Authors:
Marcelo Cicconet
and
Paulo Cezar Carvalho
Affiliation:
IMPA, Brazil
Keyword(s):
Musical information visualization, Chroma vector, Loudness, Self-similarity matrix, Novelty score.
Related
Ontology
Subjects/Areas/Topics:
Abstract Data Visualization
;
Computer Vision, Visualization and Computer Graphics
;
General Data Visualization
;
Presentation Methods
;
Visual Representation and Interaction
Abstract:
Most audio and video editors employ a representation of music pieces based on the Pulse Code Modulation waveform, from which not much information, besides the energy envelope, can be visually captured. In the present work we discuss the importance of presenting to the user some hints about the melodic content of the audio to improve the visual segmentation of a music piece, thereby speeding up editing tasks. Such a representation, although powerful in the mentioned sense, is of simple computation, a desirable property because loading an audio or video should be done very fast in an interactive environment.