<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The problem of note onset detection in musical signals is considered. The proposed solution is based on known approaches in which an <italic>onset detection function</italic> is defined on the basis of spectral characteristics of audio data. In our approach, several onset detection functions are used simultaneously to form an input vector for a multi-layer non-linear perceptron, which learns to detect onsets in the training data. This is in contrast to standard methods based on thresholding the onset detection functions with a moving average or a moving median. Our approach is also different from most of the current machine-learning-based solutions in that we explicitly use the onset detection functions as an intermediate representation, which may therefore be easily replaced with a different one, e.g., to match the characteristics of a particular audio data source. The results obtained for a database containing annotated onsets for 17 different instruments and ensembles are compared with state-of-the-art solutions.</p></abstract>

The problem of note onset detection in musical signals is considered. The proposed solution is based on known approaches in which an onset detection function is defined on the basis of spectral characteristics of audio data. In our approach, several onset detection functions are used simultaneously to form an input vector for a multi-layer non-linear perceptron, which learns to detect onsets in the training data. This is in contrast to standard methods based on thresholding the onset detection functions with a moving average or a moving median. Our approach is also different from most of the current machine-learning-based solutions in that we explicitly use the onset detection functions as an intermediate representation, which may therefore be easily replaced with a different one, e.g., to match the characteristics of a particular audio data source. The results obtained for a database containing annotated onsets for 17 different instruments and ensembles are compared with state-of-the-art solutions.

Note onset detection in musical signals via neural–network–based multi–ODF fusion

Institute of Information Technology, Łódź University of Technology, ul. Wólczańska 215, 90-924 Łódź, Poland

International Journal of Applied Mathematics and Computer Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

The problem of note onset detection in musical signals is considered. The proposed solution is based on known approaches in which an onset detection function...

Note onset detection in musical signals via neural–network–based multi–ODF fusion

Published Online: Mar 31, 2016

Page range: 203 - 213

Received: Jun 25, 2014

DOI: https://doi.org/10.1515/amcs-2016-0014

Keywords
note onset detection, onset detection function, multi-layer perceptron, multi-ODF fusion, NN-based fusion

© 2016 Bartłomiej Stasiak et al., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Note onset detection in musical signals via neural–network–based multi–ODF fusion

Published Online: Mar 31, 2016

Page range: 203 - 213

Received: Jun 25, 2014

DOI: https://doi.org/10.1515/amcs-2016-0014

Keywordsnote onset detection, onset detection function, multi-layer perceptron, multi-ODF fusion, NN-based fusion

© 2016 Bartłomiej Stasiak et al., published by De Gruyter Open

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Keywords
note onset detection, onset detection function, multi-layer perceptron, multi-ODF fusion, NN-based fusion