CN105023581A - Audio tampering detection device based on time-frequency domain joint features - Google Patents
Audio tampering detection device based on time-frequency domain joint features Download PDFInfo
- Publication number
- CN105023581A CN105023581A CN201510443452.1A CN201510443452A CN105023581A CN 105023581 A CN105023581 A CN 105023581A CN 201510443452 A CN201510443452 A CN 201510443452A CN 105023581 A CN105023581 A CN 105023581A
- Authority
- CN
- China
- Prior art keywords
- voice
- audio
- detection
- pick
- frequency domain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an audio tampering detection device based on time-frequency domain joint features. The device includes an RFID authentication module mainly used for identity authentication; a signal transmission module mainly used for communication with the RFID authentication module and a signal processing module; a signal processing module used for recording device recognition and voice tempering detection on received voice information, wherein voice tempering detection is mainly realized through a tempering detection algorithm of zero insertion for zero crossing rate, EM (Expectation Maximization) algorithm-based resampling voice tempering detection and LPC model-based initiative forensicvoice tempering detection; and recording device recognition is realized through BP neural network-based multimedia mobile equipment audio tempering recognition and detection. The device provided by the invention can store frequency spectruminformation in real time and has distinctive advantages in aspects of interference rejection, multi-band frequency and precision. The device provided by the invention has high economical efficiency, reliability and practical applicability.
Description
Technical field
The present invention relates to a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature, belong to voice process technology field.
Background technology
21 century is epoch of information, and the social economy of high speed development be unable to do without informationalized fast development, and the voice signal as information processing important component part plays more and more important effect equally.The development voice process technology new along with the science and technology day different moon is applied to different social sectors more and more widely.Have benefited from the generation of varied audio edited software, a lot of people obtains some interests by distorting voice, creates certain impact to social life.Therefore, the tampering detection technology for voice evidence obtaining is arisen at the historic moment, and becomes rapidly the important research field of information security.At commercial field, dealer can gain a lot of amount of money by cheating by phone, as produce (shenglvehao)in court evidence after the voice being used at that time making profit pass through and distort by even a lot of people, escape punishing severely of law with this, therefore voice are distorted and are being played more and more important effect.Due to audio frequency forgery, distort with hidden, and a large amount of universal along with audio edited software of present stage, make the authenticity of voice and security receive very large concern.
Summary of the invention
The object of the present invention is to provide a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature, solve the existing forgery about audio frequency, distort and the authenticity of voice, complicacy and security, efficient database cannot be formed, and the specific aim detected is poor, the problem that reference value is low.
The technical solution adopted in the present invention is as follows:
Based on an audio forgery pick-up unit for time domain and frequency domain combined feature, comprising:
RFID authentication module, be mainly used in the identification realizing identity, described RFID authentication module is made up of RFID radio frequency card circuit and CLD3320 chip, described RFID radio frequency card circuit is by radio signals identification specific objective and read and write related data, carry out voice admission in early stage, described CLD3320 chip is used for the Discern and judge of voice signal; If identification is correct, then announcement information transport module carries out the transmission of voice messaging, if identification failure, does not then notify that namely information transmission modular does not carry out transmission of speech information;
Information transmission modular, is responsible on the one hand communicating with the RFID between RFID authentication module, receives the notice of RFID authentication module; Be responsible for transmitting voice information on the other hand to signal processing module;
Signal processing module, for carrying out identification and the voice tampering detection of sound pick-up outfit to the voice messaging be transferred to.
The carrier of aforesaid information transmission modular transmitting voice information is line of electric force, Wifi, bluetooth or Zigbee.
Aforesaid signal processing module carries out the voice that voice tampering detection distorts mainly for resampling and detects, and the voice that described resampling is distorted comprise zero insertion and distort, and up-sampling is distorted and distorted with interpolation.
Aforesaid speech detection of distorting zero insertion, adopts the zero insertion tampering detection algorithm realization of zero-crossing rate.
Aforesaid speech detection of distorting up-sampling, adopts the resampling voice tampering detection based on expectation maximization EM algorithm to realize.
Aforesaid speech detection of distorting interpolation, adopts the proactive forensics voice tampering detection based on linear prediction LPC model to realize.
The aforesaid identification carrying out sound pick-up outfit adopts the how dynamic equipment recording tamper Detection based on BP neural network to detect and realizes.
The characteristic parameter that aforesaid BP neural network is extracted is MFCC.
