; Iritel a.d. Beograd, Batajnički put 23, 11080 Beorgad, Serbia
; University of Novi Sad, Faculty of Technical Sciences, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
; University of Novi Sad, Faculty of Philosophy, Dr Zorana Đinđića 2, 21000 Novi Sad, Serbia
APA 6th Edition Sovilj-Nikić, S., Sovilj-Nikić, I. i Marković, M. (2018). Meta Learning Approach to Phone Duration Modeling. Tehnički vjesnik, 25 (3), 855-860. https://doi.org/10.17559/TV-20171002122930
MLA 8th Edition Sovilj-Nikić, Sandra, et al. "Meta Learning Approach to Phone Duration Modeling." Tehnički vjesnik, vol. 25, br. 3, 2018, str. 855-860. https://doi.org/10.17559/TV-20171002122930. Citirano 18.11.2019.
Chicago 17th Edition Sovilj-Nikić, Sandra, Ivan Sovilj-Nikić i Maja Marković. "Meta Learning Approach to Phone Duration Modeling." Tehnički vjesnik 25, br. 3 (2018): 855-860. https://doi.org/10.17559/TV-20171002122930
Harvard Sovilj-Nikić, S., Sovilj-Nikić, I., i Marković, M. (2018). 'Meta Learning Approach to Phone Duration Modeling', Tehnički vjesnik, 25(3), str. 855-860. https://doi.org/10.17559/TV-20171002122930
Vancouver Sovilj-Nikić S, Sovilj-Nikić I, Marković M. Meta Learning Approach to Phone Duration Modeling. Tehnički vjesnik [Internet]. 2018 [pristupljeno 18.11.2019.];25(3):855-860. https://doi.org/10.17559/TV-20171002122930
IEEE S. Sovilj-Nikić, I. Sovilj-Nikić i M. Marković, "Meta Learning Approach to Phone Duration Modeling", Tehnički vjesnik, vol.25, br. 3, str. 855-860, 2018. [Online]. https://doi.org/10.17559/TV-20171002122930
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.