Text error correction method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a text error correction method, device and equipment and a computer readable storage medium. The text error correction method comprises the following steps: displaying a speech recognition text; receiving a focus point of the eyes of the user in the speech recognition text, and determining residence information of the focus point, the residence information including residence time; when the residence duration meets a preset condition, determining a to-be-modified text corresponding to the focus point, and displaying candidate texts of the to-be-modified text; when the focus point moves, determining a candidate text corresponding to the focus point moving moment; and modifying the to-be-modified text into a candidate text corresponding to the focus point moving moment. According to the embodiment of the invention, the error recognition of the text can be conveniently and quickly corrected without user input, and the text error can be quickly and accurately corrected.

Description

technical field [0001] The present invention relates to the field of speech recognition, in particular to a text error correction method, device, equipment and computer-readable storage medium. Background technique [0002] With the continuous development and progress of society, speech recognition will be used in many fields and scenarios. For example: industry, home appliances, communications, automotive electronics, medical care, home services, consumer electronics and other fields. [0003] Since everyone's speech speed, intonation and pronunciation are different, in the case of errors in speech recognition, one is the traditional error correction method, manual input to correct, correcting wrong text by manual input, especially for long texts In some cases, the operation is too cumbersome and inconvenient for users to use; in the other case, model training is required, and the speech recognition rate or error correction rate needs to be improved based on historical inp...

AI Technical Summary

Problems solved by technology

[0003]Because everyone's speech speed, intonation and pronunciation are different, in the case of speech recognition errors, one is the traditional error correction method, manual input to Correction, correcting wrong text by manual input, especially for long texts, the operation is too cumbersome and inconvenient for users to use; the other requires model training, which needs to improve speech recognition rate or error correction based on historical input or historical data rate, however, there is still a high speech recognition error rate if the processing is performed before the recognition result

Therefore, whether it is the traditional error correction method or the intelligent error correction method, there will be problems that the error correction cannot be performed or the error correction is not ideal, which will bring inconvenience to the user.

Images