Computación y Sistemas
versão impressa ISSN 1405-5546
NUNEZ CUADRA, Oneisys e CALVO DE LARA, José Ramón. A New Phono-Articulatory Feature Representation for Language Identification in a Discriminative Framework. Comp. y Sist. [online]. 2011, vol.15, n.1, pp.107-115. ISSN 1405-5546.
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 pho-no-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.
Palavras-chave : Phonetic features; articulatory features; language recognition and support vector machines.