ISSN 0021-3454 (print version)
ISSN 2500-0381 (online version)
Menu

3
Issue
vol 60 / MARCH, 2017
Article
UDC 81'322.6

STATISTICAL METHODS FOR AUTOMATIC PROSODIC BREAK DETECTION IN A TEXT-TO-SPEECH SYSTEM

P. . Chistikov
«Speech Technologies Center», Ltd.; scientific researcher


O. G. Khomitsevich
STC Ltd., St. Petersburg; Senior Scientist


S. V. Rybin
STC Ltd., St. Petersburg; ITMO University, Department of Speech Information Systems; Leading Programmer; Associate Professor


Abstract. Application of statistical methods for predicting positions and durations of prosodic breaks in a text-to-speech system is proposed. The methods are shown to ensure better results as compared with a baseline rule-based system.
Keywords: prosodic breaks, prosodic boundaries, pauses, speech synthesis, statistical models