Deep learning of chroma representation for cover song identification in compression domain

Methods for identifying a cover song typically involve comparing the similarity of chroma features between the query song and another song in the data set. However, considerable time is required for pairwise comparisons. In addition, to save disk space, most songs stored in the data set are in a com...

Full description

Saved in:
Bibliographic Details
Published in:Multidimensional systems and signal processing 2018-07, Vol.29 (3), p.887-902
Main Authors: Fang, Jiunn-Tsair, Chang, Yu-Ruey, Chang, Pao-Chi
Format: Article
Language:English
Subjects:
Artificial Intelligence
Artificial neural networks
Audio data
Circuits and Systems
Datasets
Decoding
Deep learning
Discrete cosine transform
Electrical Engineering
Engineering
Identification methods
Music
Neural networks
Representations
Signal,Image and Speech Processing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Methods for identifying a cover song typically involve comparing the similarity of chroma features between the query song and another song in the data set. However, considerable time is required for pairwise comparisons. In addition, to save disk space, most songs stored in the data set are in a compressed format. Therefore, to eliminate some decoding procedures, this study extracted music information directly from the modified discrete cosine transform coefficients of advanced audio coding and then mapped these coefficients to 12-dimensional chroma features. The chroma features were segmented to preserve the melodies. Each chroma feature segment was trained and learned by a sparse autoencoder, a deep learning architecture of artificial neural networks. The deep learning procedure was to transform chroma features into an intermediate representation for dimension reduction. Experimental results from a covers80 data set showed that the mean reciprocal rank increased to 0.5 and the matching time was reduced by over 94% compared with traditional approaches.
ISSN:0923-6082
1573-0824
DOI:10.1007/s11045-017-0476-x