A voice-driven password monitoring system and method
A password and voice technology, which is applied in the field of password testing and monitoring systems, can solve problems such as incorrect transmission of voice information, missing voice information collection and utilization, etc., to save storage space, improve robustness and automation, and improve query efficiency Effect
Active Publication Date: 2021-10-01
BEIJING INST OF ASTRONAUTICAL SYST ENG +1
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing fault diagnosis and health monitoring systems mostly use real-time collection of equipment data for interpretation. The system lacks the collection and utilization of voice information in the testing process, and usually makes judgments by manually listening to passwords. Problems due to miscommunication of voice messages
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0042] (1), system overview
[0043] The functions of the speech recognition system include speech preprocessing, speech recognition, user-defined thesaurus, speech analysis, and speech result storage and query functions.
[0044] Such as figure 1As shown, a kind of voice-driven testing and issuing password monitoring system provided by the present invention includes N terminal acquisition devices and voice recognition servers, and N is greater than or equal to 1. In actual use, there will be a situation where multiple people issue voice passwords at the same time. When N is greater than 1.
[0045] 1. Terminal collection equipment
[0046] The N terminal collection devices collect externally input voice passwords through microphones, and send the voice passwords to the voice recognition server.
[0047] The microphone of the terminal acq...
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
Login to View More Abstract
The present invention relates to a system and method for detecting and issuing passwords based on voice drive. A multi-threaded concurrent model is adopted, and N-channel audio signals corresponding to voice passwords conforming to the preset grammar file structure are cyclically monitored, and each time a channel of audio input is detected , record the current moment as the corresponding voice password receiving time of the audio input, open a voice processing sub-thread to perform the following steps: (1), the audio signal is preprocessed, the noise in the audio signal is eliminated, and the audio signal is audio segmented, Waveform conversion, extracting the feature vector corresponding to each word, using the feature vector, combined with the user-defined password lexicon, converting the voice password into password text information and storing it; (2), according to the preset grammar file structure, Semantic analysis is performed on the password text information, word segmentation is performed on the password text information, and the testing and issuing password information is recognized, and the testing and issuing password information is converted into a state quantity. The invention improves the robustness and automaticity of the sending and testing process.
Description
technical field [0001] The invention relates to a voice-driven testing and issuing password monitoring system and method, belonging to the technical field of voice recognition. Background technique [0002] Speech recognition means converting the content and meaning of human speech into computer-readable input, such as keystrokes, binary codes, or character sequences. This differs from speaker recognition, which is primarily about identifying and validating the person speaking rather than what is contained in it. The purpose of speech recognition is to allow machines to understand the spoken language of humans, which includes two meanings: the first is to understand word by word instead of converting it into written language; the second is to interpret the commands or requests contained in the spoken language. To understand, to respond correctly, not just stick to the correct conversion of all words. [0003] In the launch test process of the launch vehicle, fault diagnosi...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/22
Inventor 朱骋王伟李璨卢頔汪文明徐昊张学英易航李东王珏杨虎军娄路亮宋跃忠胡元威王晔
Owner BEIJING INST OF ASTRONAUTICAL SYST ENG