Phonetic Recognition by Recurrent Neural Networks Working on Audio and Visual Information

A phonetic classification scheme based on a feed forward recurrent back-propagation neural network working on audio and visual information is described. The speech signal is processed by an auditory model producing spectral-like parameters, while the visual signal is processed by a specialised hardware, called ELITE, computing lip and jaw kinematics parameters. Some results will be given for various speaker dependent and independent phonetic recognition experiments regarding the Italian plosive consonants.

Tipo Pubblicazione: 
Articolo
Author or Creator: 
Cosi P.
Dugatto M.
Ferrero F.
Magno Caldognetto E.
Vagges K.
Publisher: 
North-Holland, Amsterdam , Paesi Bassi
Source: 
Speech communication (Print) 19 (1996): 245–252. doi:10.1016/0167-6393(96)00034-9
info:cnr-pdr/source/autori:Cosi P., Dugatto M., Ferrero F., Magno Caldognetto E., Vagges K./titolo:Phonetic Recognition by Recurrent Neural Networks Working on Audio and Visual Information/doi:10.1016/0167-6393(96)00034-9/rivista:Speech communication (Pri
Date: 
1996
Resource Identifier: 
http://www.cnr.it/prodotto/i/210272
https://dx.doi.org/10.1016/0167-6393(96)00034-9
info:doi:10.1016/0167-6393(96)00034-9
http://www.sciencedirect.com/science/article/pii/0167639396000349
Language: 
Eng
ISTC Author: 
Ritratto di Piero Cosi
Real name: