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

Abstract

The invention provides a text error correction method and device, electronic equipment and a readable storage medium, and relates to the technical field of artificial intelligence such as natural language processing and deep learning. The text error correction method comprises the steps of obtaining a to-be-processed text, and determining a target text in the to-be-processed text; obtaining at least one candidate phoneme sequence according to a phoneme dictionary and an original phoneme sequence of the target text; according to the at least one candidate phoneme sequence and phoneme sequences of a plurality of candidate words, selecting a target word from the plurality of candidate words; and obtaining an error correction result of the to-be-processed text according to the target word. According to the method, the steps of text error correction can be simplified, the cost of text error correction can be reduced, cold start of text error correction can be realized, a better error correction effect can be obtained under the condition of'pronunciation-like character error 'in the text, and the accuracy of text error correction is further improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to the field of artificial intelligence technology such as natural language processing and deep learning. Specifically, a text error correction method, device, electronic equipment and readable storage medium are provided. Background technique [0002] In the Chinese environment, the automatic speech recognition system needs to recognize the sound signal into Chinese characters. Since Chinese characters have one sound with multiple characters or one character with multiple sounds, the automatic speech recognition system will tend to generate Chinese character sequences that appear with a high probability in the training samples. In addition, because the user may have inaccurate pronunciation or the voice signal introduces noise during channel propagation, the result of Chinese characters cannot be obtained correctly from the voice signal, so text error correction is ...

AI Technical Summary

Problems solved by technology

However, the existing technology usually relies on machine learning technology when performing text error correction, so there are problems of high error correction cost and inability to cold start

Images