Discriminative And Generative Machine Learning Approaches Towards Robust Phoneme Classification

Jibran Yousafzai*, Matthew Ager, Zoran Cvetkovic, Peter Sollich

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paper

6 Citations (Scopus)

Abstract

Robustness of classification of isolated phoneme segments using discriminative and generative classifiers is investigated for the acoustic waveform and PLP speech representations. The two approaches used are support vector machines (SVMs) and mixtures of probabilistic PCA (MPPCA). While recognition in the PLP domain attains superb accuracy on clean data, it is significantly affected by mismatch between training and test noise levels. Classification in the high-dimensional acoustic waveform domain, on the other hand, is more robust in the presence of additive white Gaussian noise. We also show some results on the effects of custom-designed kernel functions for SVM classification in the acoustic waveform domain.

Original languageEnglish
Title of host publicationInformation Theory and Applications Workshop, 2008
Place of PublicationNew York
PublisherIEEE
Pages533-537
Number of pages5
VolumeN/A
EditionN/A
ISBN (Print)9781424426706
DOIs
Publication statusPublished - 2008
EventIEEE Information Theory and Applications Workshop - San Diego, Canada
Duration: 1 Jan 2008 → …

Conference

ConferenceIEEE Information Theory and Applications Workshop
Country/TerritoryCanada
Period1/01/2008 → …

Keywords

  • Speech Recognition
  • Robustness
  • Discriminative Classification
  • Generative Classification
  • PLP
  • SPEECH RECOGNITION

Fingerprint

Dive into the research topics of 'Discriminative And Generative Machine Learning Approaches Towards Robust Phoneme Classification'. Together they form a unique fingerprint.

Cite this