The analysis of a simple k-means clustering algorithm
Proceedings of the sixteenth annual symposium on Computational geometry
Case study: a look of performance expression
Proceedings of the conference on Visualization '02
Performance visualization: a new challenge to music through visualization
Proceedings of the tenth ACM international conference on Multimedia
Emotional Coloring of Computer-Controlled Music Performances
Computer Music Journal
The Extraction of Expressive Shaping in Performance
Computer Music Journal
The music pattern: A creative tabletop music creation platform
Computers in Entertainment (CIE) - Special Issue: Advances in Computer Entertainment Technology
Visualizing digital media interactions: providing feedback on jam2jam AV performances
Proceedings of the 22nd Conference of the Computer-Human Interaction Special Interest Group of Australia on Computer-Human Interaction
Hi-index | 0.00 |
We present a new method for visualizing musical expressions with a special focus on the three major elements of tempo change, dynamics change, and articulation. We have represented tempo change as a horizontal interval delimited by vertical lines, while dynamics change and articulation within the interval are represented by the height and width of a bar, respectively. Then we grouped local expression into several groups by k-means clustering based on the values of the elements. The resulting groups represented the emotional expression in a performance that is controlled by the rhythmic and melodic structure, which controls the gray scale of the graphical components. We ran a pilot experiment to test the effectiveness of our method using two matching tasks and a questionnaire. In the first task, we used the same section of music, played by two different interpretations, while in the second task, two different sections of a performance were used. The results of the test seem to support the present approach, although there is still room for further improvement that will reflect the subtleties in performance.