Recording noise detection method and device of voice annotation system, equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a recording noise detection method and device of a voice annotation system, equipment and a medium. The recording noise detection method of the voice annotation system comprises the steps of obtaining to-be-annotated recording data of a conversation between a client and a robot, wherein the recording data comprises a recording audio file and corresponding recording information; labeling the to-be-labeled recording data to obtain recording labeling data; calling a noise detection engine to carry out noise detection on the recording annotation data; obtaining a noise detection result of the noise detection engine through message middleware; and according to the recording unique identification number in the noise detection result, associating the noise detection result to recording information of corresponding recording annotation data in a recording information table. According to the method, a large amount of time can be saved for annotation personnel to synchronously carry out other work, and after the detection result is obtained, the voice annotation system can update the detection result into the database in time so that the voice annotation personnel can use the detection result.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a recording noise detection method, device, equipment and medium of a voice tagging system. Background technique [0002] The voice annotation system is a system for analyzing and marking the dialogue between the customer and the robot. This system already exists in the field of intelligent voice recognition, but the analysis of the voice dialogue between the customer and the robot is not yet perfect and intelligent. [0003] At present, most voice annotation systems on the market cannot independently undertake the function of noise detection. Due to technical barriers, cost and other factors, even if the noise detection algorithm engine is connected, the solution is to use traditional offline manual packaging of recording files, and then upload noise detection. The algorithm engine, after waiting for a long time, obtains the calculation results, and then ...

AI Technical Summary

Problems solved by technology

[0002] The voice tagging system is a system for analyzing and marking the dialogue between the customer and the robot. This system already exists in the field of intelligent voice recognition, but the analysis of the voice dialogue between the customer and the robot is not yet perfect and intelligent.

[0003] At present, most voice annotation systems on the market cannot independently undertake the function of noise detection. Due to technical barriers, cost and other factors, even if the noise detection algorithm engine is connected, the solution is to use traditional offline manual packaging of recording files, and then upload noise detection. Algorithm engine, after waiting for a long time, the calculation results are obtained, and then manually input into the labeling system or directly use Excel for statistical analysis, which greatly reduces the work efficiency of labeling personnel and reduces the accuracy of dialogue between robots and customers

Images