We are Dopefeel, Doyeon Kwak and Jongpil Lee (we made the team name ‘Dopefeel’ by combining Do from Doyeon and pil from Jongpil). We are pleased to release Dopefeel’s first work. We remixed the song “Sky High” by Park Saebyul, a professional singer. We’d appreciate it so much if you could enjoy and share it. (Saebyul, Doyeon and I are all at Graduate School of Culture Technology, KAIST)
We propose sample-level deep convolutional neural networks which learn representations from very small grains of waveforms (e.g. 2 or 3 samples) beyond typical frame-level input representations. In addition, we visualize filters learned in a sample-level DCNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency along layer, such as mel-frequency spectrogram that is widely used in music classification systems.
Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstractions. Considering this issue, we propose a convolutional neural networks (CNN)-based Feature Aggregation Method that embraces multi-level and multi-scaled features.
This research focuses on two distinctive determinants of DJ popularity in Electronic Dance Music (EDM) culture. While one’s individual artistic tastes (Audio Features) influence the construction of playlists for festivals, social relationships (Social Network) with other DJs also have an effect on the promotion of a DJ’s works.