Tehnički vjesnik, Vol. 25 No. 3, 2018.
Izvorni znanstveni članak
https://doi.org/10.17559/TV-20171002122930
Meta Learning Approach to Phone Duration Modeling
Sandra Sovilj-Nikić
orcid.org/0000-0001-7710-3014
; Iritel a.d. Beograd, Batajnički put 23, 11080 Beorgad, Serbia
Ivan Sovilj-Nikić
; University of Novi Sad, Faculty of Technical Sciences, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
Maja Marković
; University of Novi Sad, Faculty of Philosophy, Dr Zorana Đinđića 2, 21000 Novi Sad, Serbia
Sažetak
One of the essential prerequisites for achieving the naturalness of synthesized speech is the possibility of the automatic prediction of phone duration, due to the high importance of segmental duration in speech perception. In this paper we present a new phone duration prediction model for the Serbian language using meta learning approach. Based on the data obtained from the analysis of a large speech database, we used a feature set of 21 parameters describing phones and their contexts. These include attributes related to the segmental identity, manner of articulation (for consonants), attributes related to phonological context, such as segment types and voicing values of neighboring phones, presence or absence of lexical stress, morphological attributes, such as part-of-speech, and prosodic attributes, such as phonological word length, the position of the segment in the syllable, the position of the syllable in a word, the position of a word in a phrase, phrase break level, etc. Phone duration model obtained using meta learning algorithm outperformed the best individual model by approximately 2,0% and 1,7% in terms of the relative reduction of the root-mean-squared error and the mean absolute error, respectively.
Ključne riječi
machine learning; meta learning algorithm; phone duration model; synthesized speech
Hrčak ID:
202631
URI
Datum izdavanja:
28.6.2018.
Posjeta: 1.701 *