Singing characterization using temporal and spectral features in Indian musical notes

Pitch extraction from a multi pitched music signal significantly relies on the training data for tasks like enhanced music-voice separation. This paper aims at identifying characteristic temporal and spectral features, using speech processing techniques that can help obtain crucial information, leading to a better understanding of the music structure. Towards this goal, the F0 contour has been studied to capture the melodic trends in a Sargam progression, and the results have been compared with the output of state of the art package PRAAT. Effects of pre-emphasising in enhancing the tracking are also discussed. A method is proposed through which the transition trends in the note progression can be validated for correctness and the results are encouraging in characterising the progression. Spectral analysis is done to get some insight into the harmonic behaviour in conjunction with the signal energy pattern. This is followed by the LP Analysis that tells about the Swara Pronunciation. The results observed indicate usefulness of the standard techniques and the constraints posed towards the singing voice analysis.