ENEE408G Capstone Design Project: Multimedia Signal Processing Group 1 By : William “Chris” Paul Louis Lo Jang-Hyun Ko Ronald McLaren Final Project : V-LOCK.

Slides:



Advertisements
Similar presentations
Chapter 3: Software Basics Section I: Preparing to Use Technology.
Advertisements

Office of Labor-Management Standards (OLMS)
Masters Presentation at Griffith University Master of Computer and Information Engineering Magnus Nilsson
Improvement of Audio Capture in Handheld Devices through Digital Filtering Problem Microphones in handheld devices are of low quality to reduce cost. This.
Automatic Lip- Synchronization Using Linear Prediction of Speech Christopher Kohnert SK Semwal University of Colorado, Colorado Springs.
Copyright © 2006 Exportech Portugal. All rights reserved.
Fingerprint Authentication Kevin Amendt David Friend April 26, MIT Course Project Presentations.
02/25/2005ENEE408G Spring 2005 Multimedia Signal Processing 1 ENEE408G: Capstone Design Project: Multimedia Signal Processing Design Project 2: Video Processing.
05/06/2005ENEE408G Spring 2005 Multimedia Signal Processing 1 ENEE408G: Capstone Design Project: Multimedia Signal Processing Final Remarks.
Fig. 2 – Test results Personal Memory Assistant Facial Recognition System The facial identification system is divided into the following two components:
(Remote Access Security) AAA. 2 Authentication User named "flannery" dials into an access server that is configured with CHAP. The access server will.
03/04/2005ENEE408G Spring 2005 Multimedia Signal Processing 1 ENEE408G: Capstone Design Project: Multimedia Signal Processing Design Project 3: Digital.
Voice-enabled Image Identification System Design Aashish P. Shrestha Ming Ming Zheng Multimedia Signal Processing, University of Bridgeport, Connecticut.
Investigation of Two Licensed Biometric Products Using Neurotechnology’s VeriLook and VeriFinger software.
Design Team #3 Work Order Tool with Voice Recognition Hai Bui Harry Himawan Chris Phillips.
Technology Terminology Jeopardy A - DE - FG - MM - SS - Z $100 $200 $300 $400 $500.
Handwritten Thai Character Recognition Using Fourier Descriptors and Robust C-Prototype Olarik Surinta Supot Nitsuwat.
Auditory User Interfaces
Support for Palm Pilot Collaboration Including Handwriting Recognition.
Security-Authentication
ECE 533 Final Project SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION Josh Easton- Tin-Yau Lo.
Vision-Based Biometric Authentication System by Padraic o hIarnain Final Year Project Presentation.
Team Members: Mohammed Hoque Troy Tancraitor Jonathan Lobaugh Lee Stein Joseph Mallozi Pennsylvania State University.
1 “ Speech ” EMPOWERED COMPUTING Greenfield Business Centre, 20 th September, 2006.
What is Skype and how do you use it? Before we start, it is a REQUIREMENT of this lesson to have a valid address. If you don’t have one, please.
Operating Systems Operating System
Java-Based In-Car Cell Phone Integration By:Chris Keller Greg Nehus Matt Odille.
Supervisor: Dr. Eddie Jones Electronic Engineering Department Final Year Project 2008/09 Development of a Speaker Recognition/Verification System for Security.
Presented by Tienwei Tsai July, 2005
Visual Linker Final presentation.
Skype Presentation By: B. Hardman Image used from
Section 1: Introducing Group Policy What Is Group Policy? Group Policy Scenarios New Group Policy Features Introduced with Windows Server 2008 and Windows.
COMPARISON OF IMAGE ANALYSIS FOR THAI HANDWRITTEN CHARACTER RECOGNITION Olarik Surinta, chatklaw Jareanpon Department of Management Information System.
EZee iCafe System. Contents Introduction Current Scenario Proposed Solution Architecture / Block Diagram Hardware / Software Requirements Features Benefits.
Supervisor: Dr. Eddie Jones Co-supervisor: Dr Martin Glavin Electronic Engineering Department Final Year Project 2008/09 Development of a Speaker Recognition/Verification.
Professional Encryption Software FINECRYPT 8.1. Contents Introduction Introduction Features Features Installation Installation Tests Tests Results Results.
Voice Recognition (Presentation 2) By: Priya Devi A. S/W Developer, Xsys technologies Bangalore.
 Most current version 1.3  Will review some basic and advanced portions of the software  Only have 50 minutes including questions  Please write down.
NOISE DETECTION AND CLASSIFICATION IN SPEECH SIGNALS WITH BOOSTING Nobuyuki Miyake, Tetsuya Takiguchi and Yasuo Ariki Department of Computer and System.
ITGS Application Software, pt. 3. ITGS Business Software Alliance (BSA) and Federation Against Software Theft (FAST) –Represent software companies and.
Introduction to Dragon NaturallySpeaking Voice Recognition Software A Short Course for Faculty and Staff of Paradise Valley Community College, Phoenix,
Shock Force Software Team & The Intellectual Disabilities Agency of the New River Valley.
Designing a Voice Activated Compartmentalized Safe with Speech Processing using Matlab Preliminary Design Review Amy Anderson Ernest Bryant Mike Joyner.
How to Use GPS to Fill Out a Bid Document February 2007.
Using Voice to Solve Ergonomic Problems Dr. William Lenharth, CHFP UNH – Project54.
Designing a Voice Activated Compartmentalized Safe with Speech Processing using Matlab Final Presentation Amy Anderson Ernest Bryant Mike Joyner Collins.
INTRODUCTION TO BIOMATRICS ACCESS CONTROL SYSTEM Prepared by: Jagruti Shrimali Guided by : Prof. Chirag Patel.
By Diana Liwanag. Overview The problem What are biometrics? –What are the different types? Short video of a system with a fingerprinting device. Identifying.
1 UNIT 19 Data Security 2. Introduction 2 AGENDA Hardware and Software protect ion Network protect ion Some authentication technologies :smart card Storage.
Configuring and Deploying Web Applications Lesson 7.
Myrtle Entertainment System Scanner How to work your way to installing a program via Myrtle Entertainment System Scanner.
My topic is…………. - It is the fundamental building block and the primary lines of defense in computer security. - It is a basic for access control and.
PREPARED BY MANOJ TALUKDAR MSC 4 TH SEM ROLL-NO 05 GUKC-2012 IN THE GUIDENCE OF DR. SANJIB KR KALITA.
How to develop a VoIP softphone in C# that enables SIP Instant Messaging (IM) This presentation describes how to create a softphone in C# that allows you.
How to develop a VoIP softphone in C# by using OZEKI VoIP SIP SDK This presentation demonstrates the first steps concerning to how to develop a fully-functional.
SMART QUILL. INTRODUCTION Inventor:- Lyndsay William of Microsoft Research.  Inventor:- Lyndsay William of Microsoft Research.  It can remember the.
BIOMETRICS VOICE RECOGNITION. Meaning Bios : LifeMetron : Measure Bios : LifeMetron : Measure Biometrics are used to identify the input sample when compared.
Computer Software.
ARTIFICIAL NEURAL NETWORKS
Home Automation System
Module 1: Getting Started
Toll-Free: Article source-
Norton is a standout amongst the most well known world class antiviruses which is generally known for offering high class security administrations to their.
Presentation for EEL6586 Automatic Speech Processing
Isolated word, speaker independent speech recognition
Presentation Outlines
A maximum likelihood estimation and training on the fly approach
M. Kezunovic (P.I.) S. S. Luo D. Ristanovic Texas A&M University
Keyword Spotting Dynamic Time Warping
THE ASSISTIVE SYSTEM SHIFALI KUMAR BISHWO GURUNG JAMES CHOU
Presentation transcript:

