Voice information batch renaming method and device, computer device and storage medium

Abstract

The embodiment of the invention discloses a voice information batch renaming method and device, a computer device and a storage medium, wherein the method comprises the steps of obtaining an input folder address where a preset training set is located if an information processing instruction is received; determining a preset input list file and an output folder address according to the informationprocessing instruction; renaming all the sub-folders in an input folder, and storing the renamed sub-folders in an output folder corresponding to the output folder address; according to a preset arrangement rule, sorting the to-be-processed voice information in each sub-folder to determine a sorting number of each to-be-processed audio; obtaining the changed file names of all sub-folders in the output folder; and changing the original audio name of each to-be-processed voice information into a target audio name. According to the invention, the unified screening of multiple pieces of to-be-processed voice information in the training set can be realized efficiently and accurately through batch renaming processing.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a batch renaming method, device, computer equipment and storage medium for voice information. Background technique [0002] In speech recognition projects, it is usually necessary to collect or collect a large amount of speech information from various channels, and use these speech information as training samples in the training set to train the neural network, so as to obtain the corresponding recognition model for feature speech recognition. In order to ensure the smooth training process of the neural network and the accuracy of the acquired recognition model, it is usually necessary to pre-process the acquired speech information before training, such as renaming all the speech information according to specific rules, etc. , and the realization of the preprocessing of a large amount of voice information requires gradual iterations to complete, but the process of repeated iterativ...

AI Technical Summary

Problems solved by technology

In order to ensure the smooth training process of the neural network and the accuracy of the acquired recognition model, it is usually necessary to pre-process the acquired speech information before training, such as renaming all the speech information according to specific rules, etc. , and the realization of the preprocessing of a large amount of voice information requires gradual iterations to complete, but the process of repeated iterative processing is very prone to operational errors due to the large amount of data, resulting in inaccurate screening of voice information

Images