English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As generative models have risen in popularity, a domain that has risenalongside is generative models for music. Our study aims to compare theperformance of a simple Markov chain model and a recurrent neural network (RNN)model, two popular models for sequence generating tasks, in jazz musicimprovisation. While music, especially jazz, remains subjective in tellingwhether a composition is "good" or "bad", we aim to quantify our results usingmetrics of groove pattern similarity and pitch class histogram entropy. Wetrained both models using transcriptions of jazz blues choruses fromprofessional jazz players, and also fed musical jazz seeds to help give ourmodel some context in beginning the generation. Our results show that the RNNoutperforms the Markov model on both of our metrics, indicating better rhythmicconsistency and tonal stability in the generated music. Through the use ofmusic21 library, we tokenized our jazz dataset into pitches and durations thatour model could interpret and train on. Our findings contribute to the growingfield of AI-generated music, highlighting the important use of metrics toassess generation quality. Future work includes expanding the dataset of MIDIfiles to a larger scale, conducting human surveys for subjective evaluations,and incorporating additional metrics to address the challenge of subjectivityin music evaluation. Our study provides valuable insight into the use ofrecurrent neural networks for sequential based tasks like generating music.

Comparative Assessment of Markov Models and Recurrent Neural Networks for Jazz Music Generation