Digital audio watermark detection method and device

Abstract

The present invention provides a digital audio watermark detection method and device, wherein the digital audio watermark detection method comprises: acquiring an audio file to be detected, inputting the audio file to be detected into a watermark detection module for processing, and obtaining the audio file to be detected The amplitude spectrum corresponding to the file without adding the preset watermark load information, the ratio sequence of the amplitude spectrum of the audio file to be detected and the corresponding amplitude spectrum without adding the preset watermark load information is input into the watermark decoding module for processing. processing, to obtain load information of the audio file to be detected; determining whether the audio file to be detected contains preset watermark information according to the load information. The invention also provides a digital audio watermark detection device. The digital audio watermark detection method and device of the present invention can not only improve the attack resistance of the watermark, but also ensure the detection of watermarked audios added with the same scheme but with different parameters.

Description

technical field [0001] This specification relates to the technical field of audio processing, and in particular, to a method and device for detecting digital audio watermarks. Background technique [0002] The audio digital watermark is a segment of identification generated or embedded based on the audio digital content, which can be used to identify the copyright attribution of the audio digital content, and can also be used to protect the integrity of the audio digital content. When the audio watermark is used to identify the copyright ownership of the audio digital content, the audio watermark is added to the audio digital content in an imperceptible and non-peelable way during the whole life cycle of the generation, management, distribution and use of the audio digital content. In the case of copyright disputes, the copyright ownership of the audio digital content can be proved only by extracting the embedded watermark information from the audio digital content. Similar...

AI Technical Summary

Problems solved by technology

6) In principle, the detection of the watermark should not require the original audio, that is, to achieve blind detection, because it is very difficult to find the original audio

After the digital watermark is attacked, the usual detection method cannot fully detect whether the digital audio has been added with a preset watermark, so that the watermark becomes invalid

Images