A New Phono-Articulatory Feature Representation for Language Identification in a Discriminative Framework

Abstract

Abstract. State of the Art language identification methods are based on acoustic or phonetic features. Recently, phono-articulatory features have been included as a new speech characteristic that conveys language information. Authors propose a new phono- articulatory representation of speech in a discriminative framework to identify languages. This simple representation shows good results discriminating between English and Spanish, using a reduced training set of phono-articulatory trigrams vectors.