How accurate is AGNITIO KIVOX Voice ID?

Size: px
Start display at page:

Download "How accurate is AGNITIO KIVOX Voice ID?"

Transcription

1 How accurate is AGNITIO KIVOX Voice ID? Overview Using natural speech, KIVOX can work with error rates below 1%. When optimized for short utterances, where the same phrase is used for enrolment and authentication, KIVOX can work with error rates as low as 0.5%. Error rates depend on several factors, such as length of utterance, audio quality and working points. To predict the error rates for a specific use case, audio samples that are as close as possible to the real world samples will be needed, and the threshold (high security or high convenience) in the desired working point will need to be set appropriately. KIVOX can achieve error rates below 1% for complete free speech conversations of seven seconds in length in a typical call center environment, using a voice print created from at least 30 seconds of speech. KIVOX can be optimized for short utterances in collaborative situations to obtain better error rates with shorter utterances. In that case, the user will enroll by repeating a selected sentence, of two to three seconds in length, three times and then they can authenticate by repeating the same sentence once. When a user is always authenticating via the same device, like a smart phone, or tablet, error rates below 0.5% are achieved. These error rates change to 1%-5% when very short phrases of less than two seconds are used, such as those used for wake-up functions. Scenarios where more challenging telephonic infrastructures are used (like call center or IVR environments) and customers can use different methods for authentication, can also result in these slightly higher rates. 1. Accuracy metrics for biometric authentication A standard authentication system usually returns a confidence score that determines whether or not the identity of the user is confirmed and they are successfully authenticated. That score can come from many different sources. For AGNITIO products, this score comes from a comparison made between the existing voice print of the user and the new access sample that is taken during the authentication process. This likelihood score is typically higher as the new sample is likely to be more similar to the already existing voice print. In order to make a decision, based on that score, the most typical approach is to set a threshold. Every time the score is above that set threshold, the user is verified, and if the score is below, the user is rejected. Using this method, two types of error can occur: 1 of 5

2 False rejection error: when a legitimate user is rejected by the authentication system (also referred to as a missed probability) False positive error: when an impostor is erroneously accepted as a legitimate user (also referred to as a false acceptance (FA) error) These two types of errors are related to the set threshold. When the threshold is set higher, false acceptance errors will be reduced, but the probability of a false rejection (FR) will be higher. The opposite behaviour will be obtained moving the existing threshold to a lower value (reducing the false rejections but increasing the false acceptances). So, we can conclude that FR and FA are inversely proportional. For this reason, an infinite number of working points are possible, which are the specific pairs of FR/FA error rates selected for a given platform and threshold. In order to measure and compare the accuracy of different systems, it is not possible to use a single working point, because depending on the specific application or use case, a different setting will be needed. There is therefore a need to understand the behaviour of that authentication technology in all possible working points. In order to do that, the DET (Detection Error Trade-off) curves are used. The idea is try to calculate all the possible FR/FA pairs for a given system by moving back and forth through the thresholds. All the working points obtained are then represented as a single curve where the X and Y axis are representing false acceptance rates (FAR) and false rejection rates (FRR) respectively. There is a special working point that is often used in order to compare two systems with a single number. That point is the Equal Error Rate (EER). The EER point has the property of having FAR and FRR equal. The EER is easy to obtain as the crossing point between the DET curve and the bisecting line of the graph. In general terms, DET curves within systems are parallel, so that means that the system with the lower EER is usually the one performing the best across all the working points. EER is a good metric to summarize the accuracy of a biometric system in a single number, but, if a system has an EER equal to 1%, it doesn t mean that you cannot achieve lower FAR or FRR, it simply means that if you want to get an FAR lower than 1%, you will need to have an FRR higher than 1% and vice versa. Therefore EER represents the point where you can achieve the lowest error rates at the same time. Usually, system don t use the EER as the working point. High security systems require very low FA (below EER) so they will have a higher FRR than the EER. In the same way, a user friendly system requires low FR (lower than the EER) making the FA higher. These points are illustrated in the following DET graphic: 2 of 5

3 2. AGNITIO s KIVOX Accuracy AGNITIO technology is based on natural speech. In collaborative environments, where the same passphrase is used for enrolment and authentication, better accuracy can be achieved for very short utterances. KIVOX can therefore authenticate users in two different modes. Firstly, when the user is actively participating in the authentication process via an app or an IVR system, a text dependent (phrase-specific) approach is used in order to reduce the time for the authentication. Secondly, when the authentication is done in a non-collaborative/transparent way, when the user is speaking freely with an agent or using the navigation commands of a smartphone, a text independent (natural speech) approach is used. 3. KIVOX Passphrase option (Text dependent) In this case, the user enrolls by repeating a two to three second long sentence, three times. Once the user models are created, only a single repetition of that same phrase is needed to authenticate the user. From there, and depending on the specific use case, KIVOX will obtain a variety of different error rates. For those scenarios where KIVOX is used in the Cloud to get users authenticated while using a unique device (typically a smartphone or tablet where are accessing protected content or an app), KIVOX s proprietary text dependent technology performs with EER as low as 0.5% depending on the sentence selected. Below, we see some DET curves that are evaluating the performance of different phrases: This level of performance means that the system can operate with working points as low as FA=FR=0.5%. Lower levels of FA or FR are possible if the user will accept a higher level of error. While two to three seconds long is the standard length for an authentication phrase, a wider variety of use cases can be tackled with KIVOX server based technology. The most typical of these use cases is when the technology is embedded in a call center/ IVR infrastructure. In that kind of environment, a wide variety of elements (switches, CTI, IVR, trunks) can affect the quality of audio. In addition, in many cases, the user will want to authenticate from different devices (home landline phone, mobile phone, office VoIP phone, etc.). In these scenarios, KIVOX is a powerful tool as it allows enrolment and authentication to be performed across many different kinds of communication 3 of 5

