Speaker independent bimodal phonetic recognition experiments

Author

Cosi, P. ; Caldognetto, E. Magno ; Ferrero, E. ; Dugatto, M. ; Vagges, K.

Author_Institution

Centro di Studio per la Richerche di Fonetica, CNR, Padova, Italy

Volume

1

fYear

1996

fDate

3-6 Oct 1996

Firstpage

54

Abstract

A speaker independent bimodal phonetic classification experiment regarding Italian plosive consonants is described. The phonetic classification scheme is based an a feedforward 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 specialized hardware, called ELITE, computing lip and jaw kinematics parameters

Keywords

backpropagation; feedforward neural nets; image recognition; multilayer perceptrons; natural language interfaces; pattern classification; recurrent neural nets; spectral analysis; speech recognition; ELITE; Italian plosive consonants; audio information; auditory model; bimodal phonetic recognition experiments; feedforward recurrent backpropagation neural network; jaw; kinematics parameters; lip; phonetic classification; speaker independent recognition; specialized hardware; spectral-like parameters; speech signal; visual information; visual signal; Acoustic noise; Degradation; Humans; Image processing; Kinematics; Petroleum; Robustness; Samarium; Speech enhancement; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607023

Filename

607023