Skip to main content

Semantic Context Detection Using Audio Event Fusion


Semantic-level content analysis is a crucial issue in achieving efficient content retrieval and management. We propose a hierarchical approach that models audio events over a time series in order to accomplish semantic context detection. Two levels of modeling, audio event and semantic context modeling, are devised to bridge the gap between physical audio features and semantic concepts. In this work, hidden Markov models (HMMs) are used to model four representative audio events, that is, gunshot, explosion, engine, and car braking, in action movies. At the semantic context level, generative (ergodic hidden Markov model) and discriminative (support vector machine (SVM)) approaches are investigated to fuse the characteristics and correlations among audio events, which provide cues for detecting gunplay and car-chasing scenes. The experimental results demonstrate the effectiveness of the proposed approaches and provide a preliminary framework for information mining by using audio characteristics.


  1. 1.

    Lienhart RW: Comparison of automatic shot boundary detection algorithms. Storage and Retrieval for Image and Video Databases VII, January 1999, San Jose, Calif, USA, Proceedings of SPIE 3656: 290–301.

    Article  Google Scholar 

  2. 2.

    Hanjalic A: Shot-boundary detection: unraveled and resolved? IEEE Transactions on Circuits and Systems for Video Technology 2002, 12(2):90–105. 10.1109/76.988656

    Article  Google Scholar 

  3. 3.

    Chang S-F, Vetro A: Video adaptation: concepts, technologies, and open issues. Proceedings of the IEEE 2005, 93(1):148–158.

    Article  Google Scholar 

  4. 4.

    Lu L, Zhang H-J, Jiang H: Content analysis for audio classification and segmentation. IEEE Transactions Speech Audio Processing 2002, 10(7):504–516. 10.1109/TSA.2002.804546

    Article  Google Scholar 

  5. 5.

    Zhang T, Jay Kuo C-C: Hierarchical system for content-based audio classification and retrieval. Multimedia Storage and Archiving Systems III, November 1998, Boston, Mass, USA, Proceedings of SPIE 3527: 398–409.

    Article  Google Scholar 

  6. 6.

    Tzanetakis G, Cook P: Musical genre classification of audio signals. IEEE Transactions Speech Audio Processing 2002, 10(5):293–302. 10.1109/TSA.2002.800560

    Article  Google Scholar 

  7. 7.

    Lu L, Zhang H-J: Automated extraction of music snippets. Proc. 11th ACM International Conference on Multimedia, November 2003, Berkeley, Calif, USA 140–147.

    Google Scholar 

  8. 8.

    Fischer S, Lienhart R, Effelsberg W: Automatic recognition of film genres. Proc. 3rd ACM International Conference on Multimedia, November 1995, San Francisco, Calif, USA 295–304.

    Google Scholar 

  9. 9.

    Liu Z, Huang J, Wang Y: Classification of TV programs based on audio information using hidden Markov model. Proc. IEEE 2nd Workshop on Multimedia Signal Processing (MMSP '98), December 1998, Redonda Beach, Calif, USA 27–31.

    Google Scholar 

  10. 10.

    Wang Y, Liu Z, Huang J-C: Multimedia content analysis-using both audio and visual clues. IEEE Signal Processing Magazine 2000, 17(6):12–36. 10.1109/79.888862

    Article  Google Scholar 

  11. 11.

    Zettl H: Sight Sound Motion: Applied Media Aesthetics. Wadsworth, Belmont, Calif, USA; 1999.

    Google Scholar 

  12. 12.

    Dorai C, Venkatesh S: Media Computing: Computational Media Aesthetics. Kluwer Academic, Boston, Mass, USA; 2002.

    Book  Google Scholar 

  13. 13.

    Moncrieff S, Venkatesh S, Dorai C: Horror film genre typing and scene labeling via audio analysis. Proc. IEEE International Conference on Multimedia and Expo (ICME '03), July 2003, Baltimore, Md, USA 2: 193–196.

    Google Scholar 

  14. 14.

