Skip to main content

Acoustic Event Detection: SVM-Based System and Evaluation Setup in CLEAR’07

  • Conference paper
Book cover Multimodal Technologies for Perception of Humans (RT 2007, CLEAR 2007)

Abstract

In this paper, the Acoustic Event Detection (AED) system developed at the UPC is described, and its results in the CLEAR evaluations carried out in March 2007 are reported. The system uses a set of features composed of frequency-filtered band energies and perceptual features, and it is based on SVM classifiers and multi-microphone decision fusion. Also, the current evaluation setup and, in particular, the two new metrics used in this evaluation are presented.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Temko, A., Malkin, R., Zieger, C., Macho, D., Nadeu, C., Omologo, M.: CLEAR Evaluation of Acoustic Event Detection and Classification systems. In: Stiefelhagen, R., Garofolo, J.S. (eds.) CLEAR 2006. LNCS, vol. 4122, pp. 311–322. Springer, Heidelberg (2007)

    Chapter  Google Scholar 

  2. CHIL - Computers In The Human Interaction Loop, http://chil.server.de/

  3. Temko, A., Macho, D., Nadeu, C., Segura, C.: UPC-TALP Database of Isolated Acoustic Events. Internal UPC report (2005)

    Google Scholar 

  4. Zieger, C., Omologo, M.: Acoustic Event Detection - ITC-irst AED database. Internal ITC report (2005)

    Google Scholar 

  5. Spring 2007 (RT-07) Rich Transcription Meeting Recognition Evaluation Plan, NIST (December 2007)

    Google Scholar 

  6. Temko, A., Nadeu, C.: AED Evaluation plan for CLEAR 2007 (February 2007)

    Google Scholar 

  7. Temko, A., Nadeu, C.: Classification of Acoustic Events using SVM-based Clustering Schemes. Pattern Recognition 39(4), 682–694 (2006)

    Article  MATH  Google Scholar 

  8. Schölkopf, B., Smola, A.: Learning with Kernels. MIT Press, Cambridge (2002)

    Google Scholar 

  9. Temko, A., Macho, D., Nadeu, C.: Enhanced SVM Training for Robust Speech Activity Detection. In: IEEE ICASSP 2007, Honolulu, Hawaii, USA (April 2007)

    Google Scholar 

  10. Platt, J., Cristianini, N., Shawe-Taylor, J.: Large Margin DAGs for Multiclass Classification. Proc. Advances in Neural Information Processing Systems 12, 547–553 (2000)

    Google Scholar 

  11. Segura, C., Abad, A., Hernando, J., Nadeu, C.: Multispeaker Localization and Tracking in Intelligent Environments. In: CLEAR 2007 Evaluation Campaign and Workshop, Baltimore MD, USA (May 2007)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Rainer Stiefelhagen Rachel Bowers Jonathan Fiscus

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Temko, A., Nadeu, C., Biel, JI. (2008). Acoustic Event Detection: SVM-Based System and Evaluation Setup in CLEAR’07. In: Stiefelhagen, R., Bowers, R., Fiscus, J. (eds) Multimodal Technologies for Perception of Humans. RT CLEAR 2007 2007. Lecture Notes in Computer Science, vol 4625. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68585-2_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-68585-2_34

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-68584-5

  • Online ISBN: 978-3-540-68585-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics