More Web Proxy on the site http://driver.im/

research-article

An Efficient Cascaded Filtering Retrieval Method for Big Audio Data

Authors:

Baoning NiuAuthors Info & Claims

IEEE Transactions on Multimedia, Volume 17, Issue 9

Pages 1450 - 1459

https://doi.org/10.1109/TMM.2015.2460121

Published: 01 September 2015 Publication History

Abstract

Fast audio retrieval is crucial for many important applications and yet demanding due to the high dimension nature and increasingly larger volume of audios on the Internet. Although audio fingerprinting can greatly reduce its dimension while keeping audio identifiable, the dimension for audio fingerprints is still too high to scale up for big audio data. The tradeoff between accuracy (measured by precision and recall rate) and efficiency (measured by retrieval time) prevents further reduction in the dimension of fingerprints. This paper shows that a multi-stage filtering strategy can achieve both speedup and high accuracy, with the beginning stages focusing on speedup and the end stage emphasizing accuracy. With this strategy, an efficient cascaded filtering retrieval method is proposed that consists of filtering with Fibonacci hashing, the middle fingerprint, thresholds to quickly select candidate audios, and refining with an accurate and robust fingerprint on the candidate audios. Experiments with 500 000 audios show that the proposed method can achieve a speed gain more than 28 K times that of the Fibonacci hashing retrieval. After applying MP3 conversion, resampling, white noise addition, and background noise addition, the recall rates of the method are all above 99.45%, and the precision is the same as the Philips audio fingerprint, which is close to 100%.

References

[1]

J. Haitsma and T. Kalker, “A highly robust audio fingerprinting system,” in Proc. ISMIR, 2002, pp. 107–115.

[2]

F. Precioso, M. Cord, D. Gorisse, and N. Thome, “Efficient bag-of-features kernel representation for image similarity search,” in Proc. ICIP, 2011, pp. 109–112.

[3]

M. Chen et al., “A fast retrieval algorithm based on Fibonacci hashing for audio fingerprinting systems,” in Proc. ICAIEES, 2013, pp. 219–222.

[4]

P. Grosche, M. Müller, and J. Serrà Audio content-based music retrieval Multimodal Music Processing, Wadern, Germany: Schloss Dagstuhl, 2012, vol. 3, pp. 157–174.

[5]

K. I. Diamantaras and S. Y. Kung, Principal Component Neural Networks: Theory and Applications, New York, NY USA: Wiley, 1996.

Digital Library

[6]

Y. G. Hu, Y. Wu, and J. Bu, “Dimensionality reduction in audio fingerprint based on weighted PCA,” in Comput. Appl., vol. 26, no. 9, pp. 2250–2254, Sep. 2006.

[7]

L. Shen, Y. Guan, Y. Wu, and Y. Zhao, “Fast audio fingerprint search strategy for song identification,” in Proc. ICNDS, 2009, pp. 259–262.

[8]

G. Zheng, M. Li, J. Han, and T. Zheng, “A fast audio retrieval method based on negativity judgment,” in Proc. IIH-MSP, 2009, pp. 1156–1159.

[9]

V. Panagiotou and N. Mitianoudis, “PCA summarization for audio song identification using gaussian mixture models,” in Proc. DSP, 2013, pp. 1–6.

[10]

J. Haitsma, T. Kalker, and J. Oostveen, “An efficient database search strategy for audio fingerprinting,” in Proc. IEEE Workshop Multimedia Signal Process., Dec. 2002, pp. 178–181.

[11]

F. Kurth, A. Ribbrock, and M. Clausen, “Identification of highly distorted audio material for querying large scale databases,” in Proc. AES112, 2002, pp. 1–8.

[12]

F. Kurth and M. Muller, “Efficient index-based audio matching,” in IEEE Trans. Audio, Speech, Language Process., vol. 16, no. 2, pp. 382–395, Feb. 2008.

Digital Library

[13]

C. P. J. Vitola, J. Sepulveda, and J. I. Martinez, “Fast content-based audio retrieval algorithm,” in Proc. STSIVA, 2013, pp. 1–5.

[14]

S. Yao, Y. Wang, and B. Niu, “An efficient cascaded filtering retrieval method for big audio data,” in Proc. BigMM, 2015, pp. 105–115.

[15]

T. Shibuya, M. Abe, and M. Nishiguchi, “Audio fingerprinting robust against reverberation and noise based on quantification of sinusoidality,” in Proc. ICME, 2013, pp. 1–6.

