In North-Indian-Music-System(NIMS), tabla is mostly used as percussive accompaniment for vocal music in polyphonic compositions like Hindi filmy music, bhajan or devotional songs etc. The human auditory system uses perceptual grouping of musical elements and easily filters the tabla component, thereby decoding prominent rhythmic features like tala, tempo or laya from a polyphonic-composition. For Western music, lots of work have been reported for automated drum analysis of polyphonic composition. However, attempts at computational analysis of tala by separating the tabla-signal from mixed signal in NIMS have not been successful. Tabla is played with two components – right and left. The right-hand component has frequency overlap with singing voice and other instruments. So, tala analysis of polyphonic-composition, by accurately extracting the tabla-signal from the mixture is a baffling task, therefore an area of challenge. We propose a novel technique for successfully detecting tala using left-tabla signal, producing meaningful results because the left-tabla normally doesn’t have frequency overlap with voice and other instruments. North-Indian-rhythm follows complex cyclic pattern, against linear approach of Western-rhythm. We have exploited this cyclic property along with stressed and non-stressed methods of playing tabla-strokes to extract a characteristic pattern from the left-tabla strokes to determine the tala and tempo of the composition. Initial version, TaalMaan1.0, is capable of detecting dadra, kaharba, rupak, bhajani tala-s from wav files of old Hindi filmy music, bhajan or devotional songs etc, having tabla as rhythm instrument. The tabla component in the input clips should have adequate prominence, i.e. the tabla part should be humanly recognizable and also original wav recordings with as less noise as possible, are encouraged. As we need to validate the application with large number of samples, we intend to store the wav file given in this portal for detection of its tala, in our database. Also we intend to extend this methodology for studying other features (both stationary and nonstationary) of the all the relevant tala-s of NIMS and designing an automated rhythm-wise categorization system for polyphonic compositions. TaalMaan can also be used as an add-on tool for content-based music retrieval system for North Indian Music and for pedagogy or the music research and training system.

Try It