Method and system for transforming written text into oral text

A text and written technology, applied in natural language translation, natural language data processing, special data processing applications, etc., can solve problems such as affecting user experience, rigidity, and poor expression, and achieve the effect of improving user experience and accurate location.

Active Publication Date: 2018-03-27
IFLYTEK CO LTD
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing text conversion methods directly analyze the written text and add the corresponding paralanguage to obtain the converted colloquial text. The converted colloquial text simply adds common paralinguistic information in spoken language to the wri

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
  • Method and system for transforming written text into oral text
  • Method and system for transforming written text into oral text
  • Method and system for transforming written text into oral text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0073] like figure 1 Shown is a flowchart of a method for converting written text into spoken text in an embodiment of the present invention, including the following steps:

[0074] Step 101, receiving source text data to be converted.

[0075] The source text data is written language text data, such as news release data, more formal meeting record data, and the like.

[0076] Step 102, performing word segmentation and vectorization processing on the source text data to obtain a sequence of word vectors for each sentence of the source text data.

[0077] The word segmentation method can use existing technology, such as word segmentation based on the conditional random field model, and the vectorization process...

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 method for transforming a written text into an oral text. The method comprises the steps that to-be-transformed source text data is received; word segmentation and vectorization processing is performed on the source text data, and a word vector sequence of each source text data sentence is obtained; the word vector sequences of all the source text data sentences are sequentially input into a text transformation model constructed in advance, and target text data corresponding to the source text data is obtained according to output of the text transformation model; andparalanguage information is interposed into the target text data, and oral text data with the paralanguage information is obtained. By use of the method, the oral text obtained after transformation can better conform to the oral expression habit.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method and system for converting written text into spoken text. Background technique [0002] Language is the system people use to communicate and usually has two different forms of expression, spoken and written. Spoken language is spoken language, and written language is written language, both of which have different characteristics. Generally speaking, spoken language is more flexible and shorter than written language, and is more dependent on context. Expressions are often accompanied by paralinguistic phenomena, such as panting, dragging, and pauses, which make spoken language sound more natural and easier to understand than written language. Therefore, in order to facilitate human understanding, the researchers propose that written texts can be converted into colloquial texts. [0003] When existing text conversion methods convert written language into spoken ...

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): G06F17/28G06F17/27
CPCG06F40/289G06F40/40
Inventor 周明江源胡国平胡郁
Owner IFLYTEK 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