Back to results
US 5,970,459 AGranted
System for synchronization between moving picture and a text-to-speech converter
AssigneeElectronics and Telecommunications Research Institute
InventorsJae Woo Yang, Jung Chul Lee, Min Soo Hahn
Life of this patent
Estimating the term…
Abstract
A method of formatting and normalizing continuous lip motions to events in a moving picture besides text in a Text-To-Speech converter is provided. A synthesized speech is synchronized with a moving picture by using the method wherein the real speech data and the shape of a lip in the moving picture are analyzed, and information on the estimated lip shape and text information are directly used in generating the synthesized speech.
Claims4
A system for synchronization between a moving picture and a text-to-speech converter, comprising:
- distributing means for receiving multi-media input information, transforming said multi-media input information into respective data structures, and distributing the respective data structures for further processing;
- image output means for receiving image information of the distributed multi-media information and displaying the image information;
- language processing means for receiving language texts of the distributed multi-media information, transforming the language texts into phoneme strings, and estimating and symbolizing prosodic information from the language texts;
- prosody processing means for receiving the prosodic information from said language processing means, and calculating values of prosodic control parameters;
- synchronization adjusting means for receiving the prosodic control parameters from said prosody processing means, adjusting time durations for every phoneme for synchronization with the image information by using synchronization information of the distributed multi-media information, and inserting adjusted time durations into the prosodic control parameters;
- signal processing means for receiving the processing results from said synchronization adjusting means and generating a synthesized speech;
- and
- a synthesis unit database block for selecting required units for synthesis in accordance with a request from said signal processing means, and transmitting the required data to said signal processing means.
5 more elements
Dependencies are inferred from the claim text.