The present invention distorts and detection technique relative to other voice, it has possessed " tomography " sensation reducing and produce acoustically, zero insertion in can distorting for the resampling of voice is distorted, realize zero-crossing rate fast to detect, detect and linear prediction detection by providing expectation maximization, mode is distorted in the local that stickup was distorted and copied to solution interpolation and up-sampling; The present invention can real-time storage spectrum information, anti-interference, multiband and degree of accuracy aspect with the obvious advantage, there is higher economy, reliability and practicality.
Accompanying drawing explanation
Fig. 1 is audio forgery pick-up unit of the present invention composition structural representation;
Fig. 2 is voice tampering detection system chart of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, technical scheme of the present invention is described in detail:
As shown in Figure 1, the audio forgery pick-up unit based on time domain and frequency domain combined feature of the present invention comprises:
RFID authentication module: be mainly used in the identification realizing identity, plays the control action of system.RFID authentication module is made up of RFID radio frequency card circuit and CLD3320 chip, RFID is a kind of communication technology, related data can be read and write by radio signals identification specific objective, and without the need to the machinery set up between recognition system and specific objective or optical contact, RFID radio frequency card circuit carries out voice admission in early stage by the RFID communication technology; CLD3320 is a voice recognition chip, is mainly used in the Discern and judge of voice signal.If identification is correct, then announcement information transport module can carry out the transmission of voice messaging, if identification failure, does not then notify that namely information transmission modular does not carry out transmission of speech information.
Information transmission modular: be responsible on the one hand communicating with the RFID between RFID authentication module, namely receive the notice of RFID authentication module.Be responsible for transmitting voice information on the other hand to signal processing module, the carrier of transmitting voice information can be line of electric force, Wifi, bluetooth or Zigbee.
Signal processing module: be mainly used in analyzing the voice messaging be transferred to and exporting, comprises identification and the voice tampering detection of different sound pick-up outfit.
As shown in Figure 2, the present invention to voice tampering detection mainly for be the voice that resampling is distorted, for the voice that resampling is distorted, be divided into zero insertion to distort distorting with general up-sampling and distort with interpolation.For the detection of the voice that zero insertion is distorted, adopt the zero insertion tampering detection algorithm realization of zero-crossing rate; For the speech detection that up-sampling is distorted, the resampling voice tampering detection based on expectation maximization EM algorithm is adopted to realize; For the speech detection that interpolation is distorted, the proactive forensics voice tampering detection based on linear prediction LPC model is adopted to realize.The present invention to the identification of different sound pick-up outfit mainly for be different sound pick-up outfit splicing voice.For the voice that different sound pick-up outfit splices, the present invention adopts the how dynamic equipment recording tamper Detection based on BP neural network to detect and realizes, and the characteristic parameter that BP neural network is extracted is MFCC, final certification its there is good robustness.
Claims (8)
1., based on an audio forgery pick-up unit for time domain and frequency domain combined feature, it is characterized in that, comprising:
RFID authentication module, be mainly used in the identification realizing identity, described RFID authentication module is made up of RFID radio frequency card circuit and CLD3320 chip, described RFID radio frequency card circuit is by radio signals identification specific objective and read and write related data, carry out voice admission in early stage, described CLD3320 chip is used for the Discern and judge of voice signal; If identification is correct, then announcement information transport module carries out the transmission of voice messaging, if identification failure, does not then notify that namely information transmission modular does not carry out transmission of speech information;
Information transmission modular, is responsible on the one hand communicating with the RFID between RFID authentication module, receives the notice of RFID authentication module; Be responsible for transmitting voice information on the other hand to signal processing module;
Signal processing module, for carrying out identification and the voice tampering detection of sound pick-up outfit to the voice messaging be transferred to.
2. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 1, is characterized in that: the carrier of described information transmission modular transmitting voice information is line of electric force, Wifi, bluetooth or Zigbee.
3. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 1, it is characterized in that: described signal processing module carries out the voice that voice tampering detection distorts mainly for resampling and detects, the voice that described resampling is distorted comprise zero insertion and distort, and up-sampling is distorted and distorted with interpolation.
4. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 3, is characterized in that: described speech detection of distorting zero insertion, adopts the zero insertion tampering detection algorithm realization of zero-crossing rate.
5. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 3, is characterized in that: described speech detection of distorting up-sampling, adopts the resampling voice tampering detection based on expectation maximization EM algorithm to realize.
6. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 3, is characterized in that, described speech detection of distorting interpolation, adopts the proactive forensics voice tampering detection based on linear prediction LPC model to realize.
7. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 1, is characterized in that, described in carry out sound pick-up outfit identification adopt the how dynamic equipment recording tamper Detection based on BP neural network to detect to realize.