4 channel. In these situations, it is quite normal to obtain lower accuracy numbers, but AGNITIO KIVOX technology can work with an EER of 1% to 5%, even in the most challenging environments and infrastructures. Below you can find a couple of examples of performance obtained in real deployments: It can be observed that even in the most challenging scenarios (right graph), it is possible to get False Alarm rates as low as 0.5% while still successfully authenticating more than 90% of your legitimate users, and that can increase to 95-98% in better environments. 4. KIVOX Natural Speech Option (Text independent) For natural speech authentication, a minimum of 30 seconds of free speech from the user is needed to enroll. As this environment is fully text independent, an old recorded conversation of the user with an agent in a call center, or historical data saved from the user navigating through an automated system, can also be used. Once enrolled, only seven seconds of speech is needed for authentication. For these reasons, it is this type of technology that is preferred in a call center environment because even with this more complex scenario, the levels of accuracy can be kept very high. In optimal conditions, KIVOX can run in a fully text independent environment with an EER below 1%. One could imagine that error rates using text independent authentication would be higher because in text dependent mode, you have a very restrictive vocabulary that makes authentication easier. However, the more speech samples available for a specific user, the better the accuracy of the system, because the biometric voice print contains a much richer, more variable collection of that person s speaking voice. The typical performance of a system with a number of different length speech samples used for authentication is shown below. Again, we must take into consideration that it is possible to obtain working points where FA or FR can be lower than 1% and we typically see variation in the range of 1% to 3%. The chart on the next page shows performance based on the length of audio used to verify the speaker (20, 30 and 60 seconds). In all cases, five calls from the specific customer were used to initially train the model. As you can see, in the 60 second examples, a working point with FA of 0.1% and FR of 2.5% can be achieved. 4 of 5

5 About AGNITIO AGNITIO is a recognized global leader in voice biometrics, with highly accurate, spoof-protected, ultra-fast technologies for speaker identification. The company works with partners worldwide to enable voice identification in the most challenging environments, including intelligence agencies, law enforcement and corporations. AGNITIO is now pioneering voice identification solutions for online transactions and business applications. The AGNITIO voice biometrics engine offers a high degree of accuracy, with the added protection of patented anti-spoofing techniques. The flexible voice identification engine, available to partners through an API, works in a wide range of applications and across languages. For more information or to request a demonstration, visit 5 of AGNITIO

Passive Detection. What is KIVOX Passive Detection? Product Datasheet. Key Benefits. 3 APIs in one product

Passive Detection. What is KIVOX Passive Detection? Product Datasheet. Key Benefits. 3 APIs in one product Passive Detection Product Datasheet KIVOX Passive Detection is part of the KIVOX 4.0 family of products. KIVOX 4.0 brings our partners the full potential of real voice biometrics technology by providing

More information

Guide to Speaker Verification & Voice Biometrics

Guide to Speaker Verification & Voice Biometrics Guide to Speaker Verification & Voice Biometrics ICR Speech Solutions & Services The Engine House Ashley Lane, Saltaire West Yorkshire BD17 7DB Tel: 01274 821111 e-mail: info@icr3s.co.uk www.icr3s.co.uk

More information

Voice Biometric Integration

Voice Biometric Integration Voice Biometric Integration Product Requirements Document, Version 2 November 28, 2016 Team Tres Commas Members: Jonathan Easterman, Sasha Shams, Arda Ungun, Carson Holoien, Vince Nicoara Mentors: Mike

More information

CHAPTER 6 RESULTS AND DISCUSSIONS

CHAPTER 6 RESULTS AND DISCUSSIONS 151 CHAPTER 6 RESULTS AND DISCUSSIONS In this chapter the performance of the personal identification system on the PolyU database is presented. The database for both Palmprint and Finger Knuckle Print

More information

VocalPassword : voice biometrics authentication.

VocalPassword : voice biometrics authentication. VocalPassword : authentication. Friendly voice authentication across web, IVR, call center, or mobile. 1 VocalPassword for easy and secure authentication. VocalPassword, the world s most widely deployed

More information

ViGo Architecture and Principles. Mobile Voice Biometrics as-a-service

ViGo Architecture and Principles. Mobile Voice Biometrics as-a-service ViGo Architecture and Principles Mobile Voice Biometrics as-a-service Part number: VV/VIGO/DOC/183/C Copyright 2015 VoiceVault Inc. All rights reserved. This document may not be copied, reproduced, transmitted

More information

Technical White Paper. Behaviometrics. Measuring FAR/FRR/EER in Continuous Authentication

Technical White Paper. Behaviometrics. Measuring FAR/FRR/EER in Continuous Authentication Technical White Paper Behaviometrics Measuring FAR/FRR/EER in Continuous Authentication Draft version 12/22/2009 Table of Contents Background... 1 Calculating FAR/FRR/EER in the field of Biometrics...

