Evaluation of Various Linear Prediction Parametric Representations in Vowel Recognition

Several alternate linear prediction parametric representations are experimentally compared as to their vowel recognition performance. The speech data used for this purpose consist of 900 utterances of 10 different vowels spoken by 3 speakers in a/b/-vowel-/b/context. The cepstral coefficients representation is found to be the best linear prediction parametric representation. ~chantillons de 10 voyelles diff~.rentes prononc~es par 3 locuteurs dans le contexte/b/voyelle/b/. Les coefficients cepstraux se r~v~lent les meilleurs param~tres, suivis par les coefficients de la r~ponse impulsionnelle du filtre auto-r~gressif.