Fourth ISCA ITRW on Speech Synthesis
August 29 - September 1, 2001
The generation of pleasant prosody parameters is Very important for speech synthesis. A prosody generation unit can be seen as a dynamical system. In this paper sophisticated time-delay recurrent neural network (NN) topologies arc presented which can be used for the modeling of dynamical systems. Within the prosody prediction task lefi and right context information is known to influence the prediction of prosody control parameters. This can be modeled by causal-retro-causal information flows , Since information being available during training is partially unavailable during application, there is a structural switching from training to application. This structural change of the information flow is handled by two asymmetric architectures.
These proposed new architectures allow the integration of flir- ther a priori knowledge. By this we are able to improve the performance of our duration control unit within our text-to-speech (TTS) system Papageno.
Bibliographic reference. Erdem, Caglayan / Zimmermann, Hans-Georg (2001): "Segmental duration control with asymmetric causal retro-causal neural networks", In SSW4-2001, paper 119.