Automatic Style-Specific Accompaniment by Ching-Hua Chuan In this project, I extend the automatic accompaniment system in my dissertation research by applying Decision Trees to chord tone determination, and by conducting two verification experiments. The automatic accompaniment system aims to assist music lovers in writing a complete song with sophisticated chord progressions. The system takes melody as input, and harmonizes it with style-specific accompaniments. project website: [ html ]
	In Search of Sudokus with Good Alignment Properties for Musical Composition by Dolly Dhariwal This project takes Tamar Diesendruck's idea of using Sudoku grids to generate music, where the numbers map to musical fragments of corresponding units of time. The project maps Sudoku numbers to music, and calculates the alignment properties of a Sudoku grid. project website: [ html ] presentation: [ pdf ]
	Looking for Taste: Musical Aesthetics by Shane Hoversten Why do we like the things we like? More concretely, why are some people rabid about Bach, some about Elvis, and others about Cannibal Corpse? If we can generate music based on other music, then we could presumably get people to opine on what they think about it. We could, in this way, determine that people trained on GeneratorA prefer GeneratorA' to GeneratorB', if it happened that they did. A Factor Oracle is built and is output analyzed. project website: [ html ] presentation: [ pdf ]
	Gospel's Friend - Lyric based composing software by Beomsoo Kim The objective of this project is to use lyrics and emotional data to automatically generate melody and corresponding chords for Gospel music. The melody generator is basically a random walk, with mean and standard deviation guided by the emotional data. Derivatives of emotional data help to decide start note, directions, and number of rests. project website: [ html ] presentation: [ pdf ]
	Macro and Micro musical attributes controller by ChangHyun Kim Because computer music generated from the stochastic or statistical model can be hard to understand, I want to design a program that uses my piano playing as input, and I want to be able to transform or change some musical attributes in my piano performance. To this end, I create a contour drawing program that controls the volume and tempo of a given musical performance. project description: [ html ]
	Grammar Induction for Musical Melodies by Reid Swanson The focus of this work is a syntactic analysis of musical melodies. In Linguistics, accurate analyses are facilitated by large scale corpora of hand annotated parse trees developed over numerous years. Unfortunately, such a large scale corpus does not yet exist for music. Although generally not as accurate as supervised pasing of strings, unsupervised methods offer a solution when enough unlabeled data is available. In this work I utilize the constituent context model as proposed by Klein & Manning (2001) that obtains good performance compared to (impressive) baseline approaches. project website: [ html ]

You can visit last year's projects HERE.