Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech recognition text processing method and device, electronic equipment and storage medium

A speech recognition and text processing technology, applied in the computer field, can solve problems such as poor readability of speech recognition texts, achieve the effect of increasing data diversity and improving accuracy

Pending Publication Date: 2022-03-08
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention solves the technical problem of poor readability of speech recognition text in the prior art by providing a speech recognition text processing method, device, electronic equipment and storage medium

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
  • Speech recognition text processing method and device, electronic equipment and storage medium
  • Speech recognition text processing method and device, electronic equipment and storage medium
  • Speech recognition text processing method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] The present invention provides a speech recognition text processing method, device, electronic equipment and storage medium to solve the technical problem of poor readability of speech recognition text in the prior art. The general idea is as follows:

[0086] Obtain the original text obtained by speech recognition; perform preset processing on the original text to obtain preset processing results, wherein the preset processing includes punctuation addition processing and / or digital regularization processing, and the preset processing results include punctuation addition processing results and / or The result of digital regularization processing; the text smoothing processing is performed on the original text through the attention mechanism to obtain the text smoothing processing result; based on the text smoothing processing result and the preset processing result, the processed text of the original text is obtained.

[0087] Through the above technical solution, text smo...

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 speech recognition text processing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an original text obtained by speech recognition; preset processing is carried out on the original text to obtain a preset processing result, the preset processing comprises punctuation adding processing and / or digital normalizing processing, and the preset processing result comprises a punctuation adding processing result and / or a digital normalizing processing result; performing text smoothing processing on the original text through an attention mechanism to obtain a text smoothing processing result; and based on the text smoothing processing result and the preset processing result, obtaining a processed text of the original text. According to the scheme, multi-target interaction of an attention mechanism is introduced, and in the process of outputting the text smoothing processing result, the characteristics of punctuation adding processing and / or digital regularizing processing are fully utilized, so that the accuracy of speech recognition text processing is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a speech recognition text processing method, device, electronic equipment and storage medium. Background technique [0002] Speech recognition technology is to recognize and process the speech signal to obtain the corresponding text. At present, the readability of the text directly outputted through speech recognition processing is poor. Therefore, there is an urgent need for a speech recognition text processing solution to solve the problem of poor readability of speech recognition text in the prior art. Contents of the invention [0003] Embodiments of the present invention solve the technical problem of poor readability of speech recognition texts in the prior art by providing a speech recognition text processing method, device, electronic equipment, and storage medium. [0004] In a first aspect, an embodiment of the present invention provides a speech recognition text ...

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): G06F40/151G06F40/103G06F40/205G06K9/62G06N3/08G10L15/22
CPCG06F40/151G06F40/103G06F40/205G10L15/22G06N3/08G06F18/214G10L15/16G06F40/279G06F40/166G10L15/26
Inventor 赵昂余健
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD