Applications of support vector machines to speech recognition

Author

Ganapathiraju, Aravind ; Hamaker, Jonathan E. ; Picone, Joseph

Author_Institution

Conversay, Redmond, WA, USA

Volume

52

Issue

8

fYear

2004

Firstpage

2348

Lastpage

2355

Abstract

Recent work in machine learning has focused on models, such as the support vector machine (SVM), that automatically control generalization and parameterization as part of the overall optimization process. In this paper, we show that SVMs provide a significant improvement in performance on a static pattern classification task based on the Deterding vowel data. We also describe an application of SVMs to large vocabulary speech recognition and demonstrate an improvement in error rate on a continuous alphadigit task (OGI Alphadigits) and a large vocabulary conversational speech task (Switchboard). Issues related to the development and optimization of an SVM/HMM hybrid system are discussed.

Keywords

hidden Markov models; learning (artificial intelligence); optimisation; pattern classification; speech recognition; support vector machines; alphadigit task; hidden Markov model; machine learning; optimization process; pattern classification; statistical modeling; support vector machines; vocabulary speech recognition; Hidden Markov models; Machine learning; Maximum likelihood estimation; Pattern recognition; Power system modeling; Robustness; Speech recognition; Support vector machine classification; Support vector machines; Vocabulary; Machine learning; speech recognition; statistical modeling; support vector machines;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/TSP.2004.831018

Filename

1315952