNAMIC BIOMETRIC AUTHENTICATION FOR WEB PORTALS

Early Intervention Services for Children with Disability Program

Request for Proposal. Pre Bid Meeting. Implementation & Maintenance of Call Center Solution (CCS) Wednesday 06 May 2015

TECHNOLOGY WHITEPAPER

Biometrics and Cyber Security

ISO Biometric Template Protection

Single Sign-on and Biometrics

FINANCIAL INDUSTRY TRENDS REPORT - Cashing in on the Customer Experience: 7 Steps to Revolutionize Your Bank s Customer Service Strategy

Automated Regional Justice Information System (ARJIS) Acceptable Use Policy for Facial Recognition

FTP-Stream Data Sheet

Application for Bond Loan and Rental Grant assistance

IT General Controls Domain COBIT Domain Control Objective Control Activity Test Plan Test of Controls Results

Evaluating Speech Self-Service Platforms

The Benefits of Cloud Computing to the E-Commerce Industry July 2011 A whitepaper on how hosting on a cloud platform can lower costs, improve

Six Challenges for the Privacy and Security of Health Information. Carl A. Gunter University of Illinois

Disaster Recovery Allowance NSW East Coast Storms and Flooding April 2015

customer care solutions

Security+ Guide to Network Security Fundamentals, Third Edition Chapter 8 Authentication

JTC 1/SC 27Security Techniques - Översikt arbetsgrupper och standarder

VoiceXML and VoIP. Architectural Elements of Next-Generation Telephone Services. RJ Auburn

Unifying framework for Identity management

Alternative authentication what does it really provide?

Disaster Recovery Allowance Tropical Cyclone Marcia (Qld) February 2015

Multi-Factor Authentication of Online Transactions

The future of eresearch user support

Diploma of Financial Services (Financial Planning) and RG 146 Application Form

Vendor Master Data Supporting Documentation Specification Commercial

CPP30411 Certificate III Security Operations Recognition of Prior Learning & Current Competency Kit. Evidence Matrix and Collation Report

Diabetes Management in the Primary Care Setting

Table of Contents. Auditor's Guide to Information Systems Auditing Richard E. Cascarino Copyright 2007, John Wiley & Sons, Inc.

Information security controls. Briefing for clients on Experian information security controls

Vendor Master Data Supporting Documentation Specification Commercial

Learning Management System Evaluation Guide

Common Criteria Evaluations for the Biometrics Industry

De Nieuwe Code voor Informatiebeveiliging

Establishing A Multi-Factor Authentication Solution. Report to the Joint Legislative Oversight Committee on Information Technology

RealMe. Technology Solution Overview. Version 1.0 Final September Authors: Mick Clarke & Steffen Sorensen

Custom Software Development Portfolio. Innovation Collaboration Evolution Results

National Cyber Security Policy -2013

Biometrics for Global Web Authentication: an Open Source Java/J2EE-Based Approach

Multi-factor authentication

Clinical Governance for Nurse Practitioners in Queensland

Type of Personal Data We Collect and How We Use It

Applying Cryptography as a Service to Mobile Applications

Erie County Medical Center Corporation. Addendum Number 1 to RFP # EMR Voice Recognition System

Web Based. Fingerprint Time & Attendance Service

RF-Enabled Applications and Technology: Comparing and Contrasting RFID and RF-Enabled Smart Cards

Transcription:

W3C Speaker Identification and Verification Workshop Speaker Verification in a Multi-Vendor Environment Mr Ross Summerfield (with support from Dr Ted Dunstone and Dr Clive Summerfield)

What is Centrelink? What is Centrelink? Equivalent to the US Department of Social Security Centrelink is an agency within the Australian Department of Human Services Mission is: Serving Australia by assisting people to become self-sufficient and supporting those in need. Service provider to over 20 government departments Including FaHCSIA, DVA, DEEWR, DAFF, DHA Services 6.5 million customers Includes delivery of a range of payments to Australians, including people with disabilities, retirees, families, carers, parents, Indigenous people and people from diverse cultural and linguistic backgrounds. Also includes crisis referral and disaster response. Has the largest call centre in the southern hemisphere More than 32 million phone calls per year Has web self services based around portals More than 18 million on-line transactions per year.

Overview of Centrelink's Speaker Verification system Identity and authentication is central to Centrelink s services Multi-algorithm solution Provided by two vendors, using an integration component (VACM) Built for semi-complex 2-factor authentication (to Australian Government Authentication Framework standards) SV Currently sits in an IVR environment Proprietary Intervoice IVR Nuance's (Speechworks vintage) Natural Language Speech Recognition plans to upgrade Nuance Text to Speech Web Services based

Centrelink's deployment Conducted a proof of concept, followed by a pilot, followed by a production deployment Stage-gate based approach to careful consideration of using this biometric based security service Conducted over a period of nearly 5 years (from concept) Included community and privacy group consultation Each stage successful Built as an initiative of data security (Run from S&IP branch) Currently being rolled out to high volume telephone callers Considering offering it to enable employment declaration processing initially over the telephone possibly over the web in the future Other multi-factor credentials are also being considered It would be part of a mix of credentials available

Centrelink's future intentions Propose to incorporate SV wholly into the security services Speaker verification is seen as a security credential used for confirming an identity, rather than being a component of a user interface. Becomes part of a security solution suite to assure identity providing authentication services to the IVR and providing authentication services to web still operating as a web service (as per our security services) Considering using its text independent features in the future

Centrelink's current system

Centrelink future directions

Data Content For the biometric only (step 1) authentication: Initialisation Provides: customer access number (CAN) (from IVR) Receives: registration profile (identifier as known by SV and details around the enrolment) Authentication: Provides: calculated result and scores from each engine for the combination of CAN, name and random digit measurements» scores logged for audit and legal purposes Receives: Question set to ask and rules around question processing

Data Content For the secret question and answer (step 2) authentication: Initialisation The already received question identifiers and rules Authentication: Provides: calculated result and scores from each engine for the answer to the secret question measurements Receives: calculated authentication status (i.a.w. AGAF process)

VoiceXML How it can help us Parallel processing and pipe-lining Current customer experience is gaps between requests for data and the associated provision and the next request Speaker verification could be processing in the background while the next request and acquisition is made Better support for streaming to both speech recognition as well as speaker recognition Some speech requires both recognition and speaker authentication recognition is also a part of the authentication mix

Standards for Speaker Verification For Centrelink (and the Australian Government in general), web services are important All our security services are web services based Our web pages are all portal based (Websphere) ISO standards (CBEFF and BioAPI) are a good start but they are not web services based Australian Biometrics Institute Privacy Code of Conduct Because privacy is a fundamental human right under the charter of 1948 Voice samples and templates should be treated as personal information Encryption is extremely important for biometrics It is very much about perception: being seen to be doing everything possible to protect the credentials Most important for opt-in (and opt-out) systems As voice data is indeed a very powerful biometric identifier, this data collection has very important implications for speech recognition systems

Standards for Speaker Verification Support in VoiceXML is probably not important to us since we are moving to use it as a piece of the security infrastructure not the voice interface Centrelink approaches speaker verification from a security perspective rather than a user perspective therefore not seen to be part of the user interface layer the technology is not considered by Centrelink to be a component of speech recognition but a technology for enhancing security and identity authentication process

A proposed arrangement: Pictorial outline

A proposed arrangement: Pictorial outline

Questions