DocumentCode
2267797
Title
Recent progress in automatic text-to-speech synthesis
Author
Shaughnessy, Douglas O.
Author_Institution
INRS-Telecommun., Quebec Univ., Nuns Island, Que., Canada
fYear
1993
fDate
16-18 Aug 1993
Firstpage
1527
Abstract
Automatic text-to-speech systems have existed for several languages for some time now, which yield intelligible but unnatural synthetic speech. Quality imperfections are usually due to inadequate modeling of human speech production in coarticulation, intonation, and vocal-tract excitation. The author examines current approaches and progress in these areas and discusses the compromises that are often made
Keywords
speech synthesis; voice equipment; automatic text-to-speech synthesis; coarticulation; human speech modelling; intonation; quality imperfections; synthetic speech; vocal-tract excitation; Business; Frequency; Humans; Natural languages; Shape control; Speech analysis; Speech processing; Speech synthesis; Synthesizers; Vocoders;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location
Detroit, MI
Print_ISBN
0-7803-1760-2
Type
conf
DOI
10.1109/MWSCAS.1993.343406
Filename
343406
Link To Document