Discriminative and generative machine learning approaches towards robust phoneme classification
Jibran Yousafzai, Matthew Ager, Zoran Cvetkovic and Peter Sollich
In: Information Theory and Applications 2008, 27 Jan - 1 Feb 2008, University of California San Diego.
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.