Speech synthesis method and system, equipment and storage medium

A speech synthesis and audio technology, applied in the computer field, can solve the problems of low audio accuracy, long time, and inability to accurately reflect the expression of the text, so as to improve the speed, reduce the possibility of missing words, and avoid the risk of missing words. Effect

Active Publication Date: 2021-05-11
亿度慧达教育科技(北京)有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the speech synthesis method at this stage either takes a long time for audio generation, or the accuracy of the obtained speech synthesis audio is low, and cannot accurately reflect the expression of the text

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
  • Speech synthesis method and system, equipment and storage medium
  • Speech synthesis method and system, equipment and storage medium
  • Speech synthesis method and system, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

preparation example Construction

[0032] In order to obtain accurate speech synthesis audio in a shorter speech synthesis time, the embodiment of the present invention provides a speech synthesis method, system, device and storage medium. The speech synthesis method provided in the embodiment of the present invention includes:

[0033] Obtain the text to be speech synthesized;

[0034] Obtaining a text unit matrix according to the text;

[0035] Obtain the number of unit spectrum frames corresponding to the text unit matrix, and acquire the unit spectrum matrix corresponding to the text unit matrix according to the prestored text unit spectrum sequence;

[0036] Constructing a text spectrum matrix corresponding to the text according to the number of unit spectrum frames and the unit spectrum matrix;

[0037] Speech synthesis is performed on the text spectrum matrix to obtain audio corresponding to the text.

[0038] In this way, the speech synthesis method provided by the embodiment of the present invention,...

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 embodiment of the invention provides a speech synthesis method and system, equipment and a storage medium. The method comprises the following steps: obtaining a text to be subjected to speech synthesis; obtaining each text unit matrix according to the text; obtaining unit frequency spectrum matrixes corresponding to the text unit matrixes according to a pre-stored text unit frequency spectrum sequence, and obtaining unit frequency spectrum frame numbers corresponding to the text unit matrixes, wherein the text unit frequency spectrum sequence stores the text unit matrixes and the unit frequency spectrum matrixes which correspond to each other; constructing a text spectrum matrix corresponding to the text according to the unit spectrum frame number and the unit spectrum matrix; and performing speech synthesis on the text spectrum matrix to obtain an audio corresponding to the text. According to the speech synthesis method and system, the equipment and the storage medium provided by the embodiment of the invention, the accurate speech synthesis audio can be obtained within a short speech synthesis time.

Description

technical field [0001] The embodiments of the present invention relate to the field of computers, and in particular, to a speech synthesis method, system, device and storage medium. Background technique [0002] Text to speech (TTS) technology is a speech technology that converts text into audio. [0003] In recent years, with the development of speech technology, speech synthesis technology has been widely used in many fields, such as: audio reading, smart speakers, simultaneous transmission and other fields. [0004] However, the speech synthesis method at the present stage either takes a long time for audio generation, or the accuracy of the obtained speech synthesis audio is low, and cannot accurately reflect the expression of the text. [0005] Therefore, how to obtain accurate speech synthesis audio in a short speech synthesis time has become a technical problem that needs to be solved urgently. Contents of the invention [0006] The technical problem to be solved ...

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): G10L13/02G10L25/18G10L25/63
CPCG10L13/02G10L25/18G10L25/63
Inventor 付涛王鑫龙彭守业
Owner 亿度慧达教育科技(北京)有限公司
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