This research is to recognize the state of emotions in speech using Hopfield technique. Speech is uttered by 30 persons who are the speakers selected for this project and being given by five sentences. The Hopfield Neural Network (HFNN) is an algorithm. The primary objective of this project is to develop ANN model to classify the collected voice data into two emotional states, happiness and anger. Several approach and methodology have been introduced in order to achieve the objectives. This project needs more revision and studies to obtain the accuracy in recognizing the emotion through speech.

1. Prof. Arun Kulkarni, Prof. Sujata Pathak,"Multimodal approaches for emotional features in speech: A survey", Proc . of EC2IT, KJSCE, Mumbai, pp. 155-160, March 2009.
2. Berlin Emotional Speech Database. http://pascal. kgw. tu-erlin. de/emodb/index-1024. html109
3. Cowie, E. Douglas-Cowie, N. Tsapatsoulis, G. Votsis, S. Kollias, W. Fellenz, and J. Taylor, "Emotion recognition in human-computer interaction," Signal Processing Magazine, IEEE, vol. 18, no. 1, Jan 2001
4. Aishah, A. R. , Komiya, R. , "A Preliminary Study of Emotion Extraction from Voice," National Conference on Computer Graphics and Multimedia (CoGRAMM'02), Malacca.
5. Rabiner, L. R. and Schafer, . W. (1978). Digital Processing of Speech Signals, Prentice-Hall, Eaglewood Cliffs, NJ.

Emotions lpc neuralnetwork (hfnn)