Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge
Abstract
We attempt to combine neural networks with knowledge from speech science to build a speaker independent speech recogni(cid:173) tion system. This knowledge is utilized in designing the preprocessing, input coding, output coding, output supervision and architectural constraints. To handle the temporal aspect of speech we combine delays, copies of activations of hidden and output units at the input level, and Back-Propagation for Sequences (BPS), a learning algorithm for networks with local self-loops. This strategy is demonstrated in several experi(cid:173) ments, in particular a nasal discrimination task for which the application of a speech theory hypothesis dramatically im(cid:173) proved generalization.
Cite
Text
Bengio et al. "Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge." Neural Information Processing Systems, 1989.Markdown
[Bengio et al. "Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/bengio1989neurips-speaker/)BibTeX
@inproceedings{bengio1989neurips-speaker,
title = {{Speaker Independent Speech Recognition with Neural Networks and Speech Knowledge}},
author = {Bengio, Yoshua and de Mori, Renato and Cardin, Régis},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {218-225},
url = {https://mlanthology.org/neurips/1989/bengio1989neurips-speaker/}
}