Phonetic Recognition Experiments with Recurrent Neural Networks

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:
/1311, /tSi/, /di/, /dZi/, ill, /pi/, /ti/, lvi/
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.

Publication type: 
Contributo in atti di convegno
Author or Creator: 
Cosi P.
Frasconi P.
Gori M.
Griggio N.
Publisher: 
Priority Printing, Edmonton, CAN
Source: 
Proceedings ICSLP-92, International Conference on Spoken Language Processing, pp. 1335–1338, Banff, Alberta, Canada, October 12-16, 1992
Date: 
1992
Resource Identifier: 
http://www.cnr.it/prodotto/i/241638
http://www.researchgate.net/publication/221478998_Phonetic_recognition_experiments_with_recurrent_neural_networks
urn:isbn:0-88864-806-5
Language: 
Eng
ISTC Author: 
Piero Cosi's picture
Real name: