Text processing method and device, electronic equipment and storage medium

A text processing and text input technology, applied in the field of information processing, can solve problems such as uncoordinated pronunciation, and achieve the effect of increasing naturalness and natural speech

Inactive Publication Date: 2019-03-29
MOBVOI INC
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides a text processing method, device, electronic equipment, and storag...

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
  • Text processing method and device, electronic equipment and storage medium
  • Text processing method and device, electronic equipment and storage medium
  • Text processing method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 This is a flowchart of a text processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of processing the pronunciation of sentences mixed with special nouns composed of letters in Chinese. The method can be executed by a text processing device. The apparatus can be implemented by hardware and / or software, and can generally be integrated in various terminals or servers that provide speech synthesis for text. like figure 1 As shown, the method includes:

[0050] Step 110: Identify at least one group of English character strings included in the input text.

[0051] In this embodiment of the present invention, the input text is a piece of text pre-stored in the database, which can answer the question raised by the user or satisfy the requirement raised by the user. Specifically, the input text can be an article, and by performing speech synthesis on the article, the requirement of playing the article for the ...

Embodiment 2

[0064] figure 2 It is a flowchart of a text processing method provided in Embodiment 2 of the present invention, and the arrangement and combination of technical features among the foregoing embodiments also fall within the protection scope of the embodiments of the present invention. The embodiments of the present invention can be applied to any situation where speech synthesis needs to be performed on text. For details, refer to figure 2 , the method may include the following steps:

[0065] Step 210: Establish a mapping relationship between the replacement character and the pronunciation of each Chinese phoneme in advance.

[0066] In the embodiment of the present invention, in order to replace the English letters in the special nouns composed of letters in the input text with the replacement characters, and then obtain the pronunciations corresponding to the English letters in the special nouns, the inconsistency of the pronunciation of the special nouns in the prior ar...

Embodiment 3

[0091] image 3 It is a schematic structural diagram of a text processing apparatus provided in Embodiment 3 of the present invention. Specifically, as image 3 As shown, the apparatus may include:

[0092] an English character string identification module 310, configured to identify at least one group of English character strings included in the input text;

[0093] The target character string replacement module 320 is configured to obtain a replacement character corresponding to each English letter in the target character string if it is determined that the English character string includes a target character string that does not belong to an English word, and perform replacement processing on the target character string. does not belong to Chinese characters;

[0094] The input text segmentation module 330 is used to perform text segmentation on the input text after the replacement processing to obtain at least one text segmentation;

[0095] The pronunciation obtaining ...

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 embodiment of the invention discloses a text processing method and device, electronic equipment and a storage medium. The method comprises the steps of identifying at least one set of English character strings included in an input text; if it is determined that the English character strings include a target character string which does not belong to English words, acquiring a replacement character corresponding to each English letter in the target character string to replace the target character string, wherein the replacement characters do not belong to Chinese characters; conducting textsegmentation on the input text obtained after replacement processing to obtain at least one text word segment; according to a mapping relationship between Chinese and English word segments and Chineseand English pronunciations and a mapping relationship between replacement characters and Chinese phoneme pronunciations, acquiring the pronunciation of each text word segment in the input text. By means of the technical scheme in the embodiment, the problem of uncoordinated pronunciations of sentences formed by mixing Chinese language with special nouns composed of letters during processing is solved, and the naturalness of the speech is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of information processing, and in particular, to a text processing method, apparatus, electronic device, and storage medium. Background technique [0002] TTS (Text To Speech, speech synthesis) is a technology that converts text into human natural language. It is widely used in car and machine navigation broadcast, online customer service of merchants, and intelligent robot language interaction. [0003] The TTS system is mainly divided into front-end and back-end. The front-end mainly completes the work of analyzing text and converting graphemes into phonemes, including text normalization, sentence segmentation, and pronunciation generation. The back-end of TTS mainly completes the synthesis of speech, including prosody prediction, original audio synthesis, etc. The quality of the TTS system is mainly determined by whether the synthesized speech is more in line with human natural lang...

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): G10L13/08G10L13/02G06F17/27
CPCG06F40/284G10L13/02G10L13/08
Inventor 李永强张冉张征
Owner MOBVOI INC
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