Significance of magnitude and phase information via VTEO for humming based biometrics

In this paper, recognition of persons is attempted from their hum. This kind of application can be useful to design humming-based biometrics system or person-dependent Query-by-Humming (QBH) system and hence play an important role in music information retrieval (MIR) system. This paper develops a new feature extraction technique to exploit phase spectrum information along with magnitude spectrum information from hum signal. In particular, structure of state-of-the-art feature set, viz., Mel Frequency Cepstral Coefficients (MFCC) is modified to capture the phase spectrum information. In addition, a new energy measure, viz., Variable length Teager Energy Operator (VTEO) is employed to compute subband energies of different time-domain subband signals (i.e., output of 24 triangular shaped filters used in Mel filterbank). Discriminatively-trained polynomial classifier of 2^nd order approximations are used as the basis for recognition experiment.