M. Gruhne, C. Dittmar, D. Gaertner, and G. Schuller, “An Evaluation of Pre-Processing Algorithms for Rhythmic Pattern Analysis,” in Proc. AES Convention 125, Oct. 2008, Paper 7542. [Online]. Available: https://aes.org/publications/elibrary-page/?id=14694
Gruhne M, Dittmar C, Gaertner D, Schuller G. An Evaluation of Pre-Processing Algorithms for Rhythmic Pattern Analysis. In: AES Convention 125. Audio Engineering Society; 2008. Paper 7542. Available from: https://aes.org/publications/elibrary-page/?id=14694
@inproceedings{Gruhne2008_14694,
author = {Gruhne, Matthias and Dittmar, Christian and Gaertner, Daniel and Schuller, Gerald},
title = {{An Evaluation of Pre-Processing Algorithms for Rhythmic Pattern Analysis}},
booktitle = {AES Convention 125},
note = {Paper 7542},
year = {2008},
month = oct,
publisher = {Audio Engineering Society},
url = {https://aes.org/publications/elibrary-page/?id=14694}
}
TY - CPAPER
TI - An Evaluation of Pre-Processing Algorithms for Rhythmic Pattern Analysis
AU - Gruhne, Matthias
AU - Dittmar, Christian
AU - Gaertner, Daniel
AU - Schuller, Gerald
T2 - AES Convention 125
M1 - Paper 7542
PY - 2008
DA - 2008/10/06
UR - https://aes.org/publications/elibrary-page/?id=14694
PB - Audio Engineering Society
LA - en
AB - For the semantic analysis of polyphonic music, such as genre recognition, rhythmic pattern features (also called Beat Histogram) can be used. Feature extraction is based on the correlation of rhythmic information from drum instruments in the audio signal. In addition to drum instruments, the sounds of pitched instruments are usually also part of the music signal to analyze. This can have a significant influence on the correlation patterns. This paper describes the influence of pitched instruments for the extraction of rhythmic features, and evaluates two different pre-processing methods. One method computes a sinusoidal and noise model, where its residual signal is used for feature extraction. In the second method, a drum transcription based on spectral characteristics of drum sounds is performed, and the rhythm pattern feature is derived directly from the occurrences of the drum events. Finally, the results are explained and compared in detail.
ER -
