A bimodal automatic speech recognition system, in which the speech signal is synchronously analyzed by an audio channel producing spectral-like parameters every 2 ms and by a visual channel computing lip and jaw kinematic parameters, is described and some results are given for various speaker independent phonetic recognition experiments regarding the Italian plosive class in different noisy conditions.
Bimodal Recognition of Italian Plosives
Cosi P;
1995
Abstract
A bimodal automatic speech recognition system, in which the speech signal is synchronously analyzed by an audio channel producing spectral-like parameters every 2 ms and by a visual channel computing lip and jaw kinematic parameters, is described and some results are given for various speaker independent phonetic recognition experiments regarding the Italian plosive class in different noisy conditions.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
