In order to prove the potential power of "learning by examples" paradigm for problems of Automatic Speech Recognition, an experiment was set up, regarding an extremely difficult Italian phonetic recognition problem: the automatic discrimination of the so called Italian alphabet i-set: /bi/, /tSi/, /di/, /dZi/, /!/, /pi/, /ti/, NM plus other two i-like stimuli /LI/, /si/. The achieved speaker independent mean recognition rate was around 65%, but either better results are expected at the end of the experiments going on.
Cite as: Cosi, P., Frasconi, P., Gori, M., Griggio, N. (1992) Phonetic recognition experiments with recurrent neural networks. Proc. 2nd International Conference on Spoken Language Processing (ICSLP 1992), 1335-1338, doi: 10.21437/ICSLP.1992-358
@inproceedings{cosi92_icslp,
author={Piero Cosi and P. Frasconi and M. Gori and N. Griggio},
title={{Phonetic recognition experiments with recurrent neural networks}},
year=1992,
booktitle={Proc. 2nd International Conference on Spoken Language Processing (ICSLP 1992)},
pages={1335--1338},
doi={10.21437/ICSLP.1992-358}
}