[16]

D. I. Barnea and H. F. Silverman, “A Class of algorithms for fast digital image registration,” in IEEE Trans. Comput., vol. 100, no. 2, pp. 179–186, Feb. 1972.

Digital Library

Cited By

Serrano SScarpa M(2023)Accuracy comparisons of fingerprint based song recognition approaches using very high granularityMultimedia Tools and Applications10.1007/s11042-023-14787-282:20(31591-31606)Online publication date: 21-Mar-2023
https://dl.acm.org/doi/10.1007/s11042-023-14787-2
Huang YWang YLi HZhang YZhang Q(2022)Encrypted speech retrieval based on long sequence BiohashingMultimedia Tools and Applications10.1007/s11042-022-12371-881:9(13065-13085)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1007/s11042-022-12371-8
Li TJia MCao X(2021)A Hierarchical Retrieval Method Based on Hash Table for Audio FingerprintingIntelligent Computing Theories and Application10.1007/978-3-030-84522-3_13(160-174)Online publication date: 12-Aug-2021
https://dl.acm.org/doi/10.1007/978-3-030-84522-3_13
Show More Cited By

Index Terms

An Efficient Cascaded Filtering Retrieval Method for Big Audio Data

Index terms have been assigned to the content through auto-classification.

Recommendations

An Efficient Cascaded Filtering Retrieval Method for Big Audio Data
BIGMM '15: Proceedings of the 2015 IEEE International Conference on Multimedia Big Data

Fast audio retrieval is crucial for many important applications and yet demanding due to the high dimension nature and increasingly larger volume of audios in the internet. Although audio fingerprinting can greatly reduce its dimension while keeping ...
A Two-Stage Audio Retrieval Method for Searching Unannotated Audio Clips
ISM '08: Proceedings of the 2008 Tenth IEEE International Symposium on Multimedia

Traditional audio retrieval systems deal principally with audio clips having text descriptions. To retrieve unannotated audio clips is cumbersome because of the immaturity of content-based analysis and retrieval techniques. In this paper, we propose a ...
Indexing and Retrieval of Audio: A Survey

With more and more audio being captured and stored, there is a growing need for automatic audio indexing and retrieval techniques that can retrieve relevant audio pieces quickly on demand. This paper provides a comprehensive survey of audio indexing and ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE Transactions on Multimedia

IEEE Transactions on Multimedia Volume 17, Issue 9

Sept. 2015

270 pages

ISSN:1520-9210

Issue’s Table of Contents

Copyright © 2015.

Publisher

IEEE Press

Publication History

Published: 01 September 2015

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 27 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Serrano SScarpa M(2023)Accuracy comparisons of fingerprint based song recognition approaches using very high granularityMultimedia Tools and Applications10.1007/s11042-023-14787-282:20(31591-31606)Online publication date: 21-Mar-2023
https://dl.acm.org/doi/10.1007/s11042-023-14787-2
Huang YWang YLi HZhang YZhang Q(2022)Encrypted speech retrieval based on long sequence BiohashingMultimedia Tools and Applications10.1007/s11042-022-12371-881:9(13065-13085)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1007/s11042-022-12371-8
Li TJia MCao X(2021)A Hierarchical Retrieval Method Based on Hash Table for Audio FingerprintingIntelligent Computing Theories and Application10.1007/978-3-030-84522-3_13(160-174)Online publication date: 12-Aug-2021
https://dl.acm.org/doi/10.1007/978-3-030-84522-3_13
Pouyanfar SYang YChen SShyu MIyengar S(2018)Multimedia Big Data AnalyticsACM Computing Surveys10.1145/315022651:1(1-34)Online publication date: 10-Jan-2018
https://dl.acm.org/doi/10.1145/3150226
Yao SNiu BLiu J(2017)Audio Identification by Sampling Sub-fingerprints and Counting MatchesIEEE Transactions on Multimedia10.1109/TMM.2017.272384619:9(1984-1995)Online publication date: 1-Sep-2017
https://dl.acm.org/doi/10.1109/TMM.2017.2723846
Liu SShao JLu H(2017)Generalized Residual Vector Quantization and Aggregating Tree for Large Scale SearchIEEE Transactions on Multimedia10.1109/TMM.2017.269218119:8(1785-1797)Online publication date: 1-Aug-2017
https://dl.acm.org/doi/10.1109/TMM.2017.2692181

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents