AVA: A Graphical User Interface for Automatic Vibrato and Portamento Detection and Analysis

Musicians are able to create different expressive performances of the same piece of music by varying expressive features. It is challenging to mathematically model and represent musical expressivity in a general manner. Vibrato and portamento are two important expressive features in singing, as well as in string, woodwind, and brass instrumental playing. We present AVA, an off-line system for automatic vibrato and portamento analysis. The system detects vibratos and extracts their parameters from audio input using a Filter Diagonalization Method, then detects portamenti using a Hidden Markov Model and presents the parameters of the best fit Logistic Model for each portamento. A graphical user interface (GUI), implemented in MATLAB, allows the user to interact with the system, to visualise and hear the detected vibratos and portamenti and their analysis results, and to identify missing vibratos or portamenti and remove spurious detection results. The GUI provides an intuitive way to see vibratos and portamenti in music audio and their characteristics, and has potential for use as a pedagogical and expression analysis tool.