Improved musical onset detection with Convolutional Neural Networks
Citations Over TimeTop 1% of 2014 papers
Abstract
Musical onset detection is one of the most elementary tasks in music analysis, but still only solved imperfectly for polyphonic music signals. Interpreted as a computer vision problem in spectrograms, Convolutional Neural Networks (CNNs) seem to be an ideal fit. On a dataset of about 100 minutes of music with 26k annotated onsets, we show that CNNs outperform the previous state-of-the-art while requiring less manual preprocessing. Investigating their inner workings, we find two key advantages over hand-designed methods: Using separate detectors for percussive and harmonic onsets, and combining results from many minor variations of the same scheme. The results suggest that even for well-understood signal processing tasks, machine learning can be superior to knowledge engineering.
Related Papers
- On the Polyphony in the Heroes of the Marshes(2007)
- Polyphonic——Another Exploration of Woolf’s Novels(2013)
- Ironic Theory of Polyphonic Novel:Commenting Milan Kundera's Polyphonic Novel(2009)
- → Role of Polyphony in Creative Work of Bishop Hilarion (Alfeyev)(2021)