Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Voice playback detection method and device

A detection method and voice technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as voice replay, and achieve the effect of avoiding replay attacks

Active Publication Date: 2016-06-22
TSINGHUA UNIV +1
View PDF16 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a recording playback detection method and device to solve the problem of voice playback in speaker recognition technology

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
  • Voice playback detection method and device
  • Voice playback detection method and device
  • Voice playback detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] refer to figure 2 , which shows a flow chart of a voice playback detection method described in Embodiment 1 of the present application, specifically including:

[0052] Step 201: Establish a user channel model according to the reserved training voice of the target user.

[0053] The reserved training voice of the target user is acquired in advance, and a user channel model is established according to the acquired reserved training voice of the target user.

[0054] The reserved training voice can be obtained from the background server or the client of the target user, or can be obtained in other ways, which is not specifically limited in this application.

[0055] Step 202: Calculate the trust score of the speech to be recognized on the user channel model.

[0056] This application uses the user channel model to score the trust degree of the speech to be recognized input by the user terminal, obtain the trust degree score of the speech to be recognized, and judge whe...

Embodiment 2

[0068] refer to Figure 5 , which shows a flow chart of a voice playback detection method described in Embodiment 2 of the present application, specifically including:

[0069] Step 501: Establish a user channel model according to the reserved training voice of the target user.

[0070] Step 501 includes the following sub-steps:

[0071] Sub-step 5011: Calculate the sum of the squares of the sampling values ​​of the currently reserved training speech segment to obtain the energy of the currently reserved training speech segment. If the energy is lower than the set threshold, the training speech segment is determined to be a low-energy speech segment.

[0072] Sub-step 5012: extract the low-energy speech segment of the target user's reserved training speech segment.

[0073] Extract the reserved training speech of the target user to obtain the low-energy speech segment of the reserved training speech, and use the short-term energy algorithm to detect the low-energy speech seg...

Embodiment 3

[0143] see Figure 7 , shows a structural block diagram of a voice playback device in Embodiment 3 of the present application, which may specifically include: a user channel module 701, configured to establish a user channel model according to the reserved training voice of the target user.

[0144] Calculation module 702, configured to calculate the trust score of the speech to be recognized on the channel model of the target user.

[0145] The first judging module 703 is configured to determine that the speech to be recognized is replayed if the trust score is less than the set threshold, and return authentication failure; otherwise, pass the replay detection.

[0146] Preferably, the user channel module includes: a first extraction module, configured to extract a low-energy speech segment of the target user's reserved training speech.

[0147] The multi-composite acoustic feature module is used to extract the multi-composite acoustic features of the low-energy speech segme...

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 application discloses a voice playback detection method and device. The method comprises the steps of establishing a user channel model according to the reserved training voice of a target user; calculating the trust degree score of the to-be-recognized voice on the user channel model; if the trust degree score is less than a set threshold value, determining that the to-be-recognized voice needs to play back, and the return authentication is unsuccessful; on the contrary, passing the playback detection, thereby solving the voice playback attack problem in a current voiceprint recognition technology.

Description

technical field [0001] The present application relates to the technical field of computer information services, in particular to a voice playback detection method and device. Background technique [0002] Speaker recognition technology, also known as voiceprint recognition technology, is mainly based on the information of the speaker's personality characteristics contained in the voice, using computers and various information recognition technologies to automatically realize the confirmation of the speaker's identity. [0003] In recent years, with the rapid development of the Internet, voice as a non-contact information carrier, people can rely on various mobile terminal devices, such as: mobile phones, microphones and IP phones, to complete voice collection anytime and anywhere, and through the network Transmission and background server to realize human-computer interaction and speaker identification. [0004] With the advent of the mobile Internet era, while providing co...

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
IPC IPC(8): G10L25/60G10L15/06G10L15/01G10L19/02
Inventor 郑方李蓝天邬晓钧王小钢刘乐
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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