papers AI Learner
The Github is limit! Click to go to the new site.

Musical Tempo and Key Estimation using Convolutional Neural Networks with Directional Filters

2019-03-26
Hendrik Schreiber, Meinard Müller

Abstract

In this article we explore how the different semantics of spectrograms’ time and frequency axes can be exploited for musical tempo and key estimation using Convolutional Neural Networks (CNN). By addressing both tasks with the same network architectures ranging from shallow, domain-specific approaches to deep variants with directional filters, we show that axis-aligned architectures perform similarly well as common VGG-style networks developed for computer vision, while being less vulnerable to confounding factors and requiring fewer model parameters.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.10839

PDF

http://arxiv.org/pdf/1903.10839


Similar Posts

Comments