CN205864580U - A kind of intelligent sound capturing system - Google Patents
A kind of intelligent sound capturing system Download PDFInfo
- Publication number
- CN205864580U CN205864580U CN201620407911.0U CN201620407911U CN205864580U CN 205864580 U CN205864580 U CN 205864580U CN 201620407911 U CN201620407911 U CN 201620407911U CN 205864580 U CN205864580 U CN 205864580U
- Authority
- CN
- China
- Prior art keywords
- capturing system
- module
- main control
- control signal
- control module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Abstract
The utility model discloses a kind of intelligent sound capturing system, this capturing system includes: for receive induced signal and judge induced signal meet one pre-conditioned time produce the main control module of a control signal;The Voice decoder that described main control module input connects;The Speech comparison module of described main control module outfan connection, memory module, photographic head;Described Voice decoder connects speech transducer.Described capturing system also includes image module;This utility model not only achieves the decoding of voice, control signal is produced when the signal sensed being judged to be satisfied with pre-conditioned also by main control module, and transmit to camera chain, the photo of shooting current scene or one section of video of recording, efficiently solve the technical problem that existing capturing system is the most intelligent.
Description
Technical field
This utility model relates to mobile unit technical field, particularly relates to a kind of shooting relying on drive recorder
Head, by voice recognition, controls the intelligent sound capturing system that photographic head carries out capturing.
Background technology
Acoustic control candid photograph sends candid photograph instruction by automatic speech recognition to photographic head and realizes.Automatic speech recognition skill
Art has three ultimate principles: first, and the linguistic information in voice signal is to compile according to the time changing pattern of short-time magnitude spectrum
Code;Secondly, language can be read, i.e. its acoustic signal can not consider that speaker attempts the information content of reception and registration
In the case of, with dozens of, there is distinctive, discrete symbol and represent;Again, interactive voice is a cognitive process, thus
Can not isolate come with the grammer of language, semanteme and pragmatic structure.
Utility model content
For deficiency of the prior art, the technical problems to be solved in the utility model there are provided a kind of intelligent sound
Capturing system.
For solving above-mentioned technical problem, this utility model is realized by below scheme: a kind of intelligent sound capturing system,
This capturing system includes:
For receive induced signal and judge induced signal meet one pre-conditioned time produce the master control of a control signal
Module;
The Voice decoder being connected with main control module input;
The Speech comparison module that is connected with main control module outfan, memory module, photographic head;
Described Voice decoder connects speech transducer.
Further, described capturing system also includes:
For receiving described control signal, image module based on control signal shooting current scene photo;
Or for receiving described control signal, the image mould of video based on control signal shooting recording one predetermined amount of time
Block;
Or be used for receiving described control signal, recording a scheduled time based on control signal shooting current scene photo simultaneously
The image module of the video of section;Described image module connects main control module.
The chip model that described speech transducer is used is LM393, the chip model that described Voice decoder is used
For LM567CN, the chip model that described main control module is used is A2S60/A2S70, and memory module uses
NM27LV210VE300 memorizer.
Relative to prior art, the beneficial effects of the utility model are: this utility model not only achieves the decoding of voice,
Produce control signal when the signal sensed being judged to be satisfied with pre-conditioned also by main control module, and transmit to video camera system
System, the photo of shooting current scene or one section of video of recording, efficiently solve the technical problem that existing capturing system is the most intelligent.
Accompanying drawing explanation
Fig. 1 is this utility model intelligent sound capturing system block diagram.
Fig. 2 is this utility model intelligent sound capturing system flow chart.
Labelling in accompanying drawing: speech transducer 1, Voice decoder 2, main control module 3, Speech comparison module 4, memory module 5,
Photographic head 6.
Detailed description of the invention
Below in conjunction with the accompanying drawings preferred embodiment of the present utility model is described in detail, so that advantage of the present utility model
Can be easier to be readily appreciated by one skilled in the art with feature, thus protection domain of the present utility model is made apparent clearly
Define.
