DocumentCode
3063197
Title
Subjective assessment of text to speech synthesis systems for the Serbian language
Author
Pakoci, Edvin ; Mak, Rudolf ; Ostrogonac, Stevan
Author_Institution
AlfaNum Speech Technol., Novi Sad, Serbia
fYear
2012
fDate
20-22 Nov. 2012
Firstpage
732
Lastpage
735
Abstract
This paper gives a short overview of contemporary text to speech (TTS) systems available for the Serbian language and then presents the results of subjective assessment tests of the quality of synthesized speech generated with these methods. Its main goal is to show the improvement in resulting speech quality obtained using the new hidden Markov model based (HMM-based) speech synthesis system for Serbian.
Keywords
hidden Markov models; natural language processing; speech synthesis; HMM-based speech synthesis system; Serbian language; TTS systems; contemporary text to speech systems; hidden Markov model based speech synthesis system; speech quality; subjective assessment tests; text to speech synthesis systems; Databases; Educational institutions; Hidden Markov models; Human voice; Speech; Speech synthesis; Synthesizers; Serbian; evaluation; hidden Markov models; speech synthesis;
fLanguage
English
Publisher
ieee
Conference_Titel
Telecommunications Forum (TELFOR), 2012 20th
Conference_Location
Belgrade
Print_ISBN
978-1-4673-2983-5
Type
conf
DOI
10.1109/TELFOR.2012.6419312
Filename
6419312
Link To Document