8. a kind of audio forgery pick-up unit based on time domain and frequency domain combined feature according to claim 7, is characterized in that, the characteristic parameter that described BP neural network is extracted is MFCC.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510443452.1A CN105023581A (en) | 2015-07-24 | 2015-07-24 | Audio tampering detection device based on time-frequency domain joint features |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510443452.1A CN105023581A (en) | 2015-07-24 | 2015-07-24 | Audio tampering detection device based on time-frequency domain joint features |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105023581A true CN105023581A (en) | 2015-11-04 |
Family
ID=54413497
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510443452.1A Pending CN105023581A (en) | 2015-07-24 | 2015-07-24 | Audio tampering detection device based on time-frequency domain joint features |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105023581A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105913856A (en) * | 2016-04-20 | 2016-08-31 | 深圳大学 | Audio tampering detection method and system based on amplitude co-occurrence vector characteristics |
CN108537014A (en) * | 2018-04-04 | 2018-09-14 | 深圳大学 | A kind of method for authenticating user identity and system based on mobile device |
CN108665905A (en) * | 2018-05-18 | 2018-10-16 | 宁波大学 | A kind of digital speech re-sampling detection method based on band bandwidth inconsistency |
CN108831506A (en) * | 2018-06-25 | 2018-11-16 | 华中师范大学 | Digital audio based on GMM-BIC distorts point detecting method and system |
CN110728991A (en) * | 2019-09-06 | 2020-01-24 | 南京工程学院 | Improved recording equipment identification algorithm |
CN110853656A (en) * | 2019-09-06 | 2020-02-28 | 南京工程学院 | Audio tampering identification algorithm based on improved neural network |
CN110853668A (en) * | 2019-09-06 | 2020-02-28 | 南京工程学院 | Voice tampering detection method based on multi-feature fusion |
CN111128234A (en) * | 2019-12-05 | 2020-05-08 | 厦门快商通科技股份有限公司 | Spliced voice recognition detection method, device and equipment |
CN115578999A (en) * | 2022-12-07 | 2023-01-06 | 深圳市声扬科技有限公司 | Method and device for detecting copied voice, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1177869A (en) * | 1996-09-25 | 1998-04-01 | 合泰半导体股份有限公司 | Remote control device with voice-sound identification function |
CN1809196A (en) * | 2006-02-06 | 2006-07-26 | 海信集团有限公司 | Mobile telephone with identity recognition and self-start by listening the environment and its implementation method |
EP1967923A3 (en) * | 2007-03-07 | 2009-10-21 | Optimal Innovations Inc | Utility control device anticipating users' needs |
CN101930737A (en) * | 2009-06-26 | 2010-12-29 | 数维科技(北京)有限公司 | Detecting method and detecting-concealing methods of error code in DRA frame |
CN102479512A (en) * | 2010-11-26 | 2012-05-30 | 深圳市丰泰瑞达实业有限公司 | Voiceprint identity authentication system based on SOPC (system on programmable chip) and voiceprint identity authentication method based on SOPC |
CN102760433A (en) * | 2012-07-06 | 2012-10-31 | 广东美的制冷设备有限公司 | Sound control remote controller and control method of networked household appliances |
CN105160368A (en) * | 2015-11-06 | 2015-12-16 | 邱钊 | Examination identity authentication system applied to big data voiceprint recognition |
-
2015
- 2015-07-24 CN CN201510443452.1A patent/CN105023581A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1177869A (en) * | 1996-09-25 | 1998-04-01 | 合泰半导体股份有限公司 | Remote control device with voice-sound identification function |
CN1809196A (en) * | 2006-02-06 | 2006-07-26 | 海信集团有限公司 | Mobile telephone with identity recognition and self-start by listening the environment and its implementation method |
EP1967923A3 (en) * | 2007-03-07 | 2009-10-21 | Optimal Innovations Inc | Utility control device anticipating users' needs |
CN101930737A (en) * | 2009-06-26 | 2010-12-29 | 数维科技(北京)有限公司 | Detecting method and detecting-concealing methods of error code in DRA frame |
CN102479512A (en) * | 2010-11-26 | 2012-05-30 | 深圳市丰泰瑞达实业有限公司 | Voiceprint identity authentication system based on SOPC (system on programmable chip) and voiceprint identity authentication method based on SOPC |
CN102760433A (en) * | 2012-07-06 | 2012-10-31 | 广东美的制冷设备有限公司 | Sound control remote controller and control method of networked household appliances |
CN105160368A (en) * | 2015-11-06 | 2015-12-16 | 邱钊 | Examination identity authentication system applied to big data voiceprint recognition |
Non-Patent Citations (3)
Title |
---|
YANNIS PANAGAKIS ETC: "Telephone handset identification by feature selection and sparse representations", 《2012 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY(WIFS)》 * |
