Robustness of phoneme classification in different representation spaces

The robustness of phoneme recognition using support vector machines to additive noise is investigated for three kinds of speech representation. The representations considered are PLP, PLP with RASTA processing, and a high-dimensional principal component approximation of acoustic waveforms. While the classification in the PLP and PLP/RASTA domains attains superb accuracy on clean data, the classification in the high-dimensional space proves to be much more robust to additive noise.