More information

Biometric Authentication. Bringing End users and Enterprise on the same page

Biometric Authentication. Bringing End users and Enterprise on the same page Biometric Authentication Bringing End users and Enterprise on the same page 1 ABOUT SPEECHPRO SpeechPro is a World Leader in Speech Technology with customers in 75 countries SpeechPro is part of the global

More information

The Expected Performance Curve: a New Assessment Measure for Person Authentication

The Expected Performance Curve: a New Assessment Measure for Person Authentication The Expected Performance Curve: a New Assessment Measure for Person Authentication Samy Bengio Johnny Mariéthoz IDIAP CP 592, rue du Simplon4 192 Martigny, Switzerland {bengio,marietho}@idiap.ch Abstract

More information

Biometric identity verification for large-scale high-security apps. Face Verification SDK

Biometric identity verification for large-scale high-security apps. Face Verification SDK Biometric identity verification for large-scale high-security apps Face Verification SDK Face Verification SDK Biometric identity verification for large-scale high-security applications Document updated

More information

Voice, Face and Behavioural Biometrics

Voice, Face and Behavioural Biometrics Voice, Face and Behavioural Biometrics Authentication & Fraud Prevention in the age of Virtual Assistants Brett Beranek, Director Product Strategy, Biometrics, Security & Fraud 2016 Nuance Communications,

More information

The Expected Performance Curve: a New Assessment Measure for Person Authentication

The Expected Performance Curve: a New Assessment Measure for Person Authentication R E S E A R C H R E P O R T I D I A P The Expected Performance Curve: a New Assessment Measure for Person Authentication Samy Bengio 1 Johnny Mariéthoz 2 IDIAP RR 03-84 March 10, 2004 submitted for publication

More information

Biometric Security Roles & Resources

Biometric Security Roles & Resources Biometric Security Roles & Resources Part 1 Biometric Systems Skip Linehan Biometrics Systems Architect, Raytheon Intelligence and Information Systems Outline Biometrics Overview Biometric Architectures

More information

Client Dependent GMM-SVM Models for Speaker Verification

Client Dependent GMM-SVM Models for Speaker Verification Client Dependent GMM-SVM Models for Speaker Verification Quan Le, Samy Bengio IDIAP, P.O. Box 592, CH-1920 Martigny, Switzerland {quan,bengio}@idiap.ch Abstract. Generative Gaussian Mixture Models (GMMs)

More information

Voice and Speech Recognition

Voice and Speech Recognition Voice and Speech Recognition Consumer, Call Center, Healthcare, Enterprise, Finance, Retail, Government, Law Enforcement, and Defense Applications: Market Analysis and Forecasts Speech and voice recognition,

More information

Exploring Similarity Measures for Biometric Databases

Exploring Similarity Measures for Biometric Databases Exploring Similarity Measures for Biometric Databases Praveer Mansukhani, Venu Govindaraju Center for Unified Biometrics and Sensors (CUBS) University at Buffalo {pdm5, govind}@buffalo.edu Abstract. Currently

More information

Confidence Measures: how much we can trust our speech recognizers

Confidence Measures: how much we can trust our speech recognizers Confidence Measures: how much we can trust our speech recognizers Prof. Hui Jiang Department of Computer Science York University, Toronto, Ontario, Canada Email: hj@cs.yorku.ca Outline Speech recognition

More information

VOICE BIOMETRICS. estilo de subtítulo del patrón Solutions

VOICE BIOMETRICS. estilo de subtítulo del patrón Solutions VOICE BIOMETRICS Haga clic Vicorp para modificar Speech el Biometric estilo de subtítulo del patrón Solutions VICORP SPEECH TECHNOLOGY UK based since 1989 with international partners - Specialising in

More information

Authors Martin Eckert Ingmar Kliche Deutsche Telekom Laboratories.

Authors Martin Eckert Ingmar Kliche Deutsche Telekom Laboratories. Workshop on speaker biometrics and VoiceXML 3.0 March 5-6, 2009, Menlo Park, CA, US Proposal of an SIV architecture and requirements Authors Martin Eckert (martin.eckert@telekom.de), Ingmar Kliche (ingmar.kliche@telekom.de),

More information

STMicroelectronics 2016 STM32 summit Voice Control, Speech recognition and Speaker verification on STM32 by Sensory

STMicroelectronics 2016 STM32 summit Voice Control, Speech recognition and Speaker verification on STM32 by Sensory STMicroelectronics 2016 STM32 summit Voice Control, Speech recognition and Speaker verification on STM32 by Sensory Simon Jeong, Director of Asia sales Agenda Sensory snapshot Sensory Technology line TrulyHandsfree

More information

Use of Extreme Value Statistics in Modeling Biometric Systems

Use of Extreme Value Statistics in Modeling Biometric Systems Use of Extreme Value Statistics in Modeling Biometric Systems Similarity Scores Two types of matching: Genuine sample Imposter sample Matching scores Enrolled sample 0.95 0.32 Probability Density Decision

More information

An Overview of Biometric Image Processing

An Overview of Biometric Image Processing An Overview of Biometric Image Processing CHAPTER 2 AN OVERVIEW OF BIOMETRIC IMAGE PROCESSING The recognition of persons on the basis of biometric features is an emerging phenomenon in our society. Traditional

More information

Manual operations of the voice identification program GritTec's Speaker-ID: The Mobile Client

Manual operations of the voice identification program GritTec's Speaker-ID: The Mobile Client Manual operations of the voice identification program GritTec's Speaker-ID: The Mobile Client Version 4.00 2017 Title Short name of product Version 4.00 Manual operations of GritTec s Speaker-ID: The Mobile

More information

Applying biometric authentication to physical access control systems

Applying biometric authentication to physical access control systems Applying biometric authentication to physical access control systems Published on 24 Jul 2018 Over the past few years, biometrics has rapidly expanded into consumer applications, like the financial market

More information

Mobile Fingerprint Authentication Solution

Mobile Fingerprint Authentication Solution Mobile Fingerprint Authentication Solution 1 BioSign 2.0 I WHY BioSign 2.0? WORLD S FASTEST SPEED WORLD S MOST ACCURATE ALGORITHM ROBUST PERFORMANCE OVER TIME FLEXIBILITY IN DESIGN 50ms* authentication

More information

Solution. Imagine... a New World of Authentication.

