A data-driven method for input feature selection within neural prosody generation

The analysis and selection of input features within machine learning techniques is an important problem if a new system has to be established or the system has to be trained for a new task. Within a Text-to-Speech (ITS) application this task has to be handled while adapting a system to a new language or a new speaker.

[1]  Arun D Kulkarni,et al.  Neural Networks for Pattern Recognition , 1991 .

[2]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[3]  Barbara Heuft,et al.  Prosody generation with a neural network: weighing the importance of input parameters , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Rüdiger Hoffmann,et al.  Data-driven importance analysis of linguistic and phonetic information , 2000, INTERSPEECH.

[5]  Martin Holzapfel,et al.  Optimization of a neural network for speaker and task dependent F/sub 0/-generation , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[6]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[7]  Rüdiger Hoffmann,et al.  Natural F0 contours with a new neural-network-hybrid approach , 2000, INTERSPEECH.