Prosody adaptation in text-to-speech synthesis

Prosody adaptation in text-to-speech synthesis

A prosody adaptation text-to-speech system based on concatenation of spoken English words is presented in this paper. To make the resulting sentences sound natural, modifications are made to the prosody of the speech units using the Time-Domain-Pitch-Synchronous- Overlap-Add method. A prosody genera...

Full description

Saved in:
Bibliographic Details
Main Authors: Poh, Teng Chuan, Foo, Say Wei, Yeo, Huat Chye
Other Authors: International Conference on Communication Systems (2000 : New Orleans, US)
Format: Conference or Workshop Item
Language:English
Published: 2011
Subjects:
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Online Access:https://hdl.handle.net/10356/92220
http://hdl.handle.net/10220/6806
http://www.eng.nus.edu.sg/EResnews/0110/rd/rd_4.html
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:A prosody adaptation text-to-speech system based on concatenation of spoken English words is presented in this paper. To make the resulting sentences sound natural, modifications are made to the prosody of the speech units using the Time-Domain-Pitch-Synchronous- Overlap-Add method. A prosody generator is built to generate the intonation pattern for the synthesised speech. An approach of smoothing the distortion at the boundaries of the concatenated units is proposed. Listening tests show that the synthesised speech has a high level of intelligibility and naturalness.

Similar Items