Refer to accompanying drawing 1~2, a kind of intelligent sound capturing system of the present utility model, this capturing system includes:
For receive induced signal and judge induced signal meet one pre-conditioned time produce the master control of a control signal
Module 3;
The Voice decoder 2 being connected with main control module 3 input;
The Speech comparison module 4 that is connected with main control module 3 outfan, memory module 5, photographic head 6;
Described Voice decoder 2 connects speech transducer 1.
Described capturing system also includes:
For receiving described control signal, image module based on control signal shooting current scene photo;
Or for receiving described control signal, the image mould of video based on control signal shooting recording one predetermined amount of time
Block;
Or be used for receiving described control signal, recording a scheduled time based on control signal shooting current scene photo simultaneously
The image module of the video of section, described image module connects main control module.
The chip model that described speech transducer 1 is used is LM393, and it is chip-shaped that described Voice decoder 2 is used
Number being LM567CN, the chip model that described main control module 3 is used is A2S60/A2S70, and memory module 5 uses
NM27LV210VE300 memorizer.
This utility model sound sensor equipment is mainly used in collecting the language that user sends, and is decoded by vocoder
Identify, main control module, be used for receiving described induced signal and judge described induced signal meet one pre-conditioned time generation one
Control signal;Image module, for receiving described control signal, photo based on described control signal shooting current scene or record
Make the video of a predetermined amount of time.Or for receiving described control signal, shooting current scene based on described control signal
Photo, record the video of a predetermined amount of time simultaneously.This utility model is the voice messaging sent by sensor collection user,
It is decoded identifying by solving code system, thus passes through identified content and send out decision instruction, control photographic head shooting current field
The photo of scape and video, and synchronize to store transmission to outut device.
For the pretreatment of speech recognition, then include that speech signal samples, anti aliasing bandpass filtering, removal individuality are weak in pronunciation
The influence of noise etc. that different and equipment, environment cause, and relate to choosing and end-point detection problem of speech recognition primitive.Later
Characteristic extraction procedure, it is simply that for extracting the parameters,acoustic reflecting substitutive characteristics in voice, such as average energy, average across zero
Rate, formant etc..The followed by training stage, the most before recognition by allowing talker that voice is repeated several times, from raw tone sample
Remove redundancy in Ben, retain critical data, according still further to certain rule, data are clustered, rock mechanism storehouse.It is finally
Pattern match, this is the core of whole speech recognition system, and it is known according to certain rule (such as certain distance measure) and expert
Know (such as word-building rule, grammatical rules, semantic rule etc.), calculate the similarity between input feature vector and inventory mode (as mated
Distance, likelihood probability), it is judged that the semantics information of input voice.
Key point of the present utility model is voice recognition processing, including signal sampling, anti aliasing bandpass filtering, removal
The influence of noise etc. that individual pronunciation difference and equipment, environment cause.Intelligent terminal's structure includes speech transducer, by necessarily
In the range of speech samples be acquired, and transmit to decoder, by main control module, the voice gathered processed.Intelligence
The voice messaging that terminal gathers, by decoder, removes the information of redundancy, retains critical data, transfers to Master Control Center and voice sample
The detection of this storehouse is analyzed, and phonetic order correct after analysis produces control signal thus controls photographic head and take pictures, it is achieved that intelligence
Acoustic control can capture function.
The foregoing is only preferred implementation of the present utility model, not thereby limit patent model of the present utility model
Enclose, every equivalent structure utilizing this utility model description and accompanying drawing content to be made or equivalence flow process conversion, or directly or
Connect and be used in other relevant technical field, be the most in like manner included in scope of patent protection of the present utility model.
Claims (5)
1. an intelligent sound capturing system, it is characterised in that this capturing system includes:
For receive induced signal and judge induced signal meet one pre-conditioned time produce the main control module of a control signal
(3);
The Voice decoder (2) being connected with main control module (3) input;
The Speech comparison module (4) that is connected with main control module (3) outfan, memory module (5), photographic head (6);
Described Voice decoder (2) connects speech transducer (1);
Described capturing system also includes:
For receiving described control signal, image module based on control signal shooting current scene photo;
Or for receiving described control signal, the image module of video based on control signal shooting recording one predetermined amount of time;
Or for receiving described control signal, recording a predetermined amount of time based on control signal shooting current scene photo simultaneously
The image module of video;
Described image module connects main control module.
