Emotion in concatenated speech

The results of preliminary attempts to add emotion to concatenative synthetic speech, intially using techniques applied to format synthesis, were presented. A new intonation contour was applied to the concatenated segments during production of the final audible utterance. The available synthesis parameters were systematically modified to increase the affective content. The output digital speech samples were subjected to the manipulation with a waveform editing package, to produce the final output utterance. The prototype rule-based implementations has produced which allow automatic production of emotional utterances. A pilot listening experiment, to compare the hand-edited and automatic phrases with the format-based synthesis has been conducted.