Method and system for automatically identifying voice recording equipment source

A technology of recording equipment and recognition methods, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of blurred information of recording equipment, and achieve the effect of high efficiency and low complexity

Inactive Publication Date: 2012-03-28
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In such a case, it is ambiguous to use the extracted features to represent the recording device information
Moreover, Naive Bayesian classifiers cannot be used to identify a large number of recording devices

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
  • Method and system for automatically identifying voice recording equipment source
  • Method and system for automatically identifying voice recording equipment source
  • Method and system for automatically identifying voice recording equipment source

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0111] The source recognition experiment of 9 groups of recording equipment datasets selected in embodiment 1;

[0112] The present invention is as shown in table 3 to the recognition result of 9 kinds of equipment data sets that embodiment 1 selects:

[0113] The recognition result (%) of 9 kinds of different recording equipment data sets that table 3 embodiment 1 selects

[0114] Model\Test

[0115] The diagonal line of the above-mentioned recording equipment source recognition matrix represents the correct recognition rate of each type of equipment, and the others are the result of misidentification. The average correct recognition rate of these 9 kinds of recording equipment is 98.34%, which shows that the present invention can improve the accuracy of the recording equipment source. Identification is valid. The DEV-GMM used in this embodiment can better fit the feature space distributions of multiple recording devices, so better results can be obtained.

Embodiment 2

[0117] Example 2 Source identification experiment of two types of data sets of the same type of microphone but different types of data acquisition equipment, and the same type of data acquisition equipment with different types of microphones

[0118] The present invention is as shown in table 5 to the recognition result of 9 kinds of equipment data sets that embodiment 2 selects:

[0119] Table 4 Recording device source identification experiments of two types of data sets (%)

[0120]

[0121] The shaded part in Table 4 is the most important part of the error rate. The upper part is just the recognition result of the same kind of acquisition equipment, and the lower part is just the recognition result of the same kind of microphone, indicating that the error rate within their class is greater than that of both of them. Error rate between classes. On the other hand, the error rate of different microphone recognition of the same acquisition device is slightly higher than the...

Embodiment 3

[0122] Embodiment 3 investigates the impact of different factors on the recording equipment source identification system

[0123] When carrying out this part of the test, only one of the factors was changed at a time, while other parameters remained consistent with those in Example 1 and Example 2. The following test uses the data sets of 9 kinds of equipment in the first part of the embodiment unless otherwise specified.

[0124] (1) The influence of the general background established by different databases on the recognition results

[0125] In order to verify the feasibility and validity of the method for establishing the device universal background model (DEV-UBM) of the present invention on different databases. Select two groups from the above four databases to retrain the general background model. The selected idea is to combine dynamic microphones and condenser microphones, so that the general background can cover these two types of commonly used microphone types, and ...

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 relates to the technical fields of intelligent voice signal processing, mode identification and artificial intelligence, and in particular relates to a method and system for automatically identifying a voice recording equipment source. The method comprises the following steps of: a, extracting a characteristic of voice recording equipment from a voice signal; b, constructing a statistical model of the voice recording equipment by using a Gaussian mixture model-universal background model (GMM-UBM); and c, performing classification judgment by using a normalized likelihood as a final score. Different voice recording equipment can comprise different equipment noises; in the method and the system, the characteristics of the voice recording equipment are extracted by using silence fields and the statistical model of the voice recording equipment is constructed so as to perform the classification and identification on the equipment. By the technical scheme in the embodiment of the invention, the extracted characteristic dimension, the computing complexity and the error identification rate are low.

Description

technical field [0001] The invention relates to the technical fields of intelligent voice signal processing, pattern recognition and artificial intelligence, in particular to a method and system for automatic recording device source recognition. Background technique [0002] With the continuous development of computer technology, powerful digital multimedia editing software makes it easier to modify and edit digital audio, image and video data. Although most people modify and edit digital multimedia just to enhance its performance, there are also some people who intentionally or even maliciously spread some carefully tampered and forged multimedia data for various purposes. Once tampered multimedia data is widely used in official media, scientific discoveries, insurance and court evidence, it will undoubtedly have a serious impact on various aspects of society, politics and military affairs. Therefore, there is a need for an objective, impartial, and capable multimedia veri...

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 Applications(China)
IPC IPC(8): G10L15/02G10L15/06G10L21/02G10L21/0208
Inventor 贺前华王志锋罗海宇沈秉乾
Owner SOUTH CHINA UNIV 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