A supervised classification algorithm for note onset detection
Alexandre Lacoste,Douglas Eck +1 more
Reads0
Chats0
TLDR
It is concluded that a supervised learning approach to note onset detection performs well and warrants further investigation.Abstract:
This paper presents a novel approach to detecting onsets in music audio files. We use a supervised learning algorithm to classify spectrogram frames extracted from digital audio as being onsets or nononsets. Frames classified as onsets are then treated with a simple peak-picking algorithm based on amoving average.We present two versions of this approach. The first version uses a single neural network classifier. The second version combines the predictions of several networks trained using different hyperparameters. We describe the details of the algorithm and summarize the performance of both variants on several datasets.We also examine our choice of hyperparameters by describing results of cross-validation experiments done on a custom dataset. We conclude that a supervised learning approach to note onset detection performs well and warrants further investigation.read more
Citations
More filters
Journal ArticleDOI
Deep Learning for Audio Signal Processing
TL;DR: Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross fertilization between areas.
Proceedings ArticleDOI
End-to-end learning for music audio
TL;DR: Although convolutional neural networks do not outperform a spectrogram-based approach, the networks are able to autonomously discover frequency decompositions from raw audio, as well as phase-and translation-invariant feature representations.
Journal ArticleDOI
Automatic music transcription: challenges and future directions
TL;DR: Limits of current transcription methods are analyzed and promising directions for future research are identified, including the integration of information from multiple algorithms and different musical aspects.
Proceedings ArticleDOI
Improved musical onset detection with Convolutional Neural Networks
Jan Schlüter,Sebastian Böck +1 more
TL;DR: It is shown that CNNs outperform the previous state-of-the-art while requiring less manual preprocessing, suggesting that even for well-understood signal processing tasks, machine learning can be superior to knowledge engineering.
Proceedings Article
Moving beyond feature design: Deep architectures and automatic feature learning in music informatics
TL;DR: By reviewing deep architectures and feature learning, this work hopes to raise awareness in the community about alternative approaches to solving MIR challenges, new and old alike.
References
More filters
Book
Neural networks for pattern recognition
TL;DR: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Book ChapterDOI
Neural Networks for Pattern Recognition
Suresh Kothari,Heekuck Oh +1 more
TL;DR: The chapter discusses two important directions of research to improve learning algorithms: the dynamic node generation, which is used by the cascade correlation algorithm; and designing learning algorithms where the choice of parameters is not an issue.
Book
Numerical Recipes in C: The Art of Scientific Computing
TL;DR: Numerical Recipes: The Art of Scientific Computing as discussed by the authors is a complete text and reference book on scientific computing with over 100 new routines (now well over 300 in all), plus upgraded versions of many of the original routines, with many new topics presented at the same accessible level.