Resumen de Knowledge-based onset detection in musical application

Norberto Degara Quintela, Antonio Pena Giménez, Manuel Ángel Sobreira Seoane, Soledad Torres Guijarro

• Onset detection is useful in a number of applications for audio signals. The goal of this paper is to present a combination of techniques using a blackboard system, an approach taken from expert systems. The proposed system defines a global sound source separation system that allows for the integration of multiple audio analysis methods. In this particular case, experts integrate onset detection algorithms that use their own analysis strategy. A voting scheme of combination of algorithms is presented.