Linguistically motivated parameter estimation methods for a superpositional intonation model

TORRES, H.M, GURLEKIAN, JA, MIXDORFF H AND PFITZINGER H.. Y TORRES, M.E.

EURASIP ASMP

Springer-Verlag

Lugar: Heidelberg; Año: 2013

1687-4722

This paper proposes two novel approaches for parameter estimation of the super-positional intonation model. These approaches present linguistic and paralinguistic assumptions allowing the initialization of a previous standard method. Additionally, all restrictions on the configuration of accents were eliminated. The proposed linguistic hypotheses can be based on either tonal or lexical accent, which gives rise to two different estimation methods. These two kind of hypotheses were validated by comparison of the estimation performance relative to two standard methods, one manual and one automatic. The results of the experiments for German, English and Spanish corpora, show that the proposed methods outperforms the standard ones.