Paper Info
Title
Musical instruments signal analysis and recognition using fractal features
Abstract
Analyzing the structure of music signals at multiple time scales is of importance both for modeling music signals and their automatic computer-based recognition. In this paper we propose the multi-scale fractal dimension profile as a descriptor useful to quantify the multiscale complexity of the music waveform. We have experimentally found that this descriptor can discriminate several aspects among different music instruments. We compare the descriptiveness of our features against that of Mel frequency cepstral coefficients (MFCCs) using both static and dynamic classifiers, such as Gaussian mixture models (GMMs) and hidden Markov models (HMMs). The methods and features proposed in this paper are promising for music signal analysis and of direct applicability in large-scale music classification tasks.
Year
Venue
Keywords
2011
Barcelona
fractals,hidden markov models,musical instruments,signal classification,mfcc,mel frequency cepstral coefficients,musical instruments signal analysis,automatic computer-based recognition,dynamic classifiers,fractal features,multiscale fractal dimension profile,music signal analysis,music waveform,musical instruments signal recognition,static classifiers,speech,steady state,multiple signal classification
Field
DocType
ISSN
Signal processing,Mel-frequency cepstrum,Fractal dimension,Pattern recognition,Musical,Computer science,Waveform,Fractal,Speech recognition,Artificial intelligence,Hidden Markov model,Mixture model
Conference
2076-1465
Citations 
PageRank 
References 
1
0.39
5
Authors
2
Name
Order
Citations
PageRank
Athanasia Zlatintsi1464.49
Petros Maragos23733591.97