Cloud voiceprint recognition system and method for community access control
A voiceprint recognition and voiceprint technology, applied in transmission systems, data processing applications, speech analysis, etc., can solve the problems of increasing the amount of voiceprint recognition calculation, system closure and single function, low recognition efficiency, etc., and achieve operation and maintenance costs. Low, improve the recognition efficiency, improve the effect of the recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] Embodiment 1, this embodiment proposes a voiceprint recognition system applied to community access control, refer to figure 1 , including the access control controller, client terminal and cloud server. The client terminal communicates with the access control controller and cloud server. Community users can register in advance through the client terminal, set the preset voiceprint password password statement, and send it to the cloud after the system recognizes it. The server builds a model, and then the user can speak the verification voiceprint password password statement on the access control controller. After the voice text recognition is successful, it will be sent to the cloud server, and the powerful computing power of the cloud server will be used for identification. After the recognition is successful, you can enter the community pedestrian passage and If the building unit is unsuccessful, it will send the information that the access control controller will not ...
Embodiment 2
[0079] Embodiment 2, this embodiment proposes a voiceprint recognition method applied to community access control, including the following steps:
[0080] Step A, preset voiceprint password:
[0081] Community users enter the preset voiceprint password through the client, first perform voice recognition on it; Password library, which synchronizes the cloud voiceprint password library with the device-side voiceprint password library, and the device side refers to the access control controller side;
[0082] The following methods can be used to model and analyze the preset voiceprint password through the cloud server:
[0083] (1) Voiceprint preprocessing: For the received preset voiceprint password data, remove its non-voice signal and silent voice signal, and divide the voice signal into frames;
[0084] (2) feature extraction: extract the MFCC parameter of each frame speech signal and save;
[0085] (3) Establish a voiceprint model library: train the user's Gaussian mixtur...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com