Modeling Concept Dynamics for Large Scale Music Search

Continuing advances in data storage and communication technologies have led to an explosive growth in digital music collections. To cope with their increasing scale, we need effective Music Information Retrieval (MIR) capabilities like tagging, concept search and clustering. Integral to MIR is a fra...

Full description

Saved in:
Bibliographic Details
Main Authors: SHEN, Jialie, PANG, Hwee Hwa, WANG, Meng, YAN, Shuicheng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2012
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/1647
https://ink.library.smu.edu.sg/context/sis_research/article/2646/viewcontent/p455_shen.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-2646
record_format dspace
spelling sg-smu-ink.sis_research-26462017-07-11T13:34:18Z Modeling Concept Dynamics for Large Scale Music Search SHEN, Jialie PANG, Hwee Hwa WANG, Meng YAN, Shuicheng Continuing advances in data storage and communication technologies have led to an explosive growth in digital music collections. To cope with their increasing scale, we need effective Music Information Retrieval (MIR) capabilities like tagging, concept search and clustering. Integral to MIR is a framework for modelling music documents and generating discriminative signatures for them. In this paper, we introduce a multimodal, layered learning framework called DMCM. Distinguished from the existing approaches that encode music as an ensemble of order-less feature vectors, our framework extracts from each music document a variety of acoustic features, and translates them into low-level encodings over the temporal dimension. From them, DMCM elucidates the concept dynamics in the music document, representing them with a novel music signature scheme called Stochastic Music Concept Histogram (SMCH) that captures the probability distribution over all the concepts. Experiment results with two large music collections confirm the advantages of the proposed framework over existing methods on various MIR tasks. 2012-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/1647 info:doi/10.1145/2348283.2348346 https://ink.library.smu.edu.sg/context/sis_research/article/2646/viewcontent/p455_shen.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Music Information Retrieval Similarity Measure Music Concepts Databases and Information Systems Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Music Information Retrieval
Similarity Measure
Music Concepts
Databases and Information Systems
Numerical Analysis and Scientific Computing
spellingShingle Music Information Retrieval
Similarity Measure
Music Concepts
Databases and Information Systems
Numerical Analysis and Scientific Computing
SHEN, Jialie
PANG, Hwee Hwa
WANG, Meng
YAN, Shuicheng
Modeling Concept Dynamics for Large Scale Music Search
description Continuing advances in data storage and communication technologies have led to an explosive growth in digital music collections. To cope with their increasing scale, we need effective Music Information Retrieval (MIR) capabilities like tagging, concept search and clustering. Integral to MIR is a framework for modelling music documents and generating discriminative signatures for them. In this paper, we introduce a multimodal, layered learning framework called DMCM. Distinguished from the existing approaches that encode music as an ensemble of order-less feature vectors, our framework extracts from each music document a variety of acoustic features, and translates them into low-level encodings over the temporal dimension. From them, DMCM elucidates the concept dynamics in the music document, representing them with a novel music signature scheme called Stochastic Music Concept Histogram (SMCH) that captures the probability distribution over all the concepts. Experiment results with two large music collections confirm the advantages of the proposed framework over existing methods on various MIR tasks.
format text
author SHEN, Jialie
PANG, Hwee Hwa
WANG, Meng
YAN, Shuicheng
author_facet SHEN, Jialie
PANG, Hwee Hwa
WANG, Meng
YAN, Shuicheng
author_sort SHEN, Jialie
title Modeling Concept Dynamics for Large Scale Music Search
title_short Modeling Concept Dynamics for Large Scale Music Search
title_full Modeling Concept Dynamics for Large Scale Music Search
title_fullStr Modeling Concept Dynamics for Large Scale Music Search
title_full_unstemmed Modeling Concept Dynamics for Large Scale Music Search
title_sort modeling concept dynamics for large scale music search
publisher Institutional Knowledge at Singapore Management University
publishDate 2012
url https://ink.library.smu.edu.sg/sis_research/1647
https://ink.library.smu.edu.sg/context/sis_research/article/2646/viewcontent/p455_shen.pdf
_version_ 1770571389096427520