Filtering by
- All Subjects: Chamber music
- All Subjects: Jazz
- Status: Published
The first section, marked “With concentrated intensity,” is characterized by the juxtaposition of tonal ambiguity and tonal affirmation, as well as the use of polymetric counterpoint (often 7/8 against 4/4 or 7/8 against 3/4). The middle section, marked “Crystalline,” provides contrast in its use of unmetered sections and independent tempos. The refraction of light is represented in this movement by a 22-note row based on a hexachord (B-flat, F, C, G, A, E) introduced in measure 164 of the first section. The third section, marked “With frenetic energy,” begins without pause on an arresting entrance of the drums playing an additive rhythmic pattern. This pattern (5+7+9+1) amounts to 22 eighth-note pulses and informs much of the motivic and structural considerations for the remainder of the piece.
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.