Method and device for carrying out error correction on texts after speech recognition

Abstract

The invention provides a method and device for carrying out error correction on texts after speech recognition. The method for carrying out error correction on texts after speech recognition comprises the following steps of: preprocessing a text after speech recognition; recognizing a search intention of the preprocessed text; determining to-be-extracted attribute information according to the recognized search intention and extracting attribute information from the preprocessed text; and calculating the similarity between the attribute information and any candidate word in a candidate lexicon, and carrying out error correction on the extracted attribute information according to the similarity. Through the method and device, the free man-machine interaction is realized, the problem that the speech recognition is incorrect in speech search is effectively solved, the speech recognition correctness is improved, the enterprise search demands are satisfied and the user experience is enhanced.

Description

technical field [0001] The present invention relates to the technical field of voice search, in particular to an error correction method for text after voice recognition, and also to an error correction device for text after voice recognition. Background technique [0002] In daily work and life, we often encounter the need to find employee information from the enterprise employee management system or find customer information from the enterprise customer relationship management system. There are generally two traditional ways to find contact information: one is in a specific In the input box, enter the contact's name, phone number, etc.; the second is to browse through the entire address book. These two methods have the disadvantage of being inconvenient to operate in some scenarios, such as in crowded places such as shopping malls and subways. In addition, flipping through the address book in turn, when there are many entries in the address book, is not only time-consuming...

AI Technical Summary

Problems solved by technology

However, due to the complexity and diversity of language and the influence of surrounding noise, the result of speech recognition often has a large deviation from the content that the user actually wants to input. This requires further error correction processing for the text after speech recognition before it can be applied to the actual system. middle

[0004] Therefore, how to provide a text error correction scheme after speech recognition suitable for address book search, which can effectively solve the problem of inaccurate speech recognition in address book voice search, has become a technical problem to be solved urgently

Images