Comparative Analysis of Pitch and Formant for Recognizing Emotions of Isolated Marathi Speech

@inproceedings{Rabiner2016ComparativeAO,
  title={Comparative Analysis of Pitch and Formant for Recognizing Emotions of Isolated Marathi Speech},
  author={Lawrence R. Rabiner and Ming Jen Cheng and Andrew Eric Rosenberg and Manu Sondhi and Yi Kechu and Tian Fu and Fu Qiang and “YU YIN and Xianghua Chu and Shashidhar G. Koolagudi and Chih-Hsien Huang and Cheng-Hung Tsai},
  year={2016}
}
Recognizing emotions from speech is a tuff task as we are not aware of the features which will accurately classify the emotions. This paper is an approach to show which speech feature classifies the emotions more accurately. The features compared here are Pitch and Formant while the classifier used is Linear Discriminant Analysis (LDA). The database used in this experiment was developed using 50 male and 50 female Marathi speaking native speakers. The emotions used here are Neutral, Happy, Sad… CONTINUE READING

From This Paper

Topics from this paper.

References

Publications referenced by this paper.
Showing 1-5 of 5 references

Li”The Corpus Preparation and Effective Feature Representation of Emotional Speech,

Chih-Hsien Huang, Cheng-Hung Tsai, Bo-Yi
Fourth International Conference on Innovative Computing, Information and Control • 2009

New methods of pitch extraction,

M. M. Sondhi
IEEE Trans.Audio Electroacoust., • 1968