Melody similarity in music is a perception of listeners based on cognitive method. Thus, the algorithms should be based on perceptually oriented computational model. We have used computer generated synthesized tune of popular song and its variations to understand similarity notion. We have generated variations of a tune by changing musical scale or relative duration of notes or notes itself and combination of them. The proposed approach to calculate similarity relationship between two tunes will be useful to model the melody similarity notion for various applications such as QBH (Query by humming), music classification and retrieval, music plagiarism etc.
Music or audio data digitally sampled contains information about musical clip such as pitch, amplitude etc at multiple points along timeline. This huge data needs to be understood in the form of musical notations for the musicians. Praat is a tool used for acoustic analyses by audio researchers. We have processed the data produced by Praat using our own program to find useful information. We have focused on finding notation, duration of note and amplitude in a flute clip of Hindustani classical music. The clip was an alap clip in which there is no rhythm accompaniment to flute. Our attempt has given us encouraging preliminary results
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.