This paper examines the applicability of some learning techniques
to the classification of phonemes. The methods tested were artificial
neural nets (ANN), support vector machines (SVM) and Gaussian
mixture modeling. We compare these methods with a traditional
hidden Markov phoneme model (HMM) working with the linear prediction-based
cepstral coefficient features (LPCC). We also tried to combine
the learners with feature transformation methods, like linear
discriminant analysis (LDA), principal component analysis (PCA)
and independent component analysis (ICA). We found that the discriminative
learners can attain the efficiency of the HMM, and after LDA they
can attain practically the same score on only 27 features. PCA
and ICA proved ineffective, apparently because of the discrete
cosine transform inherent in LPCC.
