Cell phone source recognizing method under additive noise environment based on fusion features

Abstract

The invention discloses a cell phone source recognizing method under an additive noise environment based on fusion features. The method includes the steps of using the fusion features composed of MFCCfeatures extracted from a Fourier domain, STFTSDF features and CQTSDF features extracted from a CQT domain as device fingerprints so that device differentiation information can be more precisely represented compared with a single feature; training an obtained M classification model to have universality through a multi-scene training mode in the training stage and conducting effective cell phone source recognizing on voice samples in known noise scenes and unknown noise scenes, wherein a training group contains clean voice samples without scene noises and also contains noise-containing voice samples with different scene noise types and noise intensities. The M classification model is established through a deep learning CNN model, and by means of the CNN model, the source recognizing accuracy of the clean voice samples without the scene noises is improved, the cell phone source recognizing effect of the noise-containing voice samples is greatly improved, and noise robustness is high.

Description

technical field [0001] The invention relates to the technical field of mobile phone source identification, in particular to a method for identifying mobile phone source in an additive noise environment based on fusion features. Background technique [0002] With the development of information technology, easy-to-carry mobile phones are becoming more and more popular, and many people are accustomed to using mobile phones to record voices. Therefore, research on source identification based on mobile phone recording devices has received extensive attention. In recent years, some research results have been obtained on the source identification of mobile phone recording equipment based on quiet environment. [0003] C.Hanilci et al. extracted the Mel-frequency cepstral coefficient (MFCC) from the recording file as the distinguishing feature of the device, and compared the recognition of the device by the two classifiers SVM and VQ. The set recognition rate analysis found that th...

AI Technical Summary

Problems solved by technology

[0004] Although the mobile phone source identification algorithm has made some progress, there are still some limitations. The main manifestations are: misrecognition of different models of mobile phones of the same brand, because the recording equipment of the same brand of mobile phones has a high degree of similarity in circuit design and selection of electronic components. Consistency and consistency, resulting in small differences in device information embedded in voice files, making it difficult to identify; at present, the background of mobile phone source identification applications is basically in a quiet environment, while recordings in real life are more likely to be formed in different noise environments , the environmental noise will affect the device recognition performance, which leads to the poor robustness of the existing research algorithms in the case of noise attacks

Images