This study presents a new method to exploit both accent and grouping structures of music in meter estimation. The system starts by extracting autocorrelation-based features that characterize accent periodicities. Based on the local boundary detection model, we construct grouping features that serve as additional cues for inferring meter. After the feature extraction, a multi-layer cascaded classifier based on neural network is incorporated to derive the most likely meter of input melody. Experiments on 7351 folk melodies in MIDI files indicate that the proposed system achieves an accuracy of 95.76% for classification into nine categories of meters.
Han-Ying LIN
National Chiao-Tung University
Chien-Chieh HUANG
National Chiao-Tung University
Wen-Whei CHANG
National Chiao-Tung University
Jen-Tzung CHIEN
National Chiao-Tung University
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
Han-Ying LIN, Chien-Chieh HUANG, Wen-Whei CHANG, Jen-Tzung CHIEN, "The Role of Accent and Grouping Structures in Estimating Musical Meter" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 4, pp. 649-656, April 2020, doi: 10.1587/transfun.2019EAP1107.
Abstract: This study presents a new method to exploit both accent and grouping structures of music in meter estimation. The system starts by extracting autocorrelation-based features that characterize accent periodicities. Based on the local boundary detection model, we construct grouping features that serve as additional cues for inferring meter. After the feature extraction, a multi-layer cascaded classifier based on neural network is incorporated to derive the most likely meter of input melody. Experiments on 7351 folk melodies in MIDI files indicate that the proposed system achieves an accuracy of 95.76% for classification into nine categories of meters.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2019EAP1107/_p
Copy
@ARTICLE{e103-a_4_649,
author={Han-Ying LIN, Chien-Chieh HUANG, Wen-Whei CHANG, Jen-Tzung CHIEN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={The Role of Accent and Grouping Structures in Estimating Musical Meter},
year={2020},
volume={E103-A},
number={4},
pages={649-656},
abstract={This study presents a new method to exploit both accent and grouping structures of music in meter estimation. The system starts by extracting autocorrelation-based features that characterize accent periodicities. Based on the local boundary detection model, we construct grouping features that serve as additional cues for inferring meter. After the feature extraction, a multi-layer cascaded classifier based on neural network is incorporated to derive the most likely meter of input melody. Experiments on 7351 folk melodies in MIDI files indicate that the proposed system achieves an accuracy of 95.76% for classification into nine categories of meters.},
keywords={},
doi={10.1587/transfun.2019EAP1107},
ISSN={1745-1337},
month={April},}
Copy
TY - JOUR
TI - The Role of Accent and Grouping Structures in Estimating Musical Meter
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 649
EP - 656
AU - Han-Ying LIN
AU - Chien-Chieh HUANG
AU - Wen-Whei CHANG
AU - Jen-Tzung CHIEN
PY - 2020
DO - 10.1587/transfun.2019EAP1107
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2020
AB - This study presents a new method to exploit both accent and grouping structures of music in meter estimation. The system starts by extracting autocorrelation-based features that characterize accent periodicities. Based on the local boundary detection model, we construct grouping features that serve as additional cues for inferring meter. After the feature extraction, a multi-layer cascaded classifier based on neural network is incorporated to derive the most likely meter of input melody. Experiments on 7351 folk melodies in MIDI files indicate that the proposed system achieves an accuracy of 95.76% for classification into nine categories of meters.
ER -