Solution. Imagine... a New World of Authentication. A Solution Imagine... a New World of Authentication. Imagine a World Where Passwords can t be hacked People can t share credentials Users can t pretend to be someone else Where authentication is more Secure

More information

Syntel2 by Syntel Solutions Features

Syntel2 by Syntel Solutions Features Syntel2 by Syntel Solutions Features Interested in learning how our proven software platform can revitalize your business communications? With Syntel2 by Syntel Solutions, we give you the tools and features

More information

The Future of Authentication

The Future of Authentication The Future of Authentication Table of Contents Introduction Facial Recognition Liveness Detection and Multimodal Biometrics FIDO: Standards-Based, Password-Free Authentication Biometric Authentication

More information

RSA SecurID Ready Implementation Guide

RSA SecurID Ready Implementation Guide RSA SecurID Ready Implementation Guide Last Modified: August 26, 2011 Partner Information Product Information Partner Name Web Site Product Name Version & Platform Product Description Voice Innovate http://voiceinnovate.com/

More information

Information Security Identification and authentication. Advanced User Authentication II

Information Security Identification and authentication. Advanced User Authentication II Information Security Identification and authentication Advanced User Authentication II 2016-01-29 Amund Hunstad Guest Lecturer, amund@foi.se Agenda for lecture I within this part of the course Background

More information

Voice activated spell-check

Voice activated spell-check Technical Disclosure Commons Defensive Publications Series November 15, 2017 Voice activated spell-check Pedro Gonnet Victor Carbune Follow this and additional works at: http://www.tdcommons.org/dpubs_series

More information

World s Best Mobile Fingerprint Authentication Algorithm

World s Best Mobile Fingerprint Authentication Algorithm World s Best Mobile Fingerprint Authentication Algorithm Mobile Fingerprint Authentication Algorithm l 1 I WHY? I Performance The world s fastest, most accurate mobile fingerprint technology ever provides

More information

Biometric Technology

Biometric Technology Biometric Technology Contents Biometric Technology M2SYS is a leading global provider of biometric technology and software solutions with 16 years of real-world experience. Our experience enables us to

More information

Integrated Access Management Solutions. Access Televentures

Integrated Access Management Solutions. Access Televentures Integrated Access Management Solutions Access Televentures Table of Contents OVERCOMING THE AUTHENTICATION CHALLENGE... 2 1 EXECUTIVE SUMMARY... 2 2 Challenges to Providing Users Secure Access... 2 2.1

More information

(P6) "Everyone will benefit from that," cofounder and CEO Alex Lebrun says.

(P6) Everyone will benefit from that, cofounder and CEO Alex Lebrun says. [Technology ]Voice Control: Coming Soon to a House Near You (P1) It's not unusual to find yourself talking to an uncooperative appliance or gadget. Soon, though, it could be more common for those devices

More information

Alexa, what did I do last summer?

Alexa, what did I do last summer? , what did I do last summer? Vladimir Katalov, ElcomSoft SecTor 2018 ElcomSoft Ltd. www.elcomsoft.com 1 Who s Alexa? Amazon Alexa is a virtual assistant developed by Amazon She s 4 years young First appeared

More information

INTERNATIONAL TELECOMMUNICATION UNION

INTERNATIONAL TELECOMMUNICATION UNION INTERNATIONAL TELECOMMUNICATION UNION ITU-T TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU P.862.1 (11/2003) SERIES P: TELEPHONE TRANSMISSION QUALITY, TELEPHONE INSTALLATIONS, LOCAL LINE NETWORKS Methods

More information

INTERPRETING FINGERPRINT AUTHENTICATION PERFORMANCE TECHNICAL WHITE PAPER

INTERPRETING FINGERPRINT AUTHENTICATION PERFORMANCE TECHNICAL WHITE PAPER INTERPRETING FINGERPRINT AUTHENTICATION PERFORMANCE TECHNICAL WHITE PAPER Fidelica Microsystems, Inc. 423 Dixon Landing Rd. Milpitas, CA 95035 1 INTRODUCTION The fingerprint-imaging segment of the biometrics

More information

Module Feature List

Module Feature List Key Differentiators Seamless Integration Informed and empowered interactions in every channel and every touch point - inbound and outbound calls, Email, Web chat, Social Media and SMS all from the same

More information

Cisco WebEx Cloud Connected Audio

Cisco WebEx Cloud Connected Audio Cisco WebEx Connected Audio What if you could provide employees, partners, and vendors with a better, more consistent web conferencing experience that actually helped reduce costs? Our integrated audio

More information

Adaptive Authentication Adapter for Citrix XenApp. Adaptive Authentication in Citrix XenApp Environments. Solution Brief

