Did a spike this week on the Librosa API documentation this week. Very dense stuff; Librosa seems to be a powerful and extensive library, but I think there are only a handful of specific features we will need to achieve the goal of the project. I’ve been running some test programs, seeing what data I can pull from some of my own collection of MP3s. Those little tests have given me a decent understanding of how librosa works on its own, so now it comes down to seeing how we can leverage it to meet our needs. Another member of my group is also doing the same with the Flask web framework, as we’re interested in making this application a web application.
Fleshing out the details
A member in my group who is savvy in front end design drew up some ideas for how the user interface could look. From my point of view, I think the concepts are great. It seems the direction we’re going right now is to use a visual aid, like a pie chart or bar graph, to denote the confidence that the program has in its genre classification of an uploaded audio clip. Nothing overly flashy, but bold and easy to read. That, to me, is actually more important in terms of accessibility. Front end is not really my forte, however, but I’m eager to learn and contribute to that portion of the project in any way that I can. As I mentioned before, though, I’m much more interested in the machine learning and audio preprocessing aspect of this project.
Due to some unforeseen circumstances, our group will be formally submitting our project plan tonight after our team meeting, so that will be the first order of business. After that, I have an inclination to start figuring the logistics of the audio processing portion of this assignment.
This week, I met with my new group for our Capstone project. We’re creating an app that takes in a clip of a song and be able to identify the genre of that song based on the clip. We’re going to be using some pretty interesting technologies like Tensor Flow with Keras, Librosa to preprocess the audio, and some data science libraries like pandas and matplotlib. Our goals that we set for this week were to research the Python libraries that we are planning on using, brainstorming ideas for a project plan, and sketching up an idea for the user interface for the application.
I’m going to be spending the next week researching these new libraries, but in particular I’m very interested to learn about Librosa. See, in a past life, I wanted to be a music producer. Ever since I was 12 years old, I’ve played in rock and metal bands with my friends. Here’s a pic of me from 2006 playing with some friends. Check out my edgy Parental Advisory t-shirt and wild hair!
I’ve sang and played some bass and guitar, but my really bread and butter is drums. During my first undergrad, I took many classes in recording techniques. I’ve even self produced a few songs, but only one of them I feel comfortable sharing.
Anyway, to say I’m excited to get started on this project is an understatement. Looking forward to what myself and my group create!
With the baby girl on the way, 2022 is shaping up to be a very busy year, thats for sure. I’ll be sure to update yinz with the countdown to baby at the end of my blog posts, because its fun and I’m excited!
My mom had just brought home a giant box with a cow pattern. I excitedly ripped it open and inside I found (as you may have guessed if you’re as old as I am) a Gateway 2000 computer. I was over the moon with that thing. I spent many nights staring into its oversized CRT monitor discovering all I could about how it worked. I cracked open its comically enormous tower once, much to the chagrin of my parents, and ogled over its cards and rats nest of connection cables. Life was pretty good
My love and curiosity for computers began with that lovable, off-white relic. I had never thought about actually pursuing a career in computers or software, mainly because I didn’t really think I was smart enough to do it. My math skills in high school were average at best, and guidance councilors I had spoken to had actually even tried to discourage me from it. But it wasn’t until I met my wife in 2017 that I decided to give it a try. She convinced me to take a couple community college classes in Java just to see if I had the aptitude for it. For the record, she always believed I did, I just needed to convince myself. I actually found myself taking to the basics of programming pretty easily. It wasn’t all impossibly complex mathematics like I had thought! During some of those classes, I also picked up a small Arduino starter kit. I had an interest in writing some code that actually made a real, physical thing do something. Those experiments further cemented my intent to make a career change.
I graduated with my first bachelors degree in Broadcast Communication from Wets Liberty University in 2006. I am a newscast director for the local NBC affiliate in Pittsburgh, PA and I’ve been doing this now for about 10 years. For the most part it has been a pretty fun ride; I’ve made lasting friendships, covered some pretty awesome events, and even won two regional Emmy awards. But now it’s time for me to move on. My wife and I are expecting our first child (A girl!) this summer and I’m so excited!
My Story So Far at OSU and beyond
I’ve had a great time at Oregon State. I think my favorite class I’ve taken thus far would have to be Intro to Parallel Programming. Professor Bailey is a fantastic instructor, and the subject matter was incredibly interesting to me! My primary career interests after graduation include pursuing a career in robotics and autonomous systems. I think that’s why I’d really like to be included in the music genre neural net project for CS 467. Developing/training a neural network would look great on a resume, especially if I end up going the robotics route. Pittsburgh is becoming a serious robotics hub for the east coast and I really want to be a part of it.