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

Chinese speech synthesis normalization method and device and computing equipment

A speech synthesis and normalization technology, applied in speech synthesis, speech analysis, text database query, etc., can solve the problems of recognition errors and low recognition accuracy, achieve the effect of solving rule conflicts and improving accuracy

Pending Publication Date: 2022-05-03
北京有限元科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] 2. The recognition accuracy is not high
Just like the above point 1, when a rule conflict occurs, the artificially preset strategy simply prefers to use a certain rule, which will cause the problem of identification error

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 speech synthesis normalization method and device and computing equipment
  • Chinese speech synthesis normalization method and device and computing equipment
  • Chinese speech synthesis normalization method and device and computing equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] figure 2 It is a schematic flowchart of a Chinese speech synthesis normalization method according to an embodiment of the present application. The normalization method for Chinese speech synthesis may generally include the following steps S1 to S4:

[0040] Step S1, initialize a matrix P with a size of M×N and an initial element of 0 0 (matrix P 0All elements are 0), the M is the total number of rules, and the N is the length of the text to be synthesized (that is, the number of characters); the text to be synthesized is "good, but the so-called full 199-100 of 618, Directly raise the price to 128 a bottle and there is no gift" as an example, the total number of rules M≥5, three of which are the amount rule, the date rule and the full reduction rule. Table 1 intercepts the matrix P related to the above three rules 0 Elements.

[0041] Table 1 Matrix P 0 some elements of

[0042]

[0043] Step S2, use the M rules to scan the text to be synthesized respectively,...

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 Chinese speech synthesis normalization method and apparatus, and a computing device. The method comprises the following steps: initializing a matrix P0 of which the size is M * N and the initial element is 0; respectively scanning the text to be synthesized by using M rules, and if a certain character in the text to be synthesized is matched with a certain rule, updating element values corresponding to the character and the rule in the matrix P0 to non-zero values to obtain an updated matrix P1; when at least two non-zero elements exist in a certain column of the matrix P1, priority calculation is carried out on rules corresponding to the elements, the element value corresponding to the rule with the highest priority is reserved, and other elements are reset to be zero. The device comprises an initialization module, a matrix updating module, a priority calculation module and a merging processing module. The computing equipment comprises a memory, a processor and a computer program which is stored in the memory and can be operated by the processor, and the method is implemented when the processor executes the computer program.

Description

technical field [0001] The present application relates to the field of speech synthesis, in particular to the normalization processing technology of unconventional text in speech synthesis. Background technique [0002] The function of the speech synthesis system is to generate synthesized speech according to the input text to be synthesized, which usually refers to the TTS (text to speech) system, that is, the text-to-speech system. In a commercial speech synthesis system, the speech synthesis service needs to have the ability to process unconventional text in the text to be synthesized, such as identifying text such as mobile phone numbers, well-known brands, and dates and times, and be able to pronounce them correctly. [0003] In order to solve the problem of correct pronunciation of the above text, the usual processing method is to add many rules in the form of regular expressions in the normalization module. Normalization is a front-end processing step of the TTS syst...

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): G06F16/33G06F16/903G10L13/08
CPCG06F16/334G06F16/90344G10L13/08
Inventor 何朋蒋宁王洪斌吴海英权圣杨春勇
Owner 北京有限元科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com