Paper Info
Title
REpeating Pattern Extraction Technique (REPET): A Simple Method for Music/Voice Separation
Abstract
Repetition is a core principle in music. Many musical pieces are characterized by an underlying repeating structure over which varying elements are superimposed. This is especially true for pop songs where a singer often overlays varying vocals on a repeating accompaniment. On this basis, we present the REpeating Pattern Extraction Technique (REPET), a novel and simple approach for separating the repeating “background” from the non-repeating “foreground” in a mixture. The basic idea is to identify the periodically repeating segments in the audio, compare them to a repeating segment model derived from them, and extract the repeating patterns via time-frequency masking. Experiments on data sets of 1,000 song clips and 14 full-track real-world songs showed that this method can be successfully applied for music/voice separation, competing with two recent state-of-the-art approaches. Further experiments showed that REPET can also be used as a preprocessor to pitch detection algorithms to improve melody extraction.
Year
DOI
Venue
2013
10.1109/TASL.2012.2213249
Audio, Speech, and Language Processing, IEEE Transactions
Keywords
Field
DocType
music,speech processing,time-frequency analysis,REPET,full-track real-world songs,melody extraction improvement,music-voice separation,nonrepeating foreground,pitch detection algorithms,preprocessor,repeating background,repeating pattern extraction technique,time-frequency masking,Melody extraction,music structure analysis,music/voice separation,repeating patterns
Speech processing,Data set,Pattern recognition,Masking (art),Computer science,Speech recognition,Preprocessor,Time–frequency analysis,Artificial intelligence,Pitch detection algorithm
Journal
Volume
Issue
ISSN
21
1
1558-7916
Citations 
PageRank 
References 
60
1.98
15
Authors
2
Name
Order
Citations
PageRank
Zafar Rafii1601.98
Bryan Pardo283063.92