Music Dataset Introduction

Why Music Dataset? Music Dataset is an free, public online platform that hopes to solve the subjectivity in music by collecting responses of abstract components in classical music from a variety of audiences. It seeks to take advantage of the online setting where people from all over the world can be easily connected through one project. The viewers are asked to place descriptive tags onto music according to the unique response that the particular repertoire evokes in them.

SRA Experience Recap

As a rising high school junior, I was honored to be part of a highly selective summer research program: Summer Research Academies at UC Santa Barbara in the summer of 2021. The program has an overall acceptance rate of 18.9% and I was one of five girls in a group of 26 students enrolled in its 9th track called Machine Intelligence: An Introduction to Optimization and Machine learning. During the four-week program, my two teammates and I were challenged to create a machine learning project.

Linux Learning(2) - Hugo and Git Rebase

What is Hugo? Hugo provides sample website templates, which include instructions in simple English language on how to fill in different sections. Once that is complete, Hugo will automatically generate the html code for the website using the template. The website can then be published using a url domain such as one from github. How?** Once template has been filled out, the static page can be build using code below:

Music and Machine Learning Brainstorm

My favorite hobbies revolve around music as I enjoy playing the piano, the flute, and dancing. Additionally, I enjoy building both tangible and virtual projects. In the future, I would like to major in Computer Science, and currently am most appealed in the field of machine learning. Thus, I would like to combine my interests to create a machine learning project that would benefit music education. Below are some of my project brainstorm ideas as well as how they can fulfill the needs for people from a variety of backgrounds.

Music and Machine Learning Brainstorm

If you look at my other post (SRA Experience Recap 7/26), the current music generation models can be improved to become more customizable if a dataset with specific labels is created. Then, when a user prompts for a certain characteristic as input, only songs with corresponding tags would be fed into the training model, and the output result would follow the desire of the user. Possible Labels to the MusicNet datasets Composer Musical period (eg.