A MULTI-LINEAR HMMs SYSTEM FEATURES EXTR

Abstract

In this paper we present a novel approach for articulatory features extraction. Our approach relies on an autosegmental multilinear representation of AFs. Overlap and precedence relations between AFs on the different levels of the multi-linear representation can be extracted and then presented to a phonological parser for further recognition. This… (More)

Topics

3 Figures and Tables

Slides referencing similar topics