Data-driven importance analysis of linguistic and phonetic information
Lists
Only you see this
Abstract
In this paper the weight decay concept known from neural network theory is applied to the two modules involved in prosody generation within our text-to-speech system Papageno. Both modules are based on neural networks (NN). Preprocessing layers are inserted connected to the inputs of specialized NN architectures via diagonal weight matrices. The weight decay concept is applied to the weights of these diagonal weight matrices. This allows an importance analysis of the used input parameters in the context of the ised NN architectures.
BibTeX
@inproceedings{muller2000data,
author = {Achim F. Müller and Jianhua Tao and Rüdiger Hoffmann},
title = {{Data-driven importance analysis of linguistic and phonetic information}},
booktitle = {Interspeech},
year = {2000},
url = {https://openreview.net/forum?id=lQhTxXht2T},
}Loading related content...