ENEE408G Capstone Design Project: Multimedia Signal Processing Group 1 By : William “Chris” Paul Louis Lo Jang-Hyun Ko Ronald McLaren Final Project : V-LOCK Speaker Recognition System For the Pocket PC

Project Objective Accessibility to Pocket PC using a Voice Password. Prevents unauthorized users access to files. Easier than entering in a password by hand.

Project Specifications Recognition of voice with 70-90% accuracy Blocking unauthorized voice Create your own password for voice authentication Back up authentication in case voice authentication fails Must be User Friendly

Project Preparation Visual C++ Pocket PC Research Papers Internet Research

Project Development Initial Password Setup - Speaker must decide on password to use for access. - Speaker must say the word 3 times to get a good reference signature. - Reference Signature is then sent through Feature Extraction Algorithm to get reference data to match against.

Feature Extraction Algorithm - Find the Signal. - Separate the signal into 256 sample sections. - Perform FFT on the section. - Select 16 coefficients from each sample window. - Repeat for the rest of the signal.

Match Algorithm - Utilizes a distance formula to calculate the distance between known and unknown Fourier Coefficients. - Match Number= sqrt(sum(x-y)^2); where x is the coefficient of the known reference signal and y is the coefficient of the unknown signal. - A good is match is a distance less than 25

Problems During Development None of the group members have a strong software background. There is a lack of resources for finding information on how to interface different functions of the Pocket PC (majority of the information is about software packages available for purchase). Limited knowledge of speech processing along the lines of coding the speech ourselves.

Project Demonstration For instructions on how to use the program and downloading the program go to: VISUAL C++ POCKET PC

Future Upgrades Allow for multiple users to use the Pocket PC with different passwords. Perform more thorough processing to take noise into account to reduce errors and possibly speeding up processing time for the current algorithms. Incorporate Voice commands into the functionality of Pocket PC usage Ask for password every time the Pocket PC is restarted

Conclusion Voice and Speaker Recognition is Difficult! Voice verification only at 60% due to noise and other possible factors.