Effective Music Tagging through Advanced Statistical Modeling
Music information retrieval (MIR) holds great promise as a technology for managing large music archives. One of the key components of MIR that has been actively researched into is music tagging. While significant progress has been achieved, most of the existing systems still adopt a simple classific...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2010
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/515 https://ink.library.smu.edu.sg/context/sis_research/article/1514/viewcontent/Effective_Music_Tagging_through_Advanced_Statistical_Modeling__edited_.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-1514 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-15142017-07-11T13:54:31Z Effective Music Tagging through Advanced Statistical Modeling SHEN, Jialie WANG, Meng YAN, Shuicheng PANG, Hwee Hwa HUA, Xian-Sheng Music information retrieval (MIR) holds great promise as a technology for managing large music archives. One of the key components of MIR that has been actively researched into is music tagging. While significant progress has been achieved, most of the existing systems still adopt a simple classification approach, and apply machine learning classifiers directly on low level acoustic features. Consequently, they suffer the shortcomings of (1) poor accuracy, (2) lack of comprehensive evaluation results and the associated analysis based on large scale datasets, and (3) incomplete content representation, arising from the lack of multimodal and temporal information integration. In this paper, we introduce a novel system called MMTagger that effectively integrates both multimodal and temporal information in the representation of music signal. The carefully designed multilayer architecture of the proposed classification framework seamlessly combines Multiple Gaussian Mixture Models (GMMs) and Support Vector Machine (SVM) into a single framework. The structure preserves more discriminative information, leading to more accurate and robust tagging. Experiment results obtained with two large music collections highlight the various advantages of our multilayer framework over state of the art techniques. 2010-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/515 info:doi/10.1145/1835449.1835555 https://ink.library.smu.edu.sg/context/sis_research/article/1514/viewcontent/Effective_Music_Tagging_through_Advanced_Statistical_Modeling__edited_.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 Browsing Music information retrieval Search Tagging 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 |
Browsing Music information retrieval Search Tagging Databases and Information Systems Numerical Analysis and Scientific Computing |
spellingShingle |
Browsing Music information retrieval Search Tagging Databases and Information Systems Numerical Analysis and Scientific Computing SHEN, Jialie WANG, Meng YAN, Shuicheng PANG, Hwee Hwa HUA, Xian-Sheng Effective Music Tagging through Advanced Statistical Modeling |
description |
Music information retrieval (MIR) holds great promise as a technology for managing large music archives. One of the key components of MIR that has been actively researched into is music tagging. While significant progress has been achieved, most of the existing systems still adopt a simple classification approach, and apply machine learning classifiers directly on low level acoustic features. Consequently, they suffer the shortcomings of (1) poor accuracy, (2) lack of comprehensive evaluation results and the associated analysis based on large scale datasets, and (3) incomplete content representation, arising from the lack of multimodal and temporal information integration. In this paper, we introduce a novel system called MMTagger that effectively integrates both multimodal and temporal information in the representation of music signal. The carefully designed multilayer architecture of the proposed classification framework seamlessly combines Multiple Gaussian Mixture Models (GMMs) and Support Vector Machine (SVM) into a single framework. The structure preserves more discriminative information, leading to more accurate and robust tagging. Experiment results obtained with two large music collections highlight the various advantages of our multilayer framework over state of the art techniques. |
format |
text |
author |
SHEN, Jialie WANG, Meng YAN, Shuicheng PANG, Hwee Hwa HUA, Xian-Sheng |
author_facet |
SHEN, Jialie WANG, Meng YAN, Shuicheng PANG, Hwee Hwa HUA, Xian-Sheng |
author_sort |
SHEN, Jialie |
title |
Effective Music Tagging through Advanced Statistical Modeling |
title_short |
Effective Music Tagging through Advanced Statistical Modeling |
title_full |
Effective Music Tagging through Advanced Statistical Modeling |
title_fullStr |
Effective Music Tagging through Advanced Statistical Modeling |
title_full_unstemmed |
Effective Music Tagging through Advanced Statistical Modeling |
title_sort |
effective music tagging through advanced statistical modeling |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2010 |
url |
https://ink.library.smu.edu.sg/sis_research/515 https://ink.library.smu.edu.sg/context/sis_research/article/1514/viewcontent/Effective_Music_Tagging_through_Advanced_Statistical_Modeling__edited_.pdf |
_version_ |
1770570445769146368 |