Abstract
This paper describes a scheme for the rule synthesis of speech in which words spoken in isolation were spliced after they were modified by rule. The input to this scheme consists of a typed text accompanied by phrase boundary information. The words spoken in isolation were recorded and analyzed into parameters from which these words can be synthesized after they have been modified. These modifications consisted of (1) a compression of word duration appropriate for continuous speech: however, the same shortened duration is used in all contexts; (2) minimal changes for amplitude and between-word coarticulation; and (3) pitch determined by context-dependent pitch rules. Pitch rules have been developed to deal with complex sentences whose phrase structure is known. The resulting paragraph is played as an example of the quality of synthetic speech.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.