Prosody analysis and modeling for emotional speech synthesis

Current concatenative Text-to-Speech systems can synthesize varied emotions, but the subtle and range of the results are limited because large amount of emotional speech data are required. This paper studies a more flexible approach based on analyzing and modeling the emotional prosody features. Perceptual tests are first performed to investigate whether just manipulating prosody features can attain the communication purposes of emotions. Then, based on the positive results, the same corpus with sufficient prosody coverage is shared by different emotions in unit selection. Finally, an adaptation algorithm is proposed to predict the emotional prosody features. It models the prosodic variations by linguistic cues and emotion cues separately, and requires only a small amount of data. Experiments on Mandarin show that the adaptation algorithm can obtain appropriate emotional prosody features, and at least several emotions can be synthesized without the use of special emotional corpus.