Section-level modeling of musical audio for linking performances to scores in Turkish makam music

• Published in: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 141 - 145
• Main Authors: Holzapfel, Andre, Simsekli, Umut, Senturk, Sertan, Taylan Cemgil, Ali
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-04-2015
• Series: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
• Subjects: Audio-to-score alignment; Computational modeling; Computer Science; Datalogi; Frequency estimation; Hidden Markov models; Hierarchical hidden Markov models; Joining processes; Media Technology; Medieteknik; Multiple signal classification; Probabilistic logic; Real-time systems; Section linking; Speech and Music Communication; Tal- och musikkommunikation; Turkish makam music; Audio-to-score alignment; Section linking; Turkish makam music; Hierarchical hidden Markov models
• ISBN: 1467369977; 9781467369978
• ISSN: 1520-6149; 2379-190X
• DOI: 10.1109/ICASSP.2015.7177948

Section linking aims at relating structural units in the notation of a piece of music to their occurrences in a performance of the piece. In this paper, we address this task by presenting a score-informed hierarchical Hidden Markov Model (HHMM) for modeling musical audio signals on the temporal level of sections present in a composition, where the main idea is to explicitly model the long range and hierarchical structure of music signals. So far, approaches based on HHMM or similar methods were mainly developed for a note-to-note alignment, i.e. an alignment based on shorter temporal units than sections. Such approaches, however, are conceptually problematic when the performances differ substantially from the reference score due to interpretation and improvisation, a very common phenomenon, for instance, in Turkish makam music. In addition to having low computational complexity compared to note-to-note alignment and achieving a transparent and elegant model, the experimental results show that our method outperforms a previously presented approach on a Turkish makam music corpus.