This article is cited in 2 papers

Theoretical foundations of computer science

Tonal languages speech synthesis using an indirect pitch markers and the quantitative target approximation methods

T. Y. Thai^a, H. N. Huy^b, D. V. Tuyet^cd, S. V. Ablameyko^d, D. V. Hoa^e, N. V. Hung<sup>e

a</sup> Hanoi University of Business and Technology, 29A Vinh Tuy Street, Vinh Tuy Ward, Hai Ba Trung Dist, Hanoi, Vietnam
^b Electric Power University, Vietnam Ministry of Industry and Trade, 235 Hoang Quoc Viet Street, Co Nhue, Tu Liem, Hanoi 129823, Vietnam
^c Binh Duong University, 504 Binh Duong Avenue, Thu Dau Mot Town 820000, Binh Duong Province, Vietnam
^d Belarusian State University, 4 Niezaliežnasci Avenue, Minsk 220030, Belarus
^e Military Institute of Science and Technology, 17 Hoang Sam Street, Nghia Do Ward, Cau Giay District, Hanoi, Vietnam

Abstract: Synthesizing tones plays an important role in text-to-speech systems of tonal languages. To accomplish this, the two important steps are to determine the pitch markers of voice utterances and synthesize $F_{0}$ trajectories for lexical tones. In this paper, we propose two efficient algorithms, one of them is to locate the pitch markers at the peaks of the cumulative signal of each voiced part of the input utterance and the other is to generate $F_{0}$ trajectories of tones with quantitative target approximation ($qTA$) parameters of $Xu$ model. The experimentation has shown that the proposed algorithms present pitch markers with high accuracy which has enabled us to generate tones with complex shapes

Keywords: pitch markers; cumulative signal; $Xu$ model; $qTA$; polynomial approximation.

UDC: 681.3

Received: 04.09.2019

Language: English

DOI: 10.33581/2520-6508-2019-3-105-121