Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech synthesis method and system based on rhythm

A speech synthesis and rhythm technology, applied in speech synthesis, speech analysis, natural language data processing, etc., can solve the problem of high difficulty of rhythm generation, and achieve the effect of reducing the difficulty of rhythm generation and making the results of speech synthesis vivid.

Active Publication Date: 2022-06-28
FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a rhythm-based speech synthesis method and system, which solves the technical problem that the rhythm generation of speech synthesis is difficult

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 based on rhythm
  • Speech synthesis method and system based on rhythm
  • Speech synthesis method and system based on rhythm

Examples

Experimental program
Comparison scheme
Effect test

preparation example Construction

[0045] For ease of understanding, see figure 1 , a rhythm-based speech synthesis method provided by the invention comprises the following steps:

[0046] S1. Divide the text to be processed into paragraphs to obtain a plurality of natural paragraphs.

[0047] S2. Perform word segmentation processing on each natural paragraph to obtain the word segmentation result of each natural paragraph, perform part-of-speech tagging on the word segmentation result of each natural paragraph, perform weighted calculation on the part-of-speech tagging result of the natural paragraph, and determine the corresponding natural paragraph according to the calculation result. The sentiment type of the paragraph.

[0048] S3. Perform word segmentation on the full text of the text to be processed, obtain a word segmentation result of the full text, perform part-of-speech tagging on the word segmentation result of the full text, perform weighted calculation on the part-of-speech tagging result of the ...

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 invention relates to the technical field of speech recognition, and discloses a rhythm-based speech synthesis method and system, and the method comprises the steps: dividing a to-be-processed text into a plurality of natural paragraphs, carrying out the word segmentation processing and part-of-speech tagging of each natural paragraph and a full text, and carrying out the weighted calculation according to a part-of-speech tagging result, thereby obtaining a speech recognition result. Determining the emotion type of the corresponding natural paragraph and the emotion type of the full text according to the calculation result, determining the rhythm of the natural paragraph and the rhythm of the full text according to the emotion type, and carrying out weighted calculation according to preset voice attribute data, the rhythm of the full text and the rhythm of the natural paragraph to obtain the voice synthesis rhythm of each natural paragraph; the corresponding natural paragraph is subjected to voice conversion through the voice synthesis rhythm to obtain the voice synthesis result, so that the rhythm of the natural paragraph is determined by utilizing the emotion, the rhythm generation difficulty is reduced, and the voice synthesis result is more vivid.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a method and system for rhythm-based speech synthesis. Background technique [0002] In speech synthesis, the selection of the basic rhythm is the most important step. The selection of the basic rhythm is determined by the tone of the text. If it does not conform to the tone of the text, it will cause errors in the speech synthesis of all texts, resulting in funny scenes. [0003] In speech synthesis (TTS), the existing technology only performs simple text conversion and output on speech, but the rhythm generation of speech synthesis is difficult, resulting in very rigid speech synthesis results, difficulty in expressing real emotions, and reducing user interaction. experience. SUMMARY OF THE INVENTION [0004] The present invention provides a rhythm-based speech synthesis method and system, which solves the technical problem that the rhythm generation of sp...

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): G10L13/10G10L13/02G06F40/289
CPCG10L13/10G10L13/02G06F40/289
Inventor 余勇钟少恒付佳佳陈锦荣杨毅王翊王佳骏吕华良蔡勇超丁铖陈志刚陈捷陈瑾曹小冬吴启明林承勋林家树郭泽豪符春造方美明李鸿盛
Owner FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products