Embedded speech synthesis method, device, controller and medium

A speech synthesis and embedded technology, applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of unnatural sound, large storage space, occupation, etc., to solve the problem of unnatural speech, reduce storage space requirements, and widely use value Effect

Active Publication Date: 2022-05-17
YUTOU TECH HANGZHOU
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that the existing embedded speech synthesis technology has at least the following disadvantages: first, the storage of sound clips on the embedded device still takes up a lot of storage space, and second, the voice spliced ​​out is not natural enough.

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
  • Embedded speech synthesis method, device, controller and medium
  • Embedded speech synthesis method, device, controller and medium

Examples

Experimental program
Comparison scheme
Effect test

preparation example Construction

[0057] The embodiment of the present invention provides an embedded speech synthesis method, such as figure 1 shown, including:

[0058] Step S1, obtaining the text information to be played of the embedded device;

[0059] Wherein, the text information to be played is text information to be synthesized into speech, and the text information to be played may be text information directly input by the user through the embedded device, or may be converted by the user through voice interaction with the embedded device. text information, etc.

[0060] Step S2, obtaining a plurality of linguistic feature trees corresponding to the text information to be played from the database of the embedded device;

[0061] Step S3, merging the plurality of linguistic feature trees into one target linguistic feature tree according to the text ranking of the text information to be played;

[0062] Step S4, synthesizing the target linguistic feature tree into speech.

[0063] Among them, the acoust...

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 present invention relates to an embedded speech synthesis method, device, controller and medium. The method includes acquiring text information to be played of an embedded device; acquiring the text information corresponding to the text information to be played from a database of the embedded device. multiple linguistic feature trees; merging the multiple linguistic feature trees into a target linguistic feature tree according to the text sorting of the text information to be played; synthesizing the target linguistic feature tree into speech. The invention reduces the required storage space on the embedded device and improves the quality of the embedded speech synthesis.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to an embedded speech synthesis method, device, controller and medium. Background technique [0002] Embedded device synthesis does not require arbitrary text synthesis in many scenarios, and usually only needs to do text synthesis in related fields. The computing resources and storage resources of embedded systems are much less than those in the cloud. With a small amount of resources, text conversion must be compromised. The quality of voice (also known as speech synthesis, TTS for short in English) can be completely offline. It can be seen that, in the prior art, it is still relatively difficult to implement a set of high-quality TTS on an embedded device without a network. [0003] The speech synthesis engine can usually be divided into a front-end engine and a back-end engine. The front-end can be understood as mapping characters to phonemes and other artificial ling...

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 Patents(China)
IPC IPC(8): G10L13/02G10L13/04G10L13/08
CPCG10L13/02G10L13/08G10L13/04
Inventor 郑杰文
Owner YUTOU TECH HANGZHOU
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