Multi-language text automatic broadcast method and system

A multi-language and text technology, applied in speech synthesis, speech analysis, instruments, etc., can solve the problems of low splicing accuracy, inflexibility, and heavy workload, so as to reduce workload, ensure orderliness, and save time and cost Effect

Inactive Publication Date: 2017-06-16
BEIJING INTELLIGENT STEWARD CO LTD
View PDF11 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First, the Chinese voice broadcast model is used for synthesis: "The next stop is Wangjing", and the English voice broadcast model is used for synthesis: "soho", and the user's Chinese voice broadcast model is used for synthesis: "Please pay attention to getting off the car", and the last three audios are spliced ​​into One, but this method is very inflexible. If there are many characters, it will cause excessive workload and low splicing accuracy.

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
  • Multi-language text automatic broadcast method and system
  • Multi-language text automatic broadcast method and system
  • Multi-language text automatic broadcast method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055]In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0056] Embodiment 1 of the present invention provides a specific implementation manner of a method for automatically broadcasting multilingual text. see figure 1 , the automatic broadcast method specifically includes the following content:

[0057] Step 100: Perform language identification on the multilingual text to be broadcast, and acquire tex...

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 multi-language text automatic broadcast method and system. According to the method, language identification is performed on a multi-language text to be broadcasted, and text fields corresponding to multiple languages are respectively acquired; the start and end points of each text field are respectively identified so as to obtain language identifiers; and the corresponding sound broadcast type of each language is correspondingly called according to the language identifiers, and all the text fields are broadcasted in turn. The system is provided with a character identification module and a voice broadcast module. The method and the system are intelligent and flexible so that rapid and accurate automatic identification and broadcasting of the multi-language text can be realized, and the situation of omitting language information in identifying the multi-language text can be avoided.

Description

technical field [0001] The invention relates to the technical field of speech conversion, in particular to a method and system for automatically broadcasting multilingual texts. Background technique [0002] At present, many devices have the function of TTS (Text to Speech, which converts text into sound for playback). To convert text into speech, a professional speech engine is generally used. The speech engine will select a timbre and a specific speech for sound training. After the training is complete, the audio of the corresponding language can be synthesized. Therefore, generally a specific voice broadcast model corresponds to a specific language. If the synthesized language does not correspond to the voice broadcast model, the voice may be abnormal or unable to speak. [0003] In view of this situation, if there are both Chinese and English in a piece of text, if the same voice broadcast model is used, the above problems will occur, so it is necessary to choose differ...

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): G10L13/02G10L13/08
CPCG10L13/02G10L13/08
Inventor 原树旗雷宇
Owner BEIJING INTELLIGENT STEWARD CO LTD
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