In this letter we focus on the task of selecting the melody track from a polyphonic MIDI file. Based on the intuition that music and language are similar in many aspects, we solve the selection problem by introducing an n-gram language model to learn the melody co-occurrence patterns in a statistical manner and determine the melodic degree of a given MIDI track. Furthermore, we propose the idea of using background model and posterior probability criteria to make modeling more discriminative. In the evaluation, the achieved 81.6% correct rate indicates the feasibility of our approach.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Xiao WU, Ming LI, Hongbin SUO, Yonghong YAN, "Melody Track Selection Using Discriminative Language Model" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 6, pp. 1838-1840, June 2008, doi: 10.1093/ietisy/e91-d.6.1838.
Abstract: In this letter we focus on the task of selecting the melody track from a polyphonic MIDI file. Based on the intuition that music and language are similar in many aspects, we solve the selection problem by introducing an n-gram language model to learn the melody co-occurrence patterns in a statistical manner and determine the melodic degree of a given MIDI track. Furthermore, we propose the idea of using background model and posterior probability criteria to make modeling more discriminative. In the evaluation, the achieved 81.6% correct rate indicates the feasibility of our approach.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.6.1838/_p
Copy
@ARTICLE{e91-d_6_1838,
author={Xiao WU, Ming LI, Hongbin SUO, Yonghong YAN, },
journal={IEICE TRANSACTIONS on Information},
title={Melody Track Selection Using Discriminative Language Model},
year={2008},
volume={E91-D},
number={6},
pages={1838-1840},
abstract={In this letter we focus on the task of selecting the melody track from a polyphonic MIDI file. Based on the intuition that music and language are similar in many aspects, we solve the selection problem by introducing an n-gram language model to learn the melody co-occurrence patterns in a statistical manner and determine the melodic degree of a given MIDI track. Furthermore, we propose the idea of using background model and posterior probability criteria to make modeling more discriminative. In the evaluation, the achieved 81.6% correct rate indicates the feasibility of our approach.},
keywords={},
doi={10.1093/ietisy/e91-d.6.1838},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Melody Track Selection Using Discriminative Language Model
T2 - IEICE TRANSACTIONS on Information
SP - 1838
EP - 1840
AU - Xiao WU
AU - Ming LI
AU - Hongbin SUO
AU - Yonghong YAN
PY - 2008
DO - 10.1093/ietisy/e91-d.6.1838
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2008
AB - In this letter we focus on the task of selecting the melody track from a polyphonic MIDI file. Based on the intuition that music and language are similar in many aspects, we solve the selection problem by introducing an n-gram language model to learn the melody co-occurrence patterns in a statistical manner and determine the melodic degree of a given MIDI track. Furthermore, we propose the idea of using background model and posterior probability criteria to make modeling more discriminative. In the evaluation, the achieved 81.6% correct rate indicates the feasibility of our approach.
ER -