Language identification method and device for broadcast audio, equipment and storage medium

Abstract

The invention provides a language identification method and device for broadcast audio, equipment and a storage medium, and the method comprises the steps: carrying out the resampling of to-be-detected broadcast audio data according to a first sampling rate and a second sampling rate, splicing the resampling result with the to-be-detected broadcast audio data according to the sampling rate of the to-be-detected broadcast audio data to obtain first audio data; inputting the first audio data into a language recognition model to obtain a language recognition result, wherein the language recognition model comprises an acoustic model, a rhythm model and a Gaussian mixture classifier; allowing the acoustic model to extract acoustic features of the to-be-detected broadcast audio data to obtain a first language recognition result, and the rhythm model to extract rhythm features of the to-be-detected broadcast audio data to obtain a second language recognition result; and allowing the Gaussian mixture classifier to obtain a language recognition result of the to-be-detected broadcast audio data based on the first language recognition result and the second language recognition result. The method has the beneficial effect that the language recognition accuracy of the broadcast audio can be improved.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a method, device, equipment and storage medium for language recognition of broadcast audio. Background technique [0002] With the increasing enrichment and development of foreign multilingual broadcasting in my country, broadcasting monitoring has also been flourishing. An important business of broadcast monitoring is the language identification of medium and short-wave broadcasts, that is, after judging the language of the broadcast audio, it is compared with the language planned to be broadcast, and then judged whether there is a wrong broadcast, so as to ensure safe broadcast. However, medium and short wave broadcast channels are extremely vulnerable to natural and man-made interference, which seriously reduces the signal-to-noise ratio of broadcast content and brings great challenges to language recognition tasks. [0003] In terms of language recognition,...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a broadcast audio language recognition method, device, equipment and storage medium, which are used to solve the defect of low accuracy of broadcast audio language recognition in the prior art, reduce the influence of noise on recognition results, and improve the accuracy of language recognition sex

Images