Bimodal Recognition Experiments with Recurrent Neural Networks

A bimodal automatic speech recognition system, using
simultaneously auditory model and articulatory parameters, is
described. Results given for various speaker dependent
phonetic recognition experiments, regarding the Italian plosive
class, show the usefulness of this approach especially in noisy
conditions.

Publication type: 
Contributo in atti di convegno
Author or Creator: 
Cosi P.
Magno Caldognetto E.
Vagges K.
Mian G.A.
Contolini M.
Publisher: 
IEEE, New York, USA
Source: 
Proceedings IEEE ICASSP-94, International Conference on Acoustic Speech and Signal Processing, Adelaide, Australia, 19-22 April, 1994
Date: 
1994
Resource Identifier: 
http://www.cnr.it/prodotto/i/241569
https://dx.doi.org/10.1109/ICASSP.1994.389596
info:doi:10.1109/ICASSP.1994.389596
http://www.pd.istc.cnr.it/Papers/PieroCosi/cp-ICASSP94.pdf
urn:isbn:0-7803-1775-0
Language: 
Eng