DocumentCode
2330896
Title
Improving text-to-speech synthesis
Author
Tatham, Mark ; Lewis, Eric
Author_Institution
Dept. of Language & Linguistics, Essex Univ., Colchester, UK
Volume
3
fYear
1996
fDate
3-6 Oct 1996
Firstpage
1856
Abstract
Naturalness in human speech is dependent on a number of factors and the extent to which a text to speech synthesis system can account for these factors in its model will be a measure of its success in the marketplace. As well as the obvious factors of rhythm and intonation, there is the more difficult question of modelling the variability in human speech. The paper discusses how SPRUCE (E. Lewis and M.A.A. Tatham, 1991), a high level text to speech synthesis system, incorporates several different types of variability
Keywords
modelling; natural languages; speech synthesis; SPRUCE; high level text to speech synthesis; human speech; text to speech synthesis system; variability modelling; Acoustic waves; Computer science; Context modeling; Dictionaries; Humans; Information analysis; Natural languages; Rhythm; Speech analysis; Speech synthesis;
fLanguage
English
Publisher
ieee
Conference_Titel
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location
Philadelphia, PA
Print_ISBN
0-7803-3555-4
Type
conf
DOI
10.1109/ICSLP.1996.607993
Filename
607993
Link To Document