Chinese test to voice joint synthesis system and method using rhythm control

A text-to-speech technology, applied in the field of Chinese text-to-speech splicing systems, can solve problems such as difficulty in obtaining high-quality text and speech, application limitations, etc., achieve efficient syllable synthesis, save storage space, and reduce storage space. Effect

Inactive Publication Date: 2004-01-28
CERENCE OPERATING CO
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is difficult to obtain high-quality text-to-speech on such portable devices
This makes text-to-speech conversion limited in application in these areas

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Chinese test to voice joint synthesis system and method using rhythm control
  • Chinese test to voice joint synthesis system and method using rhythm control
  • Chinese test to voice joint synthesis system and method using rhythm control

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] figure 1 A presently existing Chinese text-to-speech conversion system is shown. The conversion system mainly includes three parts: a text processor 100 , a sound clip library 200 and a synthesis device 300 . The main function of the text processor 100 is to assign corresponding phonetic symbols to Chinese characters in the Chinese text after standardization and word segmentation of the input Chinese text. Then, the obtained phonetic symbol sequence is used to match the phonetic symbol sequence stored in the sound clip library 200 , and then replaced with the corresponding voice or phrase sound clip. Finally, the synthesizing device 300 splices these sound clips according to the order of the Chinese text, and inserts appropriate pause information to obtain the required speech output. The sound clip library 200 stores a large number of Chinese text materials, as well as recordings of human pronunciation of these materials. The amount of these pronunciation materials u...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The system comprises the text processor, the device for controlling sound and rhythm and the synthesizer. Based on input text, the text processor generates a sequence of phonetic sign after word is partitioned. The sound and rhythm control device comprises at least the pronunciation label base, sound location index and the device for selecting difference rhythm vector. The said base includes at least the sound location index and difference rhythm vector. The selection device of difference rhythm vector generates control data including the index and rhythm vector after phonetic sign sequence being received. The synthesizer comprising sound unit parameter base responds to the control data from the sound and rhythm device to generate syntactic voice. The invention provides syntactic voice with good quality, suitable to mini type embedded device.

Description

technical field [0001] The present invention relates to a Chinese text-to-speech (Text-to-Speech, TTS) splicing system, in particular to a Chinese text-to-speech splicing synthesis system and method using prosody control. Background technique [0002] For electronic equipment, such as a large amount of text data stored in computers, mobile phones or personal digital assistants (PDAs), using eyes to read is easy to cause visual fatigue. And sometimes, like in a moving car, reading data on an electronic screen is inconvenient. Therefore, it is hoped that these texts will be converted into speech and played to readers to resolve these contradictions. [0003] At present, high-quality Chinese text-to-speech synthesis technology is basically based on splicing the pronunciation waveforms corresponding to each word, word or phrase in the Chinese text. The required pronunciation waveforms are generally selected from a pronunciation waveform library with a large amount of data, and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L13/04G10L13/08
CPCG10L13/10G10L13/047
Inventor 黄建成陈芳
Owner CERENCE OPERATING CO
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap