Computational Model of Speech Understanding

D.N. Müller, and P.O.A. Navaux (Brazil)


Connectionist Models, Natural Language Processing, Human-Computer Interfaces, Spoken Language Under standing.


This paper proposes a speech comprehension computa tional model based on neurocognitiveresearches. The com putational representation uses techniques as wavelets trans form and connectionist models. The speech signal codifica tion and data prosodic extraction are derived from wavelet coefficients. Moreover, the connectionist models are used to perform syntactic parsing and prosodic-semantic map ping. Thus, the computational model applies three ap proaches: the application of wavelet coefficients as input in connectionist language analysis, the use of SARDSRN RAAM system to syntactic analysis as well as the proposi tion of prosodic-semantic maps to language contexts defi nition.

Important Links:

Go Back