Abstract
Speech recognition and synthesis are among well-known applications of neural networks. In speech synthesis the main efforts so far have been to master the complex grapheme-to-phoneme transforms that are needed e.g. in English as a part of speech synthesis by rule. There are relatively few attempts of more comprehensive formulations of speech synthesis on the basis of neural nets. This paper concentrates on the generation of prosodic feature parameters, related to intonation, stress and timing, by using neural net methodology. The main emphasis is on the novel use of existing and well-known network principles to gain practical and easy implementations of the ideas. Preliminary experiments are reported to show the feasibility of the approach.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
