A Preliminary Study of Acoustic Events Classification with Factor Analysis in Meeting Rooms

  • Diego Castán
  • Alfonso Ortega
  • Antonio Miguel
  • Eduardo Lleida
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8854)


The classification of acoustic events is useful to describe the scene and can contribute to improve the robustness of different speech technologies. However, the events are usually overlapped with speech or other sounds. This work proposes an approach based on Factor Analysis to compensate the variability of the acoustic events due to overlap with speech. The system is evaluated in the CLEAR evaluation database composed of recordings in meeting rooms where the acoustic events have been spontaneously generated in five different locations. The experiments are divided in two sets. Firstly, isolated acoustic events are used as development to analyze and evaluate parameters of the Factor Analysis system. Secondly, the system is compared to a baseline based on Gaussians Mixture Models with Hidden Markov Models. The Factor Analysis approach improves the total error rate due to the variability compensation of overlapped segments.


Acoustic Events Factor Analysis Meeting Rooms CLEAR Evaluation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Atrey, P.K., Maddage, N.C., Kankanhalli, M.S.: Audio Based Event Detection for Multimedia Surveillance. In: 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, pp. V–813–V–816 (2006)Google Scholar
  2. 2.
    Chen, J., Zhang, J., Kam, A.H., Shue, L.: An Automatic Acoustic Bathroom Monitoring System. In: 2005 IEEE International Symposium on Circuits and Systems, pp. 1750–1753 (2005)Google Scholar
  3. 3.
    van Hout, J., Akbacak, M., Castan, D., Yeh, E., Sanchez, M.: Extracting Spoken and Acoustic Concepts For Multimedia Event Detection. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 2–6 (2013)Google Scholar
  4. 4.
    Huang, Z., Cheng, Y.-C., Li, K., Hautamaki, V., Lee, C.-H.: A Blind Segmentation Approach to Acoustic Event Detection Based on I-Vector. In: Proc. Interspeech, pp. 2282–2286 (August 2013)Google Scholar
  5. 5.
    Castan, D., Akbacak, M.: Indexing Multimedia Documents with Acoustic Concept Recognition Lattices. In: Interspeech, pp. 3–7 (2013)Google Scholar
  6. 6.
    Temko, A., Malkin, R., Zieger, C., Macho, D.: Acoustic event detection and classification in smart-room environments: Evaluation of CHIL project systems. IV Jornadas en Tecnología del Habla, 1–6 (2006)Google Scholar
  7. 7.
    Zhou, X., Zhuang, X., Liu, M., Tang, H., Hasegawa-Johnson, M., Huang, T.: HMM-based acoustic event detection with AdaBoost feature selection. In: Stiefelhagen, R., Bowers, R., Fiscus, J. (eds.) RT 2007 and CLEAR 2007. LNCS, vol. 4625, pp. 345–353. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  8. 8.
    Butko, T., Camprubí, C.N.: Detection of overlapped acoustic events using fusion of audio and video modalities. In: Proc. FALA, pp. 165–168 (2010)Google Scholar
  9. 9.
    Chakraborty, R.: Acoustic Event Detection and Localization using Distributed Microphone Arrays. PhD thesis (2013)Google Scholar
  10. 10.
    Temko, A., Macho, D., Nadeu, C., Segura, C.: UPC-TALP Database of Isolated Acoustic Events. In: Internal UPC report (2005)Google Scholar
  11. 11.
    Kenny, P., Boulianne, G., Ouellet, P., Dumouchel, P.: Joint Factor Analysis Versus Eigenchannels in Speaker Recognition. IEEE Trans. Audio Speech Lang. 15(4), 1435–1447 (2007)CrossRefGoogle Scholar
  12. 12.
    Castan, D., Ortega, A., Villalba, J., Miguel, A., Lleida, E.: Segmentation-By-Classification System Based on Factor Analysis. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Diego Castán
    • 1
  • Alfonso Ortega
    • 1
  • Antonio Miguel
    • 1
  • Eduardo Lleida
    • 1
  1. 1.ViVoLab, Aragon Institute of Engineering Research (I3A)University of ZaragozaSpain

Personalised recommendations