Segmental duration control by time delay neural networks with asymmetric causal and retro-causal information flows

@inproceedings{Erdem2002SegmentalDC,
  title={Segmental duration control by time delay neural networks with asymmetric causal and retro-causal information flows},
  author={Çaglayan Erdem and Hans-Georg Zimmermann},
  booktitle={ESANN},
  year={2002}
}
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 are presented which can be used for the modeling of dynamical systems Within the prosody prediction task left and right context information is known to in uence the prediction of prosody control parameters This can be modeled by causal retro causal information ows Since… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-5 of 5 references

Grothmann: Modeling of Dynamical Systems by Error Correction Neural Networks, in: A. Sooo and L. Cao eds.], Modeling and Forecasting Financial Data

  • H G Zimmermann, R Neuneier
  • ESANN'2002 proceedings -European Symposium on…
  • 2000

M uller, C a glayan Erdem, and R udiger Hoomann : prosody generation by causal retro-causal error correction neural networks

  • H.-G Zimmermann, F Achim
  • M uller, C a glayan Erdem, and R udiger Hoomann…
  • 2000

Campbell: Syllable-based segmental duration in

  • Talking Machines: Theories, Models and Designs
  • 1992

Learning internal representations by error propagation

  • D E Rumelhart, G E Hinton, R J Williams
  • Parallel Distributed P r ocessing: Explorations…
  • 1986

Review of text-to-speech c o n version for

  • D Klatt
  • English Journal of the Acoustical Society of…

Similar Papers

Loading similar papers…