Introduction Last winter, I worked on a personal project I call ongaku (from the Japanese for ‘music’). This was an attempt to use manifold learning to create a metric space for music. The preprocessing relied heavily on a method called (Valero and Alias 2012). This method was intended to replace Mel Frequency Cepstral Coefficients. Where Mel Frequency is a logarithmic transformation of sound frequency, in an attempt to simulate human perception of sound.

Introduction The internet has allowed any artist to share their work with the world, and in many cases be paid for it. This is mostly a recent development, with the creation of online marketplaces, and patronage services. The defining marketplace for the indie music scene on the internet is Bandcamp. Although it has been difficult to find an estimate for how large this marketplace actually is, Bandcamp does report some information about how much money has been spent on their platform.

Preliminary Analysis This will document the process of doing preliminary analysis on bandcamp album covers. This is part of an ongoing project which can be found here and on github. The goals of this exploration are to look into the viability of using machine learning methods in this setting. Selected methods will be fully automated and utilized for the final analysis. The './covers/' directory was generated from the album_cover_scrape function.

This is a project to look into the question: How do indie musicians use visual signs to indicate their subgenre? The main functions are in bandcamp_webtools.py, and do basic web scraping. Analysis will be done in the jupyter notebooks Proposal.ipynb, Prelims.ipynb, and Analysis.ipynb. These will also be uploaded as blog posts to my website. The github repository can be found here. The Exploratory analysis (corresponding to Proposal.ipynb) can also be found at this blog post.

Overview Ongaku is a method for creating playlists programmatically, using only the content of the song alone. It uses gammatone cepstral analysis to create unique matrices to represent each song. A gammatone cepstrum is similar to the more common spectra used for audio analysis. Instead of doing a Fourier transform, we do a reverse Fourier transform, and then apply a transformation according to the gammatone function. This function was designed to mimic the signals sent to the brain through the cochlear nerve, the nerve which connects the ear to the brain.