Speech annotation text correction method, computer equipment and storage medium

A technology of voice annotation and text, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as low efficiency, achieve the effect of reducing workload and improving efficiency

Active Publication Date: 2022-04-26
SHENZHEN RAISOUND TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Based on this, it is necessary to provide a voice annotation text correction method, computer equipment and storage medium for the low efficiency of voice annotation text correction

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 annotation text correction method, computer equipment and storage medium
  • Speech annotation text correction method, computer equipment and storage medium
  • Speech annotation text correction method, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0037] In one embodiment, such as figure 1 As shown, there is provided a voice annotation text modification method including step S110 to step S130.

[0038] Step S110, obtaining the corrected subtext in the text to be detected.

[0039] Wherein, the text to be detected is the recognition result with the highest score in the initial word graph obtained by the initial speech recognizer recognizing speech; in the embodiment of the present application, the text to be detected that has been manually proofread is recorded as the corrected subtext , and the rest is the uncorre...

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 application relates to a voice annotation text correction method, including: obtaining the corrected subtext in the text to be detected; the text to be detected is the recognition result with the highest score in the initial word map obtained by recognizing speech by an initial speech recognizer; based on the The correction type of the corrected subtext determines the adaptive model for the model adjustment in the initial speech recognizer; the adaptive recognition result is determined through the adaptive model, and the unidentified text in the text to be detected is updated according to the adaptive recognition result Correct the relevant information of the subtext. Through the above method, since the model in the speech recognizer is adjusted to obtain a new model by learning the correction logic in the corrected subtext, the part that has not been corrected can obtain a new recognition result through the new model, thus for the user to correct the subsequent The marked text can reduce a certain amount of work and improve efficiency.

Description

technical field [0001] The present application relates to the technical field of speech recognition, in particular to a method for modifying speech-marked text, computer equipment and a storage medium. Background technique [0002] Transcription, in simple terms, is to convert speech into text, and the process can be divided into rough mark and fine mark. At present, artificial voice annotators proofread based on voice recognition, and use big data collection and analysis to make voice recognition more accurate. On the one hand, speech annotation can provide basic data resources for speech recognition or other speech applications; on the other hand, in actual systems, there will always be certain errors in the results of speech recognition, so manual proofreading and Modification, and how to improve the speed of proofreading is also a problem that needs to be solved. Establishing a recognition system with a high accuracy rate generally corresponds to a large amount of manu...

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 & AuthorityPatents(China)
IPC IPC(8): G10L15/26G10L15/06
CPCG10L15/26G10L15/06
Inventor黄石磊刘轶程刚王昕
OwnerSHENZHEN RAISOUND TECH