Adaptive Authentication Adapter for Citrix XenApp. Adaptive Authentication in Citrix XenApp Environments. Solution Brief Adaptive Authentication Adapter for Citrix XenApp Adaptive Authentication in Citrix XenApp Environments Solution Brief RSA Adaptive Authentication is a comprehensive authentication platform providing costeffective

More information

No compromise Collaboration Solution. Razvan Atimariti Collaboration PSS

No compromise Collaboration Solution. Razvan Atimariti Collaboration PSS No compromise Collaboration Solution Razvan Atimariti Collaboration PSS why Collaboration? why Now? why Cisco? What Does It Mean to Be an Agile Organization? Promote open flow of information Encourage

More information

Signature Verification Why xyzmo offers the leading solution

Signature Verification Why xyzmo offers the leading solution Dynamic (Biometric) Signature Verification The signature is the last remnant of the hand-written document in a digital world, and is considered an acceptable and trustworthy means of authenticating all

More information

ViGo Developer Guide. Mobile application development with ViGo

ViGo Developer Guide. Mobile application development with ViGo ViGo Developer Guide Mobile application development with ViGo Title: ViGo Developer Guide Part number: VV/VIGO/DOC/189/B Copyright 2015 VoiceVault Inc. All rights reserved. This document may not be copied,

More information

Virtual PBX Product Guide MODEL: SP-250 SP-500 SP-1000 SP-1500 SP-3000

Virtual PBX Product Guide MODEL: SP-250 SP-500 SP-1000 SP-1500 SP-3000 Virtual PBX Product Guide MODEL: SP-250 SP-500 SP-1000 SP-1500 SP-3000 Welcome to SimplifiCloud EXPAND, IMPROVE & REDUCE COSTS OF YOUR TELEPHONE SYSTEM SimplifiCloud presents unified communication systems

More information

Hitachi ID Password Manager Telephony Integration

Hitachi ID Password Manager Telephony Integration Hitachi ID Password Manager Telephony Integration 2016 Hitachi ID Systems, Inc. All rights reserved. Contents 1 Introduction 1 2 Functional integration 2 2.1 Self-service password reset....................................

More information

How to choose a Voice Biometrics Engine

How to choose a Voice Biometrics Engine Emilio Mar*nez emar%nez@agni%o- corp.com How to choose a Voice Biometrics Engine Voice Biometrics Engines Authen*ca*on solu*on vs. Voice Biometrics Engine 2 Selec2ng a VB Engine Voice Biometrics End Users

More information

Adaptive Authentication Adapter for Juniper SSL VPNs. Adaptive Authentication in Juniper SSL VPN Environments. Solution Brief

Adaptive Authentication Adapter for Juniper SSL VPNs. Adaptive Authentication in Juniper SSL VPN Environments. Solution Brief Adaptive Authentication Adapter for Juniper SSL VPNs Adaptive Authentication in Juniper SSL VPN Environments Solution Brief RSA Adaptive Authentication is a comprehensive authentication platform providing

More information

Behavior-based Authentication Systems. Multimedia Security

Behavior-based Authentication Systems. Multimedia Security Behavior-based Authentication Systems Multimedia Security Part 1: User Authentication Through Typing Biometrics Features Part 2: User Re-Authentication via Mouse Movements 2 User Authentication Through

More information

VoiceKey.IVR. A Reliable and Cost-Effective Solution for Voice Verification using IVR. Prophecy Integration Overview

VoiceKey.IVR. A Reliable and Cost-Effective Solution for Voice Verification using IVR. Prophecy Integration Overview VoiceKey.IVR A Reliable and Cost-Effective Solution for Voice Verification using IVR Prophecy Integration Overview USA, 369 Lexington Ave, Suite 316, New York, 10017 Phone: +1 (646) 237-7895 Web: http://speechpro-usa.com

More information

Outbound Dialing Enterprise Functionality

Outbound Dialing Enterprise Functionality Outbound Dialing Enterprise Functionality Increase Agent Productivity and Utilization Reduce Training Time Increase Contact Rates Maximum Performance from Each List Easily Transfer Calls to Affiliates

More information

Business Phones. Powerful GigE and cordless phones to power your business. Grandstream DECT Cordless Phones. Polycom VV X GigE Phones

Business Phones. Powerful GigE and cordless phones to power your business. Grandstream DECT Cordless Phones. Polycom VV X GigE Phones Business Phones Powerful GigE and cordless phones to power your business With all the advancements in technology, why do we settle for the same old experience when it comes to one of our most valuable

More information

User Authentication Best Practices for E-Signatures Wednesday February 25, 2015

User Authentication Best Practices for E-Signatures Wednesday February 25, 2015 User Authentication Best Practices for E-Signatures Wednesday February 25, 2015 Agenda E-Signature Overview Legality, Authentication & Best Practices Role of authentication in e-signing Options and applications

More information

Presenter: Ravikumar Balakrishna & Santosh Subramanya April 26, 2018

Presenter: Ravikumar Balakrishna & Santosh Subramanya April 26, 2018 Unified Voice Interface Platform Presenter: Ravikumar Balakrishna & Santosh Subramanya April 26, 2018 CONNECTED Devices Possibility to connect Built-in HMIs Interface Millions of Connected Devices USER

More information

Multifactor Fusion for Audio-Visual Speaker Recognition

Multifactor Fusion for Audio-Visual Speaker Recognition Proceedings of the 7th WSEAS International Conference on Signal, Speech and Image Processing, Beijing, China, September 15-17, 2007 70 Multifactor Fusion for Audio-Visual Speaker Recognition GIRIJA CHETTY

More information

Voiceprint-based Access Control for Wireless Insulin Pump Systems

Voiceprint-based Access Control for Wireless Insulin Pump Systems Voiceprint-based Access Control for Wireless Insulin Pump Systems Presenter: Xiaojiang Du Bin Hao, Xiali Hei, Yazhou Tu, Xiaojiang Du, and Jie Wu School of Computing and Informatics, University of Louisiana

More information

Improving Personal Identification Accuracy Using Multisensor Fusion for Building Access Control Applications

Improving Personal Identification Accuracy Using Multisensor Fusion for Building Access Control Applications Improving Personal Identification Accuracy Using Multisensor Fusion for Building Access Control Applications Lisa Osadciw, Pramod Varshney, and Kalyan Veeramachaneni laosadci,varshney,kveerama@syr.edu

More information

Tutorial 1. Jun Xu, Teaching Asistant January 26, COMP4134 Biometrics Authentication

Tutorial 1. Jun Xu, Teaching Asistant January 26, COMP4134 Biometrics Authentication Tutorial 1 Jun Xu, Teaching Asistant csjunxu@comp.polyu.edu.hk COMP4134 Biometrics Authentication January 26, 2017 Table of Contents Problems Problem 1: Answer the following questions Problem 2: Biometric

More information

Keystroke Dynamics: Low Impact Biometric Verification

Keystroke Dynamics: Low Impact Biometric Verification Keystroke Dynamics: Low Impact Biometric Verification Tom Olzak September 2006 Biometrics has long been one of the solutions touted by security vendors to meet multifactor authentication objectives. However,

More information

BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition

BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition Hiren D. Joshi Phd, Dept. of Computer Science Rollwala Computer Centre

More information

SHORETEL CONNECT. Eugenia Corrales Senior Vice President of Product. ShoreTel, Inc All rights reserved worldwide. 1

SHORETEL CONNECT. Eugenia Corrales Senior Vice President of Product. ShoreTel, Inc All rights reserved worldwide. 1 SHORETEL CONNECT Eugenia Corrales Senior Vice President of Product ShoreTel, Inc. 2015. All rights reserved worldwide. 1 THE SHORETEL DIFFERENCE End-to-end customer experience Application to end point

More information

2017 Partner of the Year Winner Serbia THE MOST-COST EFFECTIVE WAY TO UPGRADE YOUR PBX SYSTEM. with Office 365 and Skype for Business

2017 Partner of the Year Winner Serbia THE MOST-COST EFFECTIVE WAY TO UPGRADE YOUR PBX SYSTEM. with Office 365 and Skype for Business 2017 Partner of the Year Winner Serbia THE MOST-COST EFFECTIVE WAY TO UPGRADE YOUR PBX SYSTEM with Office 365 and Skype for Business SAY HELLO TO A BRAND NEW COMMUNICATION SYSTEM Is it time to upgrade

More information

Voice Biometrics in Financial Services. Prepared by Clinton Alver. vecommerce.com. Commercial in Confidence Page 1 of 15

Voice Biometrics in Financial Services. Prepared by Clinton Alver. vecommerce.com. Commercial in Confidence Page 1 of 15 Voice Biometrics in Financial Services Prepared by Clinton Alver Commercial in Confidence Page 1 of 15 vecommerce.com experience security efficiency Table of Contents 1. Introduction 4 2. History and Background

More information

Face ID Security. November 2017

Face ID Security. November 2017 Face ID Security November 2017 Face ID Security Overview With a simple glance, Face ID securely unlocks iphone X. It provides intuitive and secure authentication enabled by the TrueDepth camera system,

More information

Speaker Verification in BeVocal VoiceXML

Speaker Verification in BeVocal VoiceXML Speaker Verification in BeVocal VoiceXML Version 1.5 May 2001 BeVocal, Inc. 1380 Bordeaux Drive Sunnyvale, CA 94089 2001. BeVocal, Inc. All rights reserved. 2 SPEAKER VERIFICATION IN BEVOCAL VOICEXML Table

More information

Fusion Architecture. Planning for an on-premise deployment

Fusion Architecture. Planning for an on-premise deployment Planning for an on-premise deployment Fusion Architecture Part number: VV/GUIDE/CUST/62/D Copyright 2017 VoiceVault Inc. All rights reserved. This document may not be copied, reproduced, transmitted or

More information

NeoFace Watch real-time face recognition How does it work? May 2018 Global Face Recognition Centre of Excellence NEC Europe

NeoFace Watch real-time face recognition How does it work? May 2018 Global Face Recognition Centre of Excellence NEC Europe NeoFace Watch real-time face recognition How does it work? May 2018 Global Face Recognition Centre of Excellence NEC Europe Executive Summary There is much misunderstanding about the operation of real-time

More information

Introduction to the Extended Development Platform

Introduction to the Extended Development Platform Hong Kong 2018 Introduction to the Extended Development Platform Richard Schaefer, Sr. Enterprise Solution Manager BlackBerry Development Platform A collection of enterprise ready tools which enable enterprise

More information

A Plan For Robocalls: Robosmelter

A Plan For Robocalls: Robosmelter A Plan For Robocalls: Robosmelter Ben Klang, Sene Sorrow Mojo Lingo LLC January 17, 2013 Submitted to the Federal Trade Commission s Robocall Challenge Abstract The rise of Voice over IP (VoIP) technologies

