Voice key information recording device and method based on semi-automatic correction

Abstract

Disclosed are voice key information recording device and method based on semi-automatic correction in the technical field of voice identification. The device comprises a key information extraction unit and an information correction unit connected with the key information extraction unit. The key information extraction unit acquires text information which is not corrected and extracts key information before outputting to the information correction unit, and the information correction unit outputs text information determined by user feedback. Work load of manual correction is reduced by the semi-automatic information correction unit; special nouns such as place names and professional tool names are corrected by a database, and influence caused by knowledge quantity limitation of operators in manual correction is reduced; and key information in voice information is extracted, and accordingly effective information quantity of recorded information is increased.

Description

technical field [0001] The present invention relates to a device and method in the technical field of speech recognition, in particular to a device and method for recording key speech information based on semi-automatic correction. By recognizing the speech signal and recording it in text form, it is inconvenient for the user to When the voice information is recorded in text, it can replace the user to complete the text recording of the voice information. Background technique [0002] Limited by the speech signal recognition technology, the known recording device automatically recognizes the received speech signal, and manually corrects the received speech signal to ensure the accuracy of the recorded information. As a result, the normal operation of the recording device requires a lot of manual correction work; and some information mentioned in the voice signal may not be able to be effectively corrected due to the limited knowledge of the operator itself, such as some geog...

AI Technical Summary

Problems solved by technology

[0005] However, this existing technology requires business operators to recognize all text information, and these text information are the results of direct recognition by speech recognition devices

On the one hand, all text information contains a lot of meaningless information, such as greetings, particles, and modal particles during a call. The real and effective information only accounts for a part of it. The business operator’s identification of all text information increases the workload of the business operator.

On the other hand, in the direct recognition results of the speech recognition device, one type of information is special nouns and proper nouns, and the business operator is responsible for correcting such information, so that the accuracy of error correction depends on the knowledge of the salesman. There is a risk of error correction; another type of information has certain format requirements, such as time information, which can be automatically corrected by algorithms. If the error correction of such information is handed over to the business operator, it will also increase the burden on business operations. staff error correction workload

Images