Phoneme classification using the Hartley phase spectrum

The phase of a signal conveys critical information for signal interpretation. However, signal phase extraction is not a straightforward process, mainly due to the discontinuities appearing in the phase spectrum. Previously, it was shown that for the application of audio classification, in case features of the processed phase spectrum are combined with magnitude related features they provide higher classification score compared to the case where features are extracted only from the signals’ magnitude content. Moreover, it was shown that the Hartley Phase Spectrum encapsulates the phase content of the signals more efficiently compared to its Fourier counterpart. In this work, the importance of phase and the properties of the Hartley Phase Spectrum are demonstrated for the application of phoneme classification.