This Project posits elementary analogies of existing Probabilistic and Machine Learning models that have been used to find solutions to the problem of the Structural Segmentation of Musical audio. I have tried to use the idea that the chord of a given beat or frame of a song is an analogous representation of the states generated by trained Hidden Markov Models in generating feature vectors for the aforementioned problem; and that the knowledge of the temporal boundaries within which, a group of frames lie, can be used as constraints in creating the feature vectors that are eventually clustered to identify the pattern in which the various segments of a song repeat.
The IST-PROJECT-REPORT-ABSTRACT TEMPLATE is used to produce the Project Reports of INSTITUTO SUPERIOR TECNICO, UNIVERSIDADE DE LISBOA, AGIIT and ESer Courses.
The Template is "smart", allowing to select the language of writing (English or Portuguese). Please view instructions in the README.TXT file.