F. Gouyon and P. Herrera, “Determination of the Meter of Musical Audio Signals: Seeking Recurrences in Beat Segment Descriptors,” in Proc. AES Convention 114, Mar. 2003, pp. 5811:1-8. [Online]. Available: https://aes.org/publications/elibrary-page/?id=12583
Gouyon F, Herrera P. Determination of the Meter of Musical Audio Signals: Seeking Recurrences in Beat Segment Descriptors. In: AES Convention 114. Audio Engineering Society; 2003.pp. 5811:1-8. Available from: https://aes.org/publications/elibrary-page/?id=12583
@inproceedings{Gouyon2003_12583,
author = {Gouyon, Fabien and Herrera, Perfecto},
title = {{Determination of the Meter of Musical Audio Signals: Seeking Recurrences in Beat Segment Descriptors}},
booktitle = {AES Convention 114},
pages = {5811:1-8},
url = {https://aes.org/publications/elibrary-page/?id=12583},
year = {2003},
month = mar,
publisher = {Audio Engineering Society},
address = {Amsterdam Netherlands}
}
TY - CPAPER
TI - Determination of the Meter of Musical Audio Signals: Seeking Recurrences in Beat Segment Descriptors
AU - Gouyon, Fabien
AU - Herrera, Perfecto
T2 - AES Convention 114
SP - 1
EP - 8
M1 - Paper 5811
PY - 2003
DA - 2003/03/06
UR - https://aes.org/publications/elibrary-page/?id=12583
PB - Audio Engineering Society
CY - Amsterdam Netherlands
LA - en
AB - We address the problem of classifying polyphonic musical audio signals by their Meter, as 'binary' or 'ternary'. Experiments have been conducted on a 70 instances database (20s excerpts from commercial songs without particular genre or timbre restriction). The Meter is the number of beats between regularly recurring accents (or Downbeats). Our approach aims to test the hypothesis that acoustic evidences for Downbeats can be measured on the signal; putting a special focus on their temporal recurrences. We experimented several approaches to the problem of feature selection and report some interesting results: measurements of a very small set of beat descriptors (i.e. 4) and subsequent processing (based on descriptors' autocorrelation functions) permit to reach around 95% of correct classification. Using only the temporal centroid, almost 90% of correct classification can be achieved.
ER -