Advisor

Picone, Joseph

Committee Member

Boggess, Lois

Committee Member

Younan, Nicholas

Committee Member

Moorhead, Robert J.

Date of Degree

1-1-2002

Document Type

Dissertation - Open Access

Major

Computer Engineering

Degree Name

Doctor of Philosophy

College

College of Engineering

Department

Department of Electrical and Computer Engineering

Abstract

Hidden Markov models (HMM) with Gaussian mixture observation densities are the dominant approach in speech recognition. These systems typically use a representational model for acoustic modeling which can often be prone to overfitting and does not translate to improved discrimination. We propose a new paradigm centered on principles of structural risk minimization using a discriminative framework for speech recognition based on support vector machines (SVMs). SVMs have the ability to simultaneously optimize the representational and discriminative ability of the acoustic classifiers. We have developed the first SVM-based large vocabulary speech recognition system that improves performance over traditional HMM-based systems. This hybrid system achieves a state-of-the-art word error rate of 10.6% on a continuous alphadigit task ? a 10% improvement relative to an HMM system. On SWITCHBOARD, a large vocabulary task, the system improves performance over a traditional HMM system from 41.6% word error rate to 40.6%. This dissertation discusses several practical issues that arise when SVMs are incorporated into the hybrid system.

URI

https://hdl.handle.net/11668/16383

Comments

classification||kernel methods||acoustic modeling

Share

COinS