Development of machine learning based speaker recognition system

Pekcan, Onur

Permalink

https://hdl.handle.net/2142/16226 Copy

Description

Title

Development of machine learning based speaker recognition system

Author(s)

Pekcan, Onur

Issue Date

2010-05-19T18:41:11Z

Director of Research (if dissertation) or Advisor (if thesis)

Roth, Dan

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Speaker Recognition
• Speaker Verification
• Speaker Identification
• Biometrics
• Voice Activity Detection
• Machine Learning
• Support Vector Machine
• Artificial Neural Network
• Hardware
• Software

Abstract

In this thesis, we describe a biometric authentication system that is capable of recognizing its users’ voice using advanced machine learning and digital signal processing tools. The proposed system can both validate a person’s identity (i.e. verification) and recognize it from a larger known group of people (i.e. identification). We designed the entire speaker recognition system to be integrated into the Siebel Center’s infrastructure, and named it “Biometric Authentication System for the Siebel Center (BASS)”. The main idea is to extract discriminative characteristics of an individual’s voiceprint, and employ them to train classifiers using binary classification. We formed the training data set by recording 11 speakers’ voices in a laboratory environment. The majority of the speakers were from different nations, with different language backgrounds and therefore various accents. They were considered to be a subset of the Siebel Center community. We asked them to speak 13 words including numeric digits (0-9) and proper nouns, and used triplet combinations of these words as passwords. We chose Mel-Frequency Cepstral Coefficients to represent the voice signals for forming frame-based feature vectors. With these we trained Support Vector Machine and Artificial Neural Network classifiers using “One vs. all” strategy. We tested our recognition models with unseen voice records from different speakers and found them very successful based on different criteria such as equal error rate, precision and recall values. In the scope of this work, we also assembled the hardware through which the software, including the algorithm and developed models, could operate. The hardware consists of several parts such as an infrared sensor that is used to sense the presence of users, a PIC microcontroller to communicate with the software and an LCD screen to display the passwords, etc. Based on the decision obtained from the software, BASS is also capable of opening the office door, where it is built to function.

Graduation Semester

2010-5

Permalink

http://hdl.handle.net/2142/16226

Copyright and License Information

Copyright 2010 Onur Pekcan

Owning Collections