Method and system for identifying faked identity by preventing faked recordings based on voiceprint and voice
A technology of counterfeit identity and identification method, which is applied in the field of computer and information services, can solve the problems of poor user experience, affecting the performance of voiceprint recognition and speech recognition, and poor recognition performance, so as to prevent the intrusion and identity of fake recordings Verify the effect of stable and reliable threshold adjustment
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0078] Example 1, see image 3 , This embodiment discloses a voiceprint and voice-based anti-recording fake identity recognition method, including the following steps:
[0079] (1) Establish the user's voiceprint model and voice model according to the voice of the user reading the prompt text, specifically:
[0080] (11) Generate fixed text with user ID;
[0081] (12) Combine fixed text with user ID and random text into prompt text;
[0082] (13) Collect the voice of the user to read the prompt text;
[0083] (14) Determine whether the voice in step (13) meets the length of the generated voiceprint model and the length of the voice model, if so, go to step (15), otherwise return to step (12);
[0084] (15) Establish the user's voiceprint model and voice model, and save the fixed text and voiceprint model and voice model with the user ID.
[0085] For example, the fixed text with user ID is 4-7 Chinese characters, preferably a 4-character or 7-character phrase, idiom or allegorical.
[0086...
Example Embodiment
[0099] Example 2, see Figure 4 , This embodiment discloses a voiceprint and voice-based anti-recording fake identity recognition method, including the following steps:
[0100] (1) Establish the user's voiceprint model and voice model according to the voice of the user reading the prompt text, specifically:
[0101] (11) Generate fixed text with user ID;
[0102] (12) Combine fixed text with user ID and random text into prompt text;
[0103] (13) Collect the voice of the user to read the prompt text;
[0104] (14) Determine whether the voice in step (13) meets the length of the generated voiceprint model and the length of the voice model, if so, go to step (15), otherwise return to step (12);
[0105] (15) Establish the user's voiceprint model and voice model, and save the fixed text and voiceprint model and voice model with the user ID.
[0106] For example, the fixed text with user ID is 4-7 Chinese characters, preferably a 4-character or 7-character phrase, idiom or allegorical.
[010...
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