I finally built this sad little website. It hosts my resume in case I sent you an email and forgot to attach it. I may also write some blog posts about the stuff I learned during my graduate studies. In case I become too lazy to do it, I summarized the things I worked on below. Feel free to send me an email, I’m always happy to help or collaborate.
Here is my interview on Portuguese TV channel SIC Notícias, where I talk a bit about my research, and also about Portuguese and Turkish people.
Here is a sample song generated by our model from our latest research. The model is conditioned such that valence and arousal shift from negative to positive throughout the song. In simpler terms, the expressed emotion shifts from sad to happy. Other samples are also available.
Our paper titled “Symbolic Music Generation Based on Continous Emotions” is published on IEEE Access. The supplementary material is presented at the bottom of this page.
I have uploaded my recent lecture on Youtube. I talk about the basics of deep learning, and its applications on music. No background knowledge is required. Skip to 01:11:00 for symbolic music generation using deep learning.
Our paper titled “On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks” is published on IEEE Journal of Selected Topics in Signal Processing. The supplementary material is presented at the bottom of this page.
Our paper titled “Can learned frame prediction compete with block motion compensation for video coding?” is published on Springer Journal of Signal, Image and Video Processing. The supplementary material is presented at the bottom of this page.