    Cai R, Lu L, Zhang H-J, Cai L-H: Highlight sound effects detection in audio stream. Proc. IEEE International Conference on Multimedia and Expo (ICME '03), July 2003, Baltimore, Md, USA 3: 37–40.

    Google Scholar 

  15. 15.

    Naphade MR, Kristjansson T, Frey B, Huang TS: Probabilistic multimedia objects (multijects): a novel approach to video indexing and retrieval in multimedia systems. Proc. International Conference on Image Processing (ICIP '98), October 1998, Chicago, Ill, USA 3: 536–540.

    Article  Google Scholar 

  16. 16.

    Naphade MR, Huang TS: Extracting semantics from audio-visual content: the final frontier in multimedia retrieval. IEEE Transactions on Neural Networks 2002, 13(4):793–810. 10.1109/TNN.2002.1021881

    Article  Google Scholar 

  17. 17.

    Smith JR, Naphade M, Natsev A: Multimedia semantic indexing using model vectors. Proc. IEEE International Conference on Multimedia and Expo (ICME '03), July 2003, Baltimore, Md, USA 2: 445–448.

    Google Scholar 

  18. 18.

    Hyvärinen A, Karhunen J, Oja E: Independent Component Analysis. John Wiley & Sons, New York, NY, USA; 2001.

    Book  Google Scholar 

  19. 19.

    Rabiner LR: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 1989, 77(2):257–286. 10.1109/5.18626

    Article  Google Scholar 

  20. 20.

    Duda RO, Hart PE, Stork DG: Pattern Classification. John Wiley & Sons, New York, NY, USA; 2001.

    MATH  Google Scholar 

  21. 21.

    Li SZ: Content-based audio classification and retrieval using the nearest feature line method. IEEE Transactions Speech Audio Processing 2000, 8(5):619–625. 10.1109/89.861383

    Article  Google Scholar 

  22. 22.

    Bow S-T: Pattern Recognition and Image Preprocessing. Marcel Dekker, New York, NY, USA; 2002.

    Book  Google Scholar 

  23. 23.

    Sound Ideas: Sound Effects Library

  24. 24.

    Zilca RD: Text-independent speaker verification using covariance modeling. IEEE Signal Processing Letters 2001, 8(4):97–99. 10.1109/97.911465

    Article  Google Scholar 

  25. 25.

    Vapnik VN: Statistical Learning Theory. John Wiley & Sons, New York, NY, USA; 1998.

    MATH  Google Scholar 

  26. 26.

    Platt JC, Cristianini N, Shawe-Taylor J: Large margin DAGs for multiclass classification. In Advances in Neural Information Processing Systems. Volume 12. MIT Press, Cambridge, Mass, USA; 2000:547–553.

    Google Scholar 

  27. 27.

    Hsu C-W, Lin C-J: A comparison of methods for multiclass support vector machines. IEEE Transactions Neural Networks 2002, 13(2):415–425. 10.1109/72.991427

    Article  Google Scholar 

  28. 28.

    Wang J, Xu C, Chng E, Tian Q: Sports highlight detection from keyword sequences using HMM. Proc. IEEE International Conference on Multimedia and Expo (ICME '04), June 2004, Taipei, Taiwan 1: 599–602.

    Google Scholar 

  29. 29.

    Naphade MR, Garg A, Huang TS: Audio-visual event detection using duration dependent input output Markov models. Proc. IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL '01), December 2001, Kauai, Hawaii, USA 39–43.

    Chapter  Google Scholar 

  30. 30.

    TREC Video Retrieval Evaluation

Download references

Author information



Corresponding author

Correspondence to Wei-Ta Chu.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

Chu, WT., Cheng, WH. & Wu, JL. Semantic Context Detection Using Audio Event Fusion. EURASIP J. Adv. Signal Process. 2006, 027390 (2006).

Download citation


  • Support Vector Machine
  • Content Analysis
  • Markov Model
  • Hide Markov Model
  • Quantum Information