Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech synthesis method based on accent and related device

A technology of speech synthesis and accent, which is applied in speech synthesis, speech analysis, semantic analysis, etc. It can solve the problems of poor experience, not vivid enough, and blunt voice, etc., and achieve the effect of improving the experience

Inactive Publication Date: 2022-04-12
FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This application provides an accent-based speech synthesis method and related devices, which are used to solve the technical problem that the speech obtained by the existing speech synthesis technology is blunt and not vivid enough, which leads to poor experience of the audience

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 based on accent and related device
  • Speech synthesis method based on accent and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0044] For ease of understanding, see figure 1 , an embodiment of a stress-based speech synthesis method provided by the present application, including:

[0045] Step 101: Perform part-of-speech classification processing on the target sentence based on artificial intelligence word segmentation technology to obtain a class part-of-speech set, and the categories of ...

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 discloses a voice synthesis method based on accent and a related device, and the method comprises the steps: carrying out the part-of-speech classification processing of a target sentence based on an artificial intelligence word segmentation technology, obtaining a class part-of-speech set, and enabling the classes of the class part-of-speech set to comprise verbs, nouns and modifiers; determining a sentence structure of the target sentence according to the class part-of-speech set, wherein the sentence structure comprises subject-called phrases and object phrases; carrying out importance sorting of rereading on the preset accent vocabulary set to obtain a rereading sequence; based on the preset rereading probability, the rereading sequence, the preset rereading mode and the sentence structure, rereading speech synthesis is conducted on the target sentence, a target synthesized speech is obtained, and the rereading mode comprises slow reading and pause reading. The technical problem that the audience experience is poor due to the fact that voice obtained through an existing voice synthesis technology is stiff and not vivid enough can be solved.

Description

technical field [0001] The present application relates to the technical field of speech synthesis, in particular to an accent-based speech synthesis method and related devices. Background technique [0002] Stress refers to those words or words or phrases that play an important role in expressing the meaning in the text and should be specially emphasized in reading aloud. Accented reading highlights the meaning through the emphasis of the sound, and it can add points to brightly colored and vivid words. Therefore, in the process of text-to-speech, or speech synthesis, accent is particularly important. In speech synthesis (TTS), the existing technology only performs simple text conversion and output of speech, which is very blunt and not vivid, and the audience experience is poor. Contents of the invention [0003] The present application provides an accent-based speech synthesis method and related devices, which are used to solve the technical problem that the speech obt...

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
IPC IPC(8): G10L13/027G06F16/35G06F40/211G06F40/30
Inventor 余勇钟少恒陈志刚王翊蔡勇超
Owner FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID