Paper Info
Title
Fractal Dimensions of Music and Automatic Playlist Generation: Similarity Search via MP3 Song Uploads
Abstract
We present an automated approach to music search and playlist generation based on fractal dimensions of music. We compute 372 power-law metrics per song capturing statistical proportions of musical material. Using attribute selection and principal component analysis, we have reduced these metrics to approximately 45 independent features. These have been shown to capture important aspects of music aesthetics and similarity. Through an audio-to-MIDI transcription process, users may upload MP3 songs as search queries, in real time. This new development enables construction of music recommendation systems, which may work with previously unknown music. Unlike Pandora, last.fm, and Genius, such systems will analyze the actual music (potentially like the human ear), as opposed to harvesting information from humans (e.g., websites, user preferences, or musicologist recommendations). This approach combines time-frequency and spectral processing, information retrieval and audio analysis, and music classification. We present two on-line demos, using corpora from Magnatune and 7digital.
Year
DOI
Venue
2012
10.1109/IIH-MSP.2012.112
Intelligent Information Hiding and Multimedia Signal Processing
Keywords
Field
DocType
music recommendation system,harvesting information,similarity search,automated approach,music search,actual music,music aesthetics,mp3 song uploads,automatic playlist generation,information retrieval,audio analysis,unknown music,music classification,fractal dimensions,feature extraction,attribute selection,recommender systems,music,principal component analysis,audio signal processing,time frequency analysis,measurement,power laws,zipf s law,fractals,time frequency
Computer science,Upload,Artificial intelligence,Audio signal processing,Nearest neighbor search,Recommender system,Information retrieval,Pattern recognition,Musicology,Speech recognition,Audio analyzer,Pop music automation,Evolutionary music
Conference
ISBN
Citations 
PageRank 
978-1-4673-1741-2
0
0.34
References 
Authors
9
2
Name
Order
Citations
PageRank
Dana Hughes1125.09
Bill Manaris220421.81