A kind of intelligent sound capturing system the most according to claim 1, it is characterised in that: described speech transducer (1) institute
The chip model used is LM393.
A kind of intelligent sound capturing system the most according to claim 1, it is characterised in that: described Voice decoder (2) institute
The chip model used is LM567CN.
A kind of intelligent sound capturing system the most according to claim 1, it is characterised in that: described main control module (3) is made
Chip model be A2S60/A2S70.
A kind of intelligent sound capturing system the most according to claim 1, it is characterised in that: described memory module (5) uses
NM27LV210VE300 memorizer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201620407911.0U CN205864580U (en) | 2016-04-29 | 2016-04-29 | A kind of intelligent sound capturing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201620407911.0U CN205864580U (en) | 2016-04-29 | 2016-04-29 | A kind of intelligent sound capturing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN205864580U true CN205864580U (en) | 2017-01-04 |
Family
ID=57643218
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201620407911.0U Expired - Fee Related CN205864580U (en) | 2016-04-29 | 2016-04-29 | A kind of intelligent sound capturing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN205864580U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110876034A (en) * | 2018-08-30 | 2020-03-10 | 上海博泰悦臻网络技术服务有限公司 | Vehicle and driving video recording and sharing device and method thereof |
-
2016
- 2016-04-29 CN CN201620407911.0U patent/CN205864580U/en not_active Expired - Fee Related
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110876034A (en) * | 2018-08-30 | 2020-03-10 | 上海博泰悦臻网络技术服务有限公司 | Vehicle and driving video recording and sharing device and method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Makino et al. | Recurrent neural network transducer for audio-visual speech recognition | |
US20200135158A1 (en) | System and Method of Reading Environment Sound Enhancement Based on Image Processing and Semantic Analysis | |
Thomas et al. | Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions | |
CN112102850B (en) | Emotion recognition processing method and device, medium and electronic equipment | |
JP2019211749A (en) | Method and apparatus for detecting starting point and finishing point of speech, computer facility, and program | |
CN109271533A (en) | A kind of multimedia document retrieval method | |
WO2015103836A1 (en) | Voice control method and device | |
CN106328134A (en) | Prison voice data identification and monitoring early warning system | |
CN113823262B (en) | Voice recognition method and device, electronic equipment and storage medium | |
CN108917283A (en) | A kind of intelligent refrigerator control method, system, intelligent refrigerator and cloud server | |
CN109712612A (en) | A kind of voice keyword detection method and device | |
CN114267347A (en) | Multi-mode rejection method and system based on intelligent voice interaction | |
WO2014173325A1 (en) | Gutturophony recognition method and device | |
CN110136726A (en) | A kind of estimation method, device, system and the storage medium of voice gender | |
CN113628612A (en) | Voice recognition method and device, electronic equipment and computer readable storage medium | |
CN110719436A (en) | Conference document information acquisition method and device and related equipment | |
CN115273841A (en) | Voice rejection method, device, service equipment and storage medium | |
CN109065036A (en) | Method, apparatus, electronic equipment and the computer readable storage medium of speech recognition | |
CN110148418B (en) | Scene record analysis system, method and device | |
CN205864580U (en) | A kind of intelligent sound capturing system | |
CN112967733B (en) | Method and device for intelligently identifying crying type of baby | |
CN101877223A (en) | Video and audio editing system and method and electronic equipment with video and audio editing system | |
CN109686365A (en) | A kind of audio recognition method and speech recognition system | |
CN109087646B (en) | Method for leading-in artificial intelligence ultra-deep learning for voice image recognition | |
CN110660385A (en) | Command word detection method and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170104 Termination date: 20170429 |
|
CF01 | Termination of patent right due to non-payment of annual fee |