Abstract
A long-standing problem of monotonicity in naturalness has been solved using a well-founded model, namely the Speech Hierarchy Model. This model is based on the fact that all natural speech signals have infinite variations. For example, red light is present in an infinite number of frequencies in nature, whereas a computer has only a few numbers within a finite range to create red color. Paralinguistic content, which is a part of a speech signal, also varies infinitely. Using the concept of paralinguistic content expression, which can be used to express any form of variation onto a speech signal, the present methods of synthesizing speech are enhanced and will lead to technology which is more natural in the human sense. This paper implements the method and results in a tool for synthesizing Hindi speech which gave high intelligibility in 81% of input text samples.
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.
