Filtering by
- Member of: Theses and Dissertations
demonstrate traditional jazz clarinet techniques and language in terms of motives,
patterns, and a variety of articulations. This project also includes guidelines on how to
practice jazz improvisation as well as how to apply Fountain’s techniques and jazz
language to one’s own improvisation. Though there are countless musicians who have
made remarkable contributions to the development of the jazz language, Pete Fountain’s
unique style is particularly worthy of study due to his massive media presence, effortless
playing techniques, unique tone quality, and showmanship throughout his career.
The purpose of this project is to create a useful tool for musicians that utilizes the harmonic content of their playing to recommend new, relevant chords to play. This is done by training various Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) on the lead sheets of 100 different jazz standards. A total of 200 unique datasets were produced and tested, resulting in the prediction of nearly 51 million chords. A note-prediction accuracy of 82.1% and a chord-prediction accuracy of 34.5% were achieved across all datasets. Methods of data representation that were rooted in valid music theory frameworks were found to increase the efficacy of harmonic prediction by up to 6%. Optimal LSTM input sizes were also determined for each method of data representation.
My proposed project is an educational application that will seek to simplify the<br/>process of internalizing the chord symbols most commonly seen by those learning<br/>musical improvisation. The application will operate like a game, encouraging the<br/>user to identify chord tones within time limits and award points for successfully<br/>doing so.
Using two interviews with local Phoenix professional chamber musicians, this document aims to compare their experiences across musical styles to find common ground and understand the value of chamber music as a professional and educational tool.