DocumentCode :
3055864
Title :
Fractal Dimensions of Music and Automatic Playlist Generation: Similarity Search via MP3 Song Uploads
Author :
Hughes, Dana ; Manaris, Bill
Author_Institution :
Dept. of Comput. Sci., Coll. of Charleston, Charleston, SC, USA
fYear :
2012
fDate :
18-20 July 2012
Firstpage :
436
Lastpage :
440
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.
Keywords :
audio signal processing; fractals; music; principal component analysis; query processing; recommender systems; signal classification; spectral analysis; time-frequency analysis; 7digital; MP3 song uploads; Magnatune; attribute selection; audio analysis; audio-to-MIDI transcription process; automatic playlist generation; information retrieval; music aesthetics; music classification; music fractal dimensions; music recommendation systems; music search; music similarity; musical material statistical proportions; power-law metrics; principal component analysis; search queries; similarity search; spectral processing; time-frequency; Digital audio players; Feature extraction; Fractals; Humans; Measurement; Music; Principal component analysis; Zipf´s law; audio-to-MIDI transcription; fractal geometry of music; music similarity; playlist generation; power laws;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2012 Eighth International Conference on
Conference_Location :
Piraeus
Print_ISBN :
978-1-4673-1741-2
Type :
conf
DOI :
10.1109/IIH-MSP.2012.112
Filename :
6274276
Link To Document :
بازگشت