Audio tampering recognition method based on improved neural network

A neural network and recognition method technology, applied in the field of audio tampering, can solve the problems of few and insufficient research on audio tampering recognition, and achieve the effect of improving the recognition rate, good application prospects, and improving the robustness of the model.

Active Publication Date: 2022-02-01
NANJING INST OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Firstly, there is insufficient research on the characteristics of audio tampering recognition; secondly, the audio tampering recognition model, the existing audio tampering models are all traditional signal processing models, and machine learning and deep learning are rarely used for analysis

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Audio tampering recognition method based on improved neural network
  • Audio tampering recognition method based on improved neural network
  • Audio tampering recognition method based on improved neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings.

[0043] Such as Figure 1 to Figure 3 As shown, the audio tampering recognition model based on the improved neural network of the present invention comprises the following steps,

[0044] In step A, the Mel spectrogram and frame-level features are extracted from each audio, which are the input of model 1 and model 2 respectively.

[0045] In Model 1, the mel spectrogram is used as the input, because the mel spectrogram of speech shows a lot of information related to the characteristics of the sentence, and it combines the characteristics of the spectrogram and the time domain waveform to show the change of the speech spectrum over time . Since the length of each speech is different, the size of the extracted spectrogram changes with the length of the speech, and all the information of the speech is completely preserved.

[0046] In addition, in the second model, the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an audio tampering recognition algorithm based on an improved neural network, which pools spectrograms of any size into a CNNs structure represented by a spectrogram of a fixed length and an LSTM structure with an attention mechanism, and the Mel spectrogram of the signal And frame-level features are introduced into the speech tampering recognition algorithm, which integrates the spectrum and timing information of the audio signal; by adding an improved pooling layer to the CNNs structure, CNNs can input spectrograms of any size to solve the problem of unfixed audio length; increase The attention mechanism mines the weight ratio of high-level features, and finally obtains high-quality audio features; and uses the data fusion theory to carry out decision-making fusion algorithms; improves the recognition rate of audio tampering recognition and the robustness of the model. The invention can effectively identify whether the audio has been tampered with or not, and overcomes the problem of low recognition rate of traditional audio tampering.

Description

technical field [0001] The invention belongs to the field of audio tampering, and in particular relates to an audio tampering recognition method based on an improved neural network. Background technique [0002] The increasing maturity of digital audio editing technology has destroyed the authenticity and integrity of digital audio. When falsified audio is used as evidence in court, it will have a great impact on the judgment of the case. Therefore, judging whether the audio has been tampered with or not is an urgent problem to be solved by the relevant judicial departments. [0003] In 2005, Grigoras.C found that there was a power grid frequency component in the recording signal powered by mains power, and extracted the frequency characteristics of the power grid in the audio to be tested to match and compare with the data in the power grid frequency characteristic database of the power supply department. With a high degree of similarity, it is proposed for the first time...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G10L17/04G10L17/18G10L17/14G10L25/24
CPCG10L17/04G10L17/18G10L17/14G10L25/24
Inventor 包永强梁瑞宇唐闺臣王青云冯月芹朱悦
Owner NANJING INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap