Emotion Conversion Of Speech Signal Using Neural Network
We investigate a neural network approach to transform source emotion to target emotion. We achieve this emotion
transformation by changing prosodic parameters (such as duration, pitch and intensity) learnt from the target emotion onto
the neutral emotion. Mapping techniques are used for transformation of one emotion to another emotion. We then use an
Artificial Neural Network (ANN) to learn the mapping between the neutral speech signal and the target speech signal and
performed the emotion transformation.