We present a study of separability of acoustic waveforms of speech at phoneme level. The analyzed data consist of 64 ms segments of acoustic waveforms of individual phonemes from TIMIT data base, sampled at 16 kHz. For each phoneme, by means of principal component analysis, we identify subspaces which contain a given proportion of the total energy of the available waveforms in the time-domain, and also in the spectral-magnitude domain. In order to assess the separation between phonemes in the two domains, we perform pairwise classification of phonemes on clean data and on data immersed in white additive Gaussian noise up to 0 dB signal to noise ratio. While the classification based on spectral magnitudes exhibits high sensitivity to additive noise, the time-domain classification proves to be very robust.