Entity word error correction method and device based on editing distance, electronic equipment and medium

CN119339740APending Publication Date: 2025-01-21CHINA TELECOM ARTIFICIAL INTELLIGENCE TECHNOLOGY (BEIJING) CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411426785.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-12
Publication Date
2025-01-21

AI Technical Summary

Technical Problem

Existing speech recognition technology is difficult to correctly identify entity words, such as person names, place names and company names, which leads to homophone errors in the recognition results. Hot word enhancement technology needs to be adjusted during the model training stage, which increases development costs and low efficiency.

Method used

Adopt the method of correction method based on the editing distance, by obtaining voice recognition text and entering the pre -trained physical word detection model, determine the syllable sequence of the physical word, and calculate the editing editing edit editing with the syllable sequence in the preset entity list list From the distance, select the entity word with the editing distance less than the threshold as the error correction target.

Benefits of technology

It improves the efficiency and accuracy of voice recognition, reduces the difficulty of development and deployment, reduces the training cost of voice recognition models, and only needs to adjust the physical word list in different application scenarios without the need to re -train the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119339740A_ABST
    Figure CN119339740A_ABST
Patent Text Reader

Abstract

The invention discloses an entity word error correction method and device based on an editing distance, electronic equipment and a medium, and the method comprises the steps: obtaining a voice recognition text, inputting the voice recognition text into a pre-trained entity word detection model, and obtaining a to-be-corrected first entity word; determining a first syllable sequence of the first entity word; obtaining a plurality of second entity words according to a preset entity word list, and determining a second syllable sequence of each second entity word; determining an editing distance between the first entity word and the second entity word according to the first syllable sequence and the second syllable sequence, and selecting a target entity word from the second entity word according to the editing distance; and replacing the first entity word in the speech recognition text with the target entity word. According to the invention, entity word error correction is carried out on the basis of the speech recognition result by using the editing distance, the speech recognition efficiency and accuracy are improved, and the method can be widely applied to the technical field of speech recognition.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Security check X-ray machine image voice annotation method

    CN122472054A