Robust Feature Extraction for Mobile-Based Speech Emotion Recognition System

  • Kang-Kue Lee
  • Youn-Ho Cho
  • Kyu-Sik Park
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 345)


In this paper, we propose a robust feature extraction method for mobile-based speech emotion recognition system. A query speech signal is captured by a cellular phone in the real mobile environment. A major problem in this environment is distortions contained in the features of the query sound due to the mobile network and environmental noise. In order to alleviate these noises, a signal subspace noise reduction algorithm is applied. Then a robust feature extraction method called SFS feature optimization is implemented to improve and stabilize the system performance. The proposed system has been tested with cellular phones in the real world and it shows about 73% of average classification success rate with Fuzzy SVM classifier.


Speech Signal Emotion Recognition Cellular Phone Speech Emotion Sequential Forward Selection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dellaert, F., Polzin, T., Waibel, A.:Recognizing Emotion in Speech, In Proc. International Conf. on Spoken Language Processing (1996) 1970–1973Google Scholar
  2. 2.
    Scherer, K.R.:Adding the Affective Dimension: A New Look in Speech Anlysis and Synthesis, In Proc. International Conf. on Spoken Language Processing (1996) 1808–1811Google Scholar
  3. 3.
    Zhou, G., John, Hansen, James, H. L., Kaiser, F.:Nonlinear Feature Based Classification of Speech Under Stress, IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, VOL. 9, NO. 3, MARCH (2001)Google Scholar
  4. 4.
    Kostov, V., Fukuda, S.:Emotion in User lnterface, Voice Interaction system, IEEE Intl Conf. on systems, Man, Cybernetics Representation, no. 2 (2000) 798–803Google Scholar
  5. 5.
    Oriyama, T. M., Oazwa.:Emotion Recognition and Synthisis System on Speech, IEEE Intl. Conference on Multimedea Computing and Systems (1999) 840–844Google Scholar
  6. 6.
    Lee, C. M., Narayanan, S., Pieraccin, i R.:Classifying Emotions in Human-machine Spoken Dialogs, ICME’02 (2002)Google Scholar
  7. 7.
    Shigeo Abe, Takuya Inoue.: Fuzzy Support Vector Machines for Multiclass Problems”ESANN’2002 proceedings-European Symposium on Artificial Neural Networks, Bruges (Belgium), 24–26 April 2002, d-side publi., ISBN 2-930307-02-1, 113–118Google Scholar
  8. 8.
    Anil K. Jin, Robert P.W. Duin, Jianchang Mai.:Statistical Pattern Recognition: A Review IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 1, Jan (2000)Google Scholar
  9. 9.
    Ephraim, Y.:A signal subspace approach for speech enhancement, IEEE Transactions on Speech and Audio Processing, vol. 3, no. 4,. July (1995) 251–266Google Scholar
  10. 10.
    Ross, M.J., Shaer, H.L., Cohen, A., Freudberg, R., Manley, H. J.:Average Magnitude Dierence Function Pitch Extractor, ASSP-22:, Oct (1974) 353–362Google Scholar
  11. 11.
    Noll, M.: Pitch Determination of Human Speech by the Harmonic Product Spectrum, the Harmonic Sum Spectrum, and a Maximum Likelihood Estimate. In Proceedings of the Symposium on Computer Processing Communications (1969) 779–797Google Scholar
  12. 12.
    Xuejing Sun.:A Pitch Determination Algorithm Based On Subharmonic-toHarmonic Ratio, ICSLP (2000) 676–679Google Scholar
  13. 13.
    Liu, M., Wan, C.:A study on Content-based Classification Retrieval of Audio Database, Proc. of the International Database Engineering & Applications Symposium (2001) 339–345Google Scholar
  14. 14.
    Kang, Bong-Seok.:A Text-independent Emotion Recognition Algorithm Using Speech Signal, Yonsei University (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kang-Kue Lee
    • 1
  • Youn-Ho Cho
    • 1
  • Kyu-Sik Park
    • 1
  1. 1.Division of Information and Computer ScienceDankook UniversitySeoulKorea

Personalised recommendations