Towards Polyphony Reconstruction Using Multidimensional Multiple Sequence Alignment
The digitization of printed music scores through the process of optical music recognition is imperfect. In polyphonic scores, with two or more simultaneous voices, errors of duration or position can lead to badly aligned and inharmonious digital transcriptions. We adapt biological sequence analysis tools as a post-processing step to correct the alignment of voices. Our multiple sequence alignment approach works on multiple musical dimensions and we investigate the contribution of each dimension to the correct alignment. Structural information, such musical phrase boundaries, is of major importance; therefore, we propose the use of the popular bioinformatics aligner Mafft which can incorporate such information while being robust to temporal noise. Our experiments show that a harmony-aware Mafft outperforms sophisticated, multidimensional alignment approaches and can achieve near-perfect polyphony reconstruction.
The authors would like to thank Meinard Müller and Hendrik Vincent Koops for comments that greatly improved the manuscript.
- 2.Boulanger-Lewandowski, N., Bengio, Y., Vincent, P.: Modeling temporal dependencies in high-dimensional sequences: application to polyphonic music generation and transcription. arXiv preprint arXiv:1206.6392 (2012)
- 3.Bountouridis, D., Koops, H.V., Wiering, F., Veltkamp, R.C.: A data-driven approach to chord similarity and chord mutability. In: International Conference on Multimedia Big Data, pp. 275–278 (2016)Google Scholar
- 4.Cambouropoulos, E.: The local boundary detection model (LBDM) and its application in the study of expressive timing. In: International Computer Music Conference, pp. 17–22 (2001)Google Scholar
- 6.Carroll, H., Clement, M.J., Ridge, P., Snell, Q.O.: Effects of gap open and gap extension penalties. In: Biotechnology and Bioinformatics Symposium, pp. 19–23 (2006)Google Scholar
- 7.Dayhoff, M.O., Schwartz, R.M., Orcutt, B.C.: 22 a model of evolutionary change in proteins. In: Atlas of Protein Sequence and Structure, vol. 5, pp. 345–352. National Biomedical Research Foundation Silver Spring, MD (1978)Google Scholar
- 12.Hudek, A.K.: Improvements in the accuracy of pairwise genomic alignment (2010)Google Scholar
- 17.Lyu, Q., Wu, Z., Zhu, J., Meng, H.: Modelling high-dimensional sequences with LSTM-RTRBM: application to polyphonic music generation. In: International Conference on Artificial Intelligence, pp. 4138–4139. AAAI Press (2015)Google Scholar
- 19.Pugin, L., Crawford, T.: Evaluating omr on the early music online collection. In: International Society on Music, Information Retrieval, pp. 439–444 (2013)Google Scholar
- 21.Rodríguez López, M.E.: Automatic Melody Segmentation. Ph.D. thesis, Utrecht University (2016)Google Scholar
- 22.Sanguansat, P.: Multiple multidimensional sequence alignment using generalized dynamic time warping. WSEAS Trans. Math. 11(8), 668–678 (2012)Google Scholar
- 25.van Kranenburg, P.: A computational approach to content-based retrieval of folk song melodies. Ph.D. thesis (2010)Google Scholar
- 26.Volk, A., Garbers, J., Van Kranenburg, P., Wiering, F., Veltkamp, R.C., Grijp, L.P.: Applying rhythmic similarity based on inner metric analysis to folksong research. In: International Society on Music Information Retrieval, pp. 293–296 (2007)Google Scholar
- 28.Wang, S., Ewert, S., Dixon, S.: Robust joint alignment of multiple versions of a piece of music, pp. 83–88 (2014)Google Scholar