Class-level spectral features for emotion recognition

  title={Class-level spectral features for emotion recognition},
  author={Dmitri Bitouk and Ragini Verma and Ani Nenkova},
  journal={Speech communication},
  volume={52 7-8},
The most common approaches to automatic emotion recognition rely on utterance level prosodic features. Recent studies have shown that utterance level statistics of segmental spectral features also contain rich information about expressivity and emotion. In our work we introduce a more fine-grained yet robust set of spectral features: statistics of Mel-Frequency Cepstral Coefficients computed over three phoneme type classes of interest-stressed vowels, unstressed vowels and consonants in the… CONTINUE READING
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 141 citations. REVIEW CITATIONS
83 Citations
34 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 83 extracted citations

142 Citations

Citations per Year
Semantic Scholar estimates that this publication has 142 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 34 references

Emotion recognition using mel-frequency cepstral coefficients

  • N. Sato, Y. Obuchi
  • Inf. Media Technol
  • 2007
Highly Influential
5 Excerpts

Improving emotion

  • D. Bitouk, A. Nenkova, R. Verma
  • expression. J. Personality Social Psychology
  • 2009
Highly Influential
1 Excerpt

Similar Papers

Loading similar papers…