TOTAL VARIATION IN VOCALS OVER TIME
Abstract: Recent advancements in audio processing provide a new opportunity to study musical trends using quantitative methods. In this work, we conduct an exploratory study of 43,153 vocal tracks of popular songs spanning nearly a century, from 1924 to 2010. We use source separation to extract the vocal stem and fundamental frequency (f0) estimation to analyze pitch tracks. In this demonstration, we calculate the total variation (TV) of each song, report trends in the metric over time and between genres, and provide lis- tening examples at our demo website.
NOTE: this event is part of the DL4MIR workshop series (ccrma-mir.github.io); guest speaker talks are open to the broader CCRMA community.