Automatic Composing Based On Pitch Detection of Chinese Poetry Recitation

DOI

10.2991/icmcm-16.2016.6How to use a DOI?

Keywords

Computer Music; Digital Audio Signal Processing; Algorithmic Composition

Abstract

The balance between randomization and regularization is a key and contradictory issue in the development of automatic composing. Randomized algorithm focuses on creating innovative and novel melodies but will generate unpleasant result. Regularized algorithm uses the existed music and rules to compose pleasant music piece, but the results are similar to the pieces in the training set. In this paper, we set up a new automatic composition model by detecting the pitch of Chinese poetry recitation. First, we utilize the Simplified Inverse Filter Tracking (SIFT) to detect the pitch of the acoustic input signal. Variety of the intonations of the texts of Chinese poetry ensures the innovativeness and randomness of the pitch change. Meanwhile, the congruence between melody and tones makes the change of pitch musically. In order to make the rhythm musical as well, we introduce the database of music scores (in the form of MusicXML) and apply a matching algorithm to determine the duration of each note. The experiment shows that the melody generated by our system is both innovative and in agreement with the musicology in pitch and rhythm.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Rongfeng Li
AU  - Xinyun Zhang
PY  - 2016/12
DA  - 2016/12
TI  - Automatic Composing Based On Pitch Detection of Chinese Poetry Recitation
BT  - Proceedings of the 2016 7th International Conference on Mechatronics, Control and Materials (ICMCM 2016)
PB  - Atlantis Press
SP  - 25
EP  - 29
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmcm-16.2016.6
DO  - 10.2991/icmcm-16.2016.6
ID  - Li2016/12
ER  -