Troubleshooting Our Model So we saw that our first GBT approach in the last post was, to quote myself, a “steaming pile of hot garbage”. In reality, that’s probably and understatement because it’s barely even a model. I could’ve gotten the results with literally no model and straight guesses. Disappointing to say the least. Of […]
Read More Music Genre Clustering #7 – Gradient Boosting (Part II)Selecting Model Man, we’ve made it so far haha. It’s felt like quite a journey so far. This is good. The bright light at the end of the tunnel is ahead. Let’s hope, when we reach the other side, the bright light comes from a blazing sun in a bright blue sky with clouds that […]
Read More Music Genre Clustering #6 – Gradient Boosting (Part I)Training & Classification Last post, I referenced a great MIR resource that already had outlined a process to do what I’m currently trying to do. To recap some of the methods I learned, each training song is broken up into frames and the MFCCs of each frame became a training sample. Each song yielded around […]
Read More Music Genre Clustering #5 – Extracting MFCCs from My iTunes LibraryMel-Frequency Cep-WHAA?? Uhh yeah, pretty much what the title says lol. Okay, let’s back up about 3 days. I’ve been doing a bit of light research on how to meaningfully extract features out of a song. In fact, this can probably be generalized to sounds in general because I’m by no means an expert on […]
Read More Music Genre Clustering #4 – Mel-Frequency Cepstral CoefficientsReview Okay, so the last post was great and all, but what exactly did I get out of it that will help me identify something to analyze? I saw librosa’s spectrogram, chromagram, and tempogram capabilities which help us somewhat identify the instruments, key, and tempo respectively. These will absolutely change and evolve as we listen […]
Read More Music Genre Clustering #3 – Analyzing Music GenresLibrosa I learned about LibROSA while watching a scipy video: Seems pretty cool, the guy seems like a huge music nerd (in the senses of a nerd about music and just a nerd in general), he seems to get who I am and what I want to do, so why not give it a try. […]
Read More Music Genre Clustering #2 – Exploring Librosa and its VisualizationsYello Yello. My name is Chi, and this is my second set of posts on this blog. In my first post about basketball, I go into a bit of an intro of myself. I won’t rehash everything, but maybe a small intro will help again. First of all, I work as an IT consultant by […]
Read More Music Genre Clustering #1 – Intro