张保生 等: "《中国证据法治发展报告》", 30 June 2013, 中国政法大学出版社 * |
朱妹丽: "三种篡改情况下的音频鉴定方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105913856A (en) * | 2016-04-20 | 2016-08-31 | 深圳大学 | Audio tampering detection method and system based on amplitude co-occurrence vector characteristics |
CN108537014A (en) * | 2018-04-04 | 2018-09-14 | 深圳大学 | A kind of method for authenticating user identity and system based on mobile device |
CN108665905B (en) * | 2018-05-18 | 2021-06-15 | 宁波大学 | Digital voice resampling detection method based on frequency band bandwidth inconsistency |
CN108665905A (en) * | 2018-05-18 | 2018-10-16 | 宁波大学 | A kind of digital speech re-sampling detection method based on band bandwidth inconsistency |
CN108831506A (en) * | 2018-06-25 | 2018-11-16 | 华中师范大学 | Digital audio based on GMM-BIC distorts point detecting method and system |
CN108831506B (en) * | 2018-06-25 | 2020-07-10 | 华中师范大学 | GMM-BIC-based digital audio tamper point detection method and system |
CN110853656A (en) * | 2019-09-06 | 2020-02-28 | 南京工程学院 | Audio tampering identification algorithm based on improved neural network |
CN110853668A (en) * | 2019-09-06 | 2020-02-28 | 南京工程学院 | Voice tampering detection method based on multi-feature fusion |
CN110728991A (en) * | 2019-09-06 | 2020-01-24 | 南京工程学院 | Improved recording equipment identification algorithm |
CN110853668B (en) * | 2019-09-06 | 2022-02-01 | 南京工程学院 | Voice tampering detection method based on multi-feature fusion |
CN110728991B (en) * | 2019-09-06 | 2022-03-01 | 南京工程学院 | Improved recording equipment identification algorithm |
CN111128234A (en) * | 2019-12-05 | 2020-05-08 | 厦门快商通科技股份有限公司 | Spliced voice recognition detection method, device and equipment |
CN111128234B (en) * | 2019-12-05 | 2023-02-14 | 厦门快商通科技股份有限公司 | Spliced voice recognition detection method, device and equipment |
CN115578999A (en) * | 2022-12-07 | 2023-01-06 | 深圳市声扬科技有限公司 | Method and device for detecting copied voice, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105023581A (en) | Audio tampering detection device based on time-frequency domain joint features | |
CN109285538B (en) | Method for identifying mobile phone source in additive noise environment based on constant Q transform domain | |
CN105741835B (en) | A kind of audio-frequency information processing method and terminal | |
CN108922518A (en) | voice data amplification method and system | |
CN105575394A (en) | Voiceprint identification method based on global change space and deep learning hybrid modeling | |
CN105874732B (en) | The method and apparatus of a piece of music in audio stream for identification | |
CN104485102A (en) | Voiceprint recognition method and device | |
CN102394062A (en) | Method and system for automatically identifying voice recording equipment source | |
CN101640043A (en) | Speaker recognition method based on multi-coordinate sequence kernel and system thereof | |
CN108281158A (en) | Voice biopsy method, server and storage medium based on deep learning | |
CN108206027A (en) | A kind of audio quality evaluation method and system | |
CN106372653A (en) | Stack type automatic coder-based advertisement identification method | |
US20160034247A1 (en) | Extending Content Sources | |
CN115116458B (en) | Voice data conversion method, device, computer equipment and storage medium | |
CN109686360A (en) | A kind of voice is made a reservation robot | |
Kawa et al. | Attack agnostic dataset: Towards generalization and stabilization of audio deepfake detection | |
CN103778917A (en) | System and method for detecting identity impersonation in telephone satisfaction survey | |
CN105283916A (en) | Digital-watermark embedding device, digital-watermark embedding method, and digital-watermark embedding program | |
CN109410946A (en) | A kind of method, apparatus of recognition of speech signals, equipment and storage medium | |
Cui et al. | Research on audio recognition based on the deep neural network in music teaching | |
Zhang et al. | Fault diagnosis method based on MFCC fusion and SVM | |
CN104882146A (en) | Method and device for processing audio popularization information | |
US11521629B1 (en) | Method for obtaining digital audio tampering evidence based on phase deviation detection | |
Bui et al. | A non-linear GMM KL and GUMI kernel for SVM using GMM-UBM supervector in home acoustic event classification | |
Sun et al. | An attention based speaker-independent audio-visual deep learning model for speech enhancement |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151104 |
|
RJ01 | Rejection of invention patent application after publication |