This is a research and learning project i plan to continue for the time being The aim of this project is to test , analyse and learn the working of sound bytes and the working of the sound in itself
Dataset used ------->http://www.esac-data.org/
the dataset used here is for the german language as it was the first one i looked at and followed with I plan on using other asian languages and sound datasets to analyse sound generation for them specifially
Tools Used -------->
Music21 - a python package
anaconda
git , vs code , pycharm , pyenv , muscore(4) , and packages like Tensorflow , Keras , json and numpy to name a few also i plan on using a lot of research papers as my source of study and code-inspirations , so i will try and link them indivisually to make it easier to find later on
I plan on doing many things with this dataset such as using different parametres and working on improving my overall melody or efficiency as one would day. I also plan on doing a lot more than sound generation in itself , such as sound analysis - providing a taste of music to the user or maybe even composer analysis
My main aim is to do RESEARCH and by that term dont mean to invent nessesarily , but to find new usecases or to find a new way to implement a new method in this whole process to give the programmer an edge in performance and time and result optimzation.