This text connects essential knowledge about music and human auditory perception with signal processing algorithms to solve the specific problem of pitch estimation. The designed algorithm obtains an estimate of the magnitude spectrum via STFT and models the harmonic structure of each pitch contained in the magnitude spectrum with Gaussian density mixtures, whose parameters are subsequently estimated via an Expectation-Maximization (EM) algorithm. Heuristics for EM initialization are formulated mathematically. A prototype was implemented in MATLAB, featuring a GUI that provides for visual (spectrogram) and numerical (console) verification of results. The algorithm was tested using an array of data ranging from single to triple superposed instrument recordings. Its advantages and limitations are discussed, and a brief outlook over potential future research is given.

Autorentext

The author studied Electrical Engineering and Computer Science at the Technische Universität Berlin from 2001 to 2004, where he held a Teaching Assistantship position in Communication Systems under Prof. Dr.-Ing. Thomas Sikora. In late 2003, he was selected as a Naumann-Etienne scholar and a World Student Fund fellow, which led him to the Georgia Institute of Technology in Atlanta, Ga., in 2004. There, he pursued advanced studies in Digital Signal Processing, Control Systems, and Software Engineering. He concluded his studies with research in pitch estimation under Dr. Chin-Hui Lee.