A mobile phone source identification method in additive noise environment based on fusion features

Abstract

The invention discloses a method for identifying the source of a mobile phone in an additive noise environment based on a fusion feature. The fusion feature composed of the MFCC feature, the STFTSDF feature extracted from the Fourier domain and the CQTSDF feature extracted from the CQT domain is used as the device fingerprint , compared with a single feature, it can more accurately characterize the device distinction information; in the training phase, a multi-scene training method is adopted. In the training set, there are not only clean speech samples without scene noise, but also different scene noise types and noise intensities. The M classification model obtained by training is universal, and can effectively identify the source of mobile phones for speech samples of known noise scenes and unknown noise scenes; it uses the deep learning CNN model to establish the M classification model. , the CNN model not only improves the source recognition accuracy of clean speech samples without adding scene noise, but also greatly improves the mobile phone source recognition effect of noisy speech samples, with strong noise robustness.

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