Abstract
One of the components of the text-to-speech synthesis system is the database of sounds. Two Lithuanian diphone databases in the MBROLA format are presented in this paper. The list of phonemes and the list of diphones necessary for Lithuanian text-to-speech synthesis are described. The problem of phoneme combinations that are not used in the Lithuanian language is dealt with in the work. Also, the article is concerned with transcribing a Lithuanian text.
Highlights
In his previous articles (Kasparaitis, 2001a; Kasparaitis, 2001b) the present author described the Lithuanian text-to-speech synthesizer “Aistis” in which 480 phonetic units of various lengths were used: parts of phonemes, allophones, diphthongs and mixed diphthongs, most often consonants with the beginnings of vowels and allophones of vowels are made use of
8464 combinations may be built on the basis of 92 phonemes, it is impossible to have all the diphones made from these combinations in the Lithuanian language
The Project is aimed at creating a set of speech synthesizers and accumulating databases of speech sounds of as many languages as possible
Summary
In his previous articles (Kasparaitis, 2001a; Kasparaitis, 2001b) the present author described the Lithuanian text-to-speech synthesizer “Aistis” in which 480 phonetic units of various lengths were used: parts of phonemes, allophones, diphthongs and mixed diphthongs, most often consonants with the beginnings of vowels and allophones of vowels are made use of. This method has some disadvantages, the most important one being the problems related to changing the length of sounds. The transition points between the sounds are stored in the database, the duration of sounds can be calculated exactly
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have