More information

BlackBerry Enterprise Identity

BlackBerry Enterprise Identity Datasheet BlackBerry Enterprise Identity The Challenge: Cloud services are critical in today s enterprises, yet a reliance on the cloud comes with real and growing security risks. Enterprises want a simple,

More information

Business Phones. Powerful GigE and cordless phones to power your business. Grandstream DECT Cordless Phones. Polycom VV X GigE Phones

Business Phones. Powerful GigE and cordless phones to power your business. Grandstream DECT Cordless Phones. Polycom VV X GigE Phones Business Phones Powerful GigE and cordless phones to power your business With all the advancements in technology, why do we settle for the same old experience when it comes to one of our most valuable

More information

Online Signature Verification Technique

Online Signature Verification Technique Volume 3, Issue 1 ISSN: 2320-5288 International Journal of Engineering Technology & Management Research Journal homepage: www.ijetmr.org Online Signature Verification Technique Ankit Soni M Tech Student,

More information

Beyond Blind Defense: Gaining Insights from Proactive App Sec

Beyond Blind Defense: Gaining Insights from Proactive App Sec Beyond Blind Defense: Gaining Insights from Proactive App Sec Speaker Rami Essaid CEO Distil Networks Blind Defense Means Trusting Half Your Web Traffic 46% of Web Traffic is Bots Source: Distil Networks

More information

ResponseTek Listening Platform Release Notes Q4 16

ResponseTek Listening Platform Release Notes Q4 16 ResponseTek Listening Platform Release Notes Q4 16 Nov 23 rd, 2016 Table of Contents Release Highlights...3 Predictive Analytics Now Available...3 Text Analytics Now Supports Phrase-based Analysis...3

More information

MultiDSLA. Measuring Network Performance. Malden Electronics Ltd

MultiDSLA. Measuring Network Performance. Malden Electronics Ltd MultiDSLA Measuring Network Performance Malden Electronics Ltd The Business Case for Network Performance Measurement MultiDSLA is a highly scalable solution for the measurement of network speech transmission

More information

SAMSUNG 6000 SERIES HANDSET BROCHURE PLATINUM SERVICE PROVIDER

SAMSUNG 6000 SERIES HANDSET BROCHURE PLATINUM SERVICE PROVIDER PLATINUM SERVICE PROVIDER HANDSET BROCHURE SAMSUNG 6000 SERIES THE NEW SMT-I6000 RANGE OF DESKPHONES FROM SAMSUNG CHANGE THE RULES IN IP PHONE DEPLOYMENT AND THE USER S EXPERIENCE. WIRED OR WIRELESS THE

More information

THE FREEDOM TO GROW KX-NS700 UNIFIED COMMUNICATIONS PLATFORM

THE FREEDOM TO GROW KX-NS700 UNIFIED COMMUNICATIONS PLATFORM THE FREEDOM TO GROW KX-NS700 UNIFIED COMMUNICATIONS PLATFORM Choose the smart hybrid PBX system that can grow the way you want Looking to reduce your operational and capital costs through high-quality,

More information

Watermark-Based Authentication and Key Exchange in Teleconferencing Systems

Watermark-Based Authentication and Key Exchange in Teleconferencing Systems Watermark-Based Authentication and Key Exchange in Teleconferencing Systems Ulrich Rührmair a, Stefan Katzenbeisser b, Martin Steinebach c, and Sascha Zmudzinski c a Technische Universität München, Department

More information

InformationTechnology

InformationTechnology dvanced Calling Features The Polycom VVX 501 is the supported handset for the University's digital voice-over-ip telephone service. The VVX 501 integrates with the University's Skype for Business unified

More information

Questions & Answers. Sangoma Webinar: Building Your Contact Center with FreePBX / PBXact UC. November 2, 2016

Questions & Answers. Sangoma Webinar: Building Your Contact Center with FreePBX / PBXact UC. November 2, 2016 Questions & Answers Sangoma Webinar: Building Your Contact Center with FreePBX / PBXact UC November 2, 2016 Q: Can we integrate your systems to ours (e.g. CRM) via API? A: We do not provide a CTI link

More information

Multimodal Fusion Vulnerability to Non-Zero Effort (Spoof) Imposters

Multimodal Fusion Vulnerability to Non-Zero Effort (Spoof) Imposters Multimodal Fusion Vulnerability to Non-Zero Effort (Spoof) mposters P. A. Johnson, B. Tan, S. Schuckers 3 ECE Department, Clarkson University Potsdam, NY 3699, USA johnsopa@clarkson.edu tanb@clarkson.edu

More information

Microsoft speech offering

Microsoft speech offering Microsoft speech offering Win 10 Speech APIs Local Commands with constrained grammar E.g. Turn on, turn off Cloud dictation Typing a message, Web search, complex phrases Azure marketplace Oxford APIs LUIS

More information

VClarity Voice Platform

VClarity Voice Platform VClarity Voice Platform VClarity L.L.C. Voice Platform Snap-in Functional Overview White Paper Technical Pre-release Version 2.0 for VClarity Voice Platform Updated February 12, 2007 Table of Contents

More information

The 2013 Digital Dilemma Report: Mobility, Security, Productivity Can We Have It All?

