We have been developing a music analysis system called a polyphonic music time-span tree analyzer (PTTA). A time-span tree assigns a hierarchy of ‘structural importance’ to the notes of a piece of music on the basis of the Generative Theory of Tonal Music (GTTM). However, the theory only accepts homophonic music. To solve this problem, we first record the composers’ processes for arranging from polyphony to homophony because the processes show how a musician reduces ornamental notes. Using the recording of the arrangement process with the time-span tree of the homophony, we manually acquire a time-span tree of polyphony. Then we attempt to develop a PTTA that semi-automatically acquires a time-span tree of polyphony by implementing an additional novel rule for time-span analysis. Experimental results show that the PTTA using our proposed rules outperforms the baseline.
- Masatoshi Hamanaka, Keiji Hirata, Satoshi Tojo: Toward Developing a Polyphonic Music Time-Span Tree Analyzer, Mathematics and Computation in Music 2013(MCM2013), June 2013. [PDF]
- Masatoshi Hamanaka, Satoshi Tojo: Interactive Gttm Analyzer, Proceedings of the 10th International Conference on Music Information Retrievalconference(ISMIR2009), pp. 291-296, October 2009. [PDF]
- Keiji Hirata, Satoshi Tojo, Masatoshi Hamanaka: Techniques for Implementing the Generative Theory of Tonal Music, ISMIR 2007(7th International Conference on Music Information Retrieval) Tutorial, September, 2007. [PDF]
- Masatoshi Hamanaka, Keiji Hirata, Satoshi Tojo: Implementing “A Generating Theory of Tonal Music”, Jornal of New Music Reserch (JNMR), Vol. 35, No. 4, pp. 249-277, 2006. [PDF]