Automatic recognition of speech emotion using long-term spectro-temporal features

  title={Automatic recognition of speech emotion using long-term spectro-temporal features},
  author={Siqing Wu and T. H. Falk and Wai-Yip Chan},
  journal={2009 16th International Conference on Digital Signal Processing},
This paper proposes a novel feature type for the recognition of emotion from speech. The features are derived from a long-term spectro-temporal representation of speech. They are compared to short-term spectral features as well as popular prosodic features. Experimental results with the Berlin emotional speech database show that the proposed features outperform both types of compared features. An average recognition accuracy of 88.6% is achieved by using a combined proposed & prosodic feature… CONTINUE READING
Highly Cited
This paper has 36 citations. REVIEW CITATIONS
20 Citations
21 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 20 extracted citations


Publications referenced by this paper.
Showing 1-10 of 21 references

Feature set search algorithms

  • J. Kittler
  • Pattern Recognition and Signal Processing, pp. 41…
  • 1978
Highly Influential
4 Excerpts

An evaluation of the robustness of existing supervisedmachine learning approaches to the classification of emotions in speech

  • M. Shami andW. Verhelst
  • Speech Communication, vol. 49, pp. 201–212, 2007.
  • 2007
3 Excerpts

Classifier fusion for emotion recognition from speech

  • S. Scherer, F. Schwenker, G. Palm
  • 3rd IET International Conference on Intelligent…
  • 2007
1 Excerpt

Similar Papers

Loading similar papers…