The 2013 Digital Dilemma Report: Mobility, Security, Productivity Can We Have It All? The 2013 Digital Dilemma Report: Mobility, Security, Productivity Can We Have It All? January 15, 2013 Sponsored by: www.mobileworkexchange.com 1 Introduction The Digital Government Strategy calls for

More information

Fingerprint Authentication for SIS-based Healthcare Systems

Fingerprint Authentication for SIS-based Healthcare Systems Fingerprint Authentication for SIS-based Healthcare Systems Project Report Introduction In many applications there is need for access control on certain sensitive data. This is especially true when it

More information

Multi-Factor Authentication FAQs

Multi-Factor Authentication FAQs General FAQs What is Multi-factor Authentication (MFA)? Multi-factor authentication (MFA) seeks to decrease the likelihood that others can access your data. Specifically, it enhances the security of your

More information

Speakler recognition for stand-alone or Web applications. VeriSpeak SDK

Speakler recognition for stand-alone or Web applications. VeriSpeak SDK Speakler recognition for stand-alone or Web applications VeriSpeak SDK VeriSpeak SDK Speaker recognition for stand-alone or Web applications Document updated on September 28, 2017 CONTENTS VeriSpeak algorithm

More information

User Guide Advanced Authentication - Smartphone Applications. Version 5.6

User Guide Advanced Authentication - Smartphone Applications. Version 5.6 User Guide Advanced Authentication - Smartphone Applications Version 5.6 Legal Notices For information about legal notices, trademarks, disclaimers, warranties, export and other use restrictions, U.S.

More information

WebEx Audio. Features

WebEx Audio. Features WebEx Integrated Audio provides a high-performance, feature-rich, telephony-based audio conference service. This service can be used in a stand-alone mode or fully integrated within a WebEx meeting. s,

More information

Dragon TV Overview. TIF Workshop 24. Sept Reimund Schmald mob:

Dragon TV Overview. TIF Workshop 24. Sept Reimund Schmald mob: Dragon TV Overview TIF Workshop 24. Sept. 2013 Reimund Schmald reimund.schmald@nuance.com mob: +49 171 5591906 2002-2013 Nuance Communications, Inc. All rights reserved. Page 1 Reinventing the relationship

More information

Wireless Clients and Users Monitoring Overview

Wireless Clients and Users Monitoring Overview Wireless Clients and Users Monitoring Overview Cisco Prime Infrastructure 3.1 Job Aid Copyright Page THE SPECIFICATIONS AND INFORMATION REGARDING THE PRODUCTS IN THIS MANUAL ARE SUBJECT TO CHANGE WITHOUT

More information

Smart Mobile Identity. Revolutionizing biometric identity verification

Smart Mobile Identity. Revolutionizing biometric identity verification Smart Mobile Identity Revolutionizing biometric identity verification Introduction Mobile devices are poised to transform the biometric industry and greatly broaden the use of biometrics for identity verification.

More information

PRODUCT BROCHURE. Polycom RealPresence Group Series

PRODUCT BROCHURE. Polycom RealPresence Group Series PRODUCT BROCHURE Polycom Group Series Polycom Group Series Effective group collaboration has never been more important in business communication. Geographically dispersed teams need to get more done with

More information

BT CLOUD PHONE. USER GUIDE FOR MY EXTENSION.

BT CLOUD PHONE. USER GUIDE FOR MY EXTENSION. BT CLOUD PHONE. USER GUIDE FOR MY EXTENSION. WHAT S IN THIS GUIDE. 1. Welcome to BT Cloud Phone. 3 2. Express setup. 4 3. Accessing the BT Cloud Phone Portal. 5 4. My Extension Dashboard. 6 4.1 Overview:

More information

OpenScape Business. Introduction and New release V2R3. Unify Dev Lab UCC Greece Vas Giatilis

OpenScape Business. Introduction and New release V2R3. Unify Dev Lab UCC Greece Vas Giatilis OpenScape Business Introduction and New release V2R3 Unify Dev Lab Athens @ UCC Greece Development Site Unify s largest development site is in Athens Greece 300 software engineers More than 10 years of

More information

The US Contact Center Decision-Makers Guide Contact Center Performance. sponsored by

The US Contact Center Decision-Makers Guide Contact Center Performance. sponsored by The US Contact Center Decision-Makers Guide 2013 Contact Center Performance sponsored by INTRODUCTION AND METHODOLOGY The "US Contact Center Decision-Makers' Guide (2013-6 th edition)" is the major annual

More information

The paper shows how to realize write-once-run-anywhere for such apps, and what are important lessons learned from our experience.

The paper shows how to realize write-once-run-anywhere for such apps, and what are important lessons learned from our experience. Paper title: Developing WebRTC-based team apps with a cross-platform mobile framework. Speaker: John Buford. Track: Mobile and Wearable Devices, Services, and Applications. Hello everyone. My name is John

More information

ios Collaboration Mobile App Guide - English

ios Collaboration Mobile App Guide - English Mar 19, 2019 00:09 ios Collaboration Mobile App Guide - English Wildix Collaboration Mobile application provides access to Wildix Unified Communications from your iphone, ipod touch and ipad. ios Version:

More information

1 Hitachi ID Password Manager

1 Hitachi ID Password Manager 1 Hitachi ID Password Manager Managing the User Lifecycle Across On-Premises and Cloud-Hosted Applications Integrated credential management: Passwords, security questions, certificates, tokens, smart cards

More information

Authentication Work stream FIGI Security Infrastructure and Trust Working Group. Abbie Barbir, Chair

Authentication Work stream FIGI Security Infrastructure and Trust Working Group. Abbie Barbir, Chair Authentication Work stream FIGI Security Infrastructure and Trust Working Group Abbie Barbir, Chair Security, Infrastructure, Trust Working Group To enhance confidence in using Digital Financial Services

More information