Mobile phone sound record equipment source identification method
An identification method and equipment technology, applied in speech analysis, instruments, etc., can solve problems such as untested and difficult to determine the function, and achieve the effect of improving efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] The method provided by the present invention extracts features in the same way no matter for the test samples or the training samples. Wherein the test sample or training sample is a recording file obtained by collecting recordings from different mobile phones, which is stored as an uncompressed WAV format file, and several 2-second recording segments are formed after cutting.
[0041] The specific process of feature extraction for test samples or training samples is as follows:
[0042] a) The test samples / training samples are first divided into frames to obtain several frames of audio frames, and then a Hamming window is added to each frame of audio frames. Record the test sample / training sample as s, the frame length is N=256, divide the test sample / training sample into T frames of audio frames, and record each frame of audio frame as s (t) , where t=1,2,...,T is the frame number. Let H be the coefficient of the Hamming window with window size N elements. The sign...
Embodiment 2
[0059] Different devices have different ways of responding to frequencies, and their properties are usually reflected in the frequency spectrum of the audio. The analysis found that for different devices, the frequency energy of adjacent narrowbands has certain differences, and this difference exists stably. From this "band energy difference" a frequency response curve (device fingerprint) can be constructed. figure 1 It is a schematic diagram of the "frequency band energy difference characteristics" of eleven mobile devices. The audio collected with 11 devices includes the voices of 4 people (2 men and 2 women, marked M1 / M2 / F1 / F2 in the picture) and recordings at two locations (marked as places @A and @C in the picture) . It can be seen from the figure that the characteristic curves of each device under different conditions are similar in shape and have peaks and valleys at the same position, while different devices have different shapes (frequency response patterns).
[0...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com