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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0050] Example one
[0051] Reference figure 2 , Shows a flowchart of a voice replay detection method described in Embodiment 1 of the present application, which specifically includes:
[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 obtained in advance, and a user channel model is established according to the obtained 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 other methods can be used to obtain the reserved training voice, which is not specifically restricted in this application.
[0055] Step 202: Calculate the trust score of the voice to be recognized on the user channel model.
[0056] This application uses the user channel model to score the trustworthiness of the speech to be recognized input by the user terminal, obtain the trustworthiness scor...
Example Embodiment
[0067] Example two
[0068] Reference Figure 5 , Shows a flowchart of a voice replay detection method described in Embodiment 2 of the present application, which specifically includes:
[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 sample values of the currently reserved training speech segment to obtain the energy of the current 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 reserved training speech segment of the target user.
[0073] The reserved training speech of the target user is extracted to obtain the low-energy speech segment of the reserved training speech, and the low-energy speech segment that meets the conditions is d...
Example Embodiment
[0142] Example three
[0143] See Figure 7 , Shows a structural block diagram of a voice playback device in the third embodiment of the present application, which may specifically include: a user channel module 701 for establishing a user channel model according to the reserved training voice of the target user.
[0144] The calculation module 702 is used to calculate the trust score of the voice to be recognized on the channel model of the target user.
[0145] The first judging module 703 is configured to, if the trust score is less than the set threshold, determine that the voice to be recognized has replay and return the authentication failure; otherwise, pass the replay detection.
[0146] Preferably, the user channel module includes: a first extraction module for extracting a low-energy speech segment of the target user's reserved training speech.
[0147] The multiple composite acoustic feature module is used to extract multiple composite acoustic features of the low-energy spee...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap