4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Speaker Independent Bimodal Phonetic Recognition Experiments

Piero Cosi (1), E. Magno Caldognetto (1), Franco Ferrero (1), M. Dugatto (2), K. Vagges (1)

(1) Centro di Studio per le Ricerche di Fonetica (CNR), Padova, Italy
(2) UniversitÓ di Padova, Dipartimento di Elettronica ed Informatica, Padova, Italy

A speaker independent bimodal phonetic classification experiment regarding the Italian plosive consonants is described. The phonetic classification scheme is based on a feed forward recurrent back-propagation neural network working on audio and visual information. The speech signal is processed by an auditory model producing spectral-like parameters, while the visual signal is processed by a specialized hardware, called ELITE, computing lip and jaw kinematics parameters.

Full Paper

Bibliographic reference.  Cosi, Piero / Caldognetto, E. Magno / Ferrero, Franco / Dugatto, M. / Vagges, K. (1996): "Speaker independent bimodal phonetic recognition experiments", In ICSLP-1996, 54-57.