Quick extraction method and device for telephone channel data and computer readable storage medium

Abstract

The invention relates to the technical field of human computers, and provides a telephone channel data rapid extraction method, which comprises the following steps: obtaining an effective audio in to-be-extracted channel data, the to-be-extracted channel data being channel data acquired in a conversation process of at least two persons; segmenting the effective audio into a plurality of segments; determining a fragment belonging to the first speaker and a speaker change fragment by comparing the voiceprint features of the adjacent fragments; and according to the fragment of the first speaker and the change fragment, clustering the fragments belonging to the first speaker in the effective audio to obtain the effective audio of the first speaker. Based on the method provided by the embodiment of the invention, the effective audio of the speaker can be automatically and quickly extracted without depending on manpower, so that the cost is saved and the data acquisition efficiency is improved. In addition, the invention also provides a telephone channel data rapid extraction device and a computer readable storage medium.

Description

technical field [0001] The present application relates to the field of computer information technology, in particular to a method, device and computer-readable storage medium for quickly extracting telephone channel data. Background technique [0002] The field of artificial intelligence usually requires a large amount of data to support, such as training samples, input layer data, etc., all of which require preprocessing including collection, cleaning, classification, labeling, and construction. These preprocessing tasks are mainly done manually, so whether it is Both the training of the algorithm model and the data required for the model application require a lot of labor costs and are time-consuming. [0003] Artificial intelligence technology will also encounter similar problems in the application of telephone calls. Telephone channel data is mainly divided into two categories: one is binaural data, and the two channels store the audio of the speakers at both ends of the...

AI Technical Summary

Problems solved by technology

[0002] The field of artificial intelligence usually requires a large amount of data to support, such as training samples, input layer data, etc., all of which require preprocessing including collection, cleaning, classification, labeling, and construction. These preprocessing tasks are mainly done manually, so whether it is Both the training of the algorithm model and the data required for the model application require a lot of labor costs and are time-consuming

Images