CN105336330A - Simple voice recognizing system - Google Patents
Simple voice recognizing system Download PDFInfo
- Publication number
- CN105336330A CN105336330A CN201510663604.9A CN201510663604A CN105336330A CN 105336330 A CN105336330 A CN 105336330A CN 201510663604 A CN201510663604 A CN 201510663604A CN 105336330 A CN105336330 A CN 105336330A
- Authority
- CN
- China
- Prior art keywords
- voice
- controller
- module
- collection module
- actuator
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a simple voice recognizing system. The simple voice recognizing system consists of a voice acquiring module, a triggering module, a controller, a memory and an actuator, wherein the voice acquiring module is used for acquiring voice signals; the triggering module is used for accumulating signals outputted by the voice acquiring module and transmitting triggering signals after a threshold value is achieved, so that the controller begins to work; the memory stores voice command data required to be recognized; the controller is used for carrying out analog-to-digital conversion on the voice data and then recognizing the voice data; and the actuator is used for actuating control signals transmitted from the controller. The simple voice recognizing system is low in cost and easy to implement, has the advantages of low power consumption and small size, and is particularly suitable for applications which have few recognition commands and are sensitive to costs and volumes.
Description
Technical field
The present invention relates to a kind of recognition system, particularly relate to a kind of simple speech recognition system.
Background technology
Speech recognition application is in modern society more and more frequent, and people also often can use the sci-tech product with speech identifying function in life.Such as voice are made a phone call, voice create message, Voice command TV etc.By articulation type classification, can be divided into isolated word recognition, connection string and continuous speech recognition etc., the algorithm of identification has dynamic time warping, vector quantization, hidden Markov model, artificial neural network etc.Under constantly studying, speech recognition obtains considerable progress, and discrimination and identification range are greatly improved, but the recognition system more complicated of these algorithms, and require higher to chip computing power, the networking that even needs had realizes.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of simple speech recognition system, and its structure is simple, requires lower to chip computing power.
The present invention solves above-mentioned technical matters by following technical proposals: a kind of simple speech recognition system, it is characterized in that, it is made up of voice collection module, trigger module, controller, storer and actuator, and wherein voice collection module is responsible for gathering voice signal; The signal that trigger module is responsible for voice collection module exports adds up, and sends trigger pip, controller is started working after reaching threshold value; Storer stores the voice command data needing to identify; Controller is responsible for identifying after speech data analog-to-digital conversion; Actuator is responsible for the control signal that implementation controller sends.
Preferably, described voice collection module is connected with trigger module, and voice collection module, trigger module are all connected with storer, and storer, controller, actuator connect successively.
Preferably, described voice collection module is microphone.
Positive progressive effect of the present invention is: the present invention is with low cost, easily realizes, and has low-power consumption, feature that volume is little, be particularly suitable for recognition command less, to cost and the more sensitive application of volume, as signal light control, home wiring control etc.
Accompanying drawing explanation
Fig. 1 is the theory diagram of simple speech recognition system of the present invention.
Fig. 2 is the workflow diagram of simple speech recognition system of the present invention.
Embodiment
Present pre-ferred embodiments is provided, to describe technical scheme of the present invention in detail below in conjunction with accompanying drawing.
As shown in Figure 1, simple speech recognition system of the present invention is made up of voice collection module, trigger module, controller, storer and actuator, wherein voice collection module is responsible for gathering voice signal, namely adopt microphone that voice are changed into electric signal, because external interference is more, signal is fainter, needs to carry out filter and amplification to signal; The signal that trigger module is responsible for voice collection module exports adds up, and sends trigger pip, controller is started working after reaching threshold value; Controller and storer are the system cores, and storer stores the voice command data needing to identify, namely order voice are at the frequency of each time period and frequency change rate; Controller is responsible for identifying after speech data analog-to-digital conversion; Actuator is responsible for the control signal that implementation controller sends.Voice collection module is connected with trigger module, and voice collection module, trigger module are all connected with storer, and storer, controller, actuator connect successively.Voice collection module can be microphone.Trigger module can be trigger.
For Voice command light, need the statement of identification little, be limited to "ON", "Off", " lightening ", " dimmed " etc.These need the speech waveform data in advance of recognition command to preserve in memory.Because statement is little, storer is also very little, reduces cost.Speech data collected by microphone, voice amplitude when the external world reaches threshold range at certain hour, and trigger sends trigger pip, namely sends an interruption to controller, controller is in dormant state at ordinary times with power saving, to wake up from dormancy when having no progeny in receiving, by analog to digital converter sampled speech data, and the speech data in these speech datas and storer being compared, if comparative result meets, then send corresponding control command actuate actuators to perform, such as, turn off the light, turn on light.If do not meet all orders prestored, then dormancy waits for that next time identifies again.The detailed process of speech recognition is as shown in Figure 2: first extract the speech data that gathers at the frequency of each time period and frequency change rate.Then frequency and the frequency change rate of the order speech data in storer is read, the frequency values of more each time period two speech datas, if difference exceedes threshold value, the start time window of adjustment image data, compares with the frequency values of each time period of the order speech data stored again.If the difference that repeatedly adjustment starts to compare after window has also been above threshold value, then think that the signal that receives and pre-stored command do not mate.If the difference of frequency does not all exceed threshold value in all time periods, then continue the frequency change rate comparing two data, if also do not exceed threshold value, then think the order that have received and prestore, carry out corresponding action according to the different driving actuator of order.Such as have received "ON" instruction, then drive relay to light electric light.Have received "Off" instruction, then drive relay disconnecting circuit.The benefit of this speech recognition is that algorithm is simple, and only need comparison signal at the frequency of each time period and frequency change rate, common single-chip microcomputer can be competent at, because operand is little, power consumption is also little, and is in dormant state due to single-chip microcomputer at ordinary times, can reduce power consumption further.Therefore the power supply of system can adopt compact battery, reduces system bulk.Further, this recognition methods can also get rid of statement interference, such as user is when shut the gate is mentioned in chat at ordinary times, although "Off" statement and the commands match prestored, but frequency and the frequency change rate of the time period of follow-up " door " word upper pre-stored command are all 0, do not mate with the data collected, therefore also can not close electric light.
The present invention is with low cost, easily realizes, and has low-power consumption, feature that volume is little, be particularly suitable for recognition command less, to cost and the more sensitive application of volume, as signal light control, home wiring control etc.
Above-described specific embodiment; the technical matters of solution of the present invention, technical scheme and beneficial effect are further described; be understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (3)
1. a simple speech recognition system, is characterized in that, it is made up of voice collection module, trigger module, controller, storer and actuator, and wherein voice collection module is responsible for gathering voice signal; The signal that trigger module is responsible for voice collection module exports adds up, and sends trigger pip, controller is started working after reaching threshold value; Storer stores the voice command data needing to identify; Controller is responsible for identifying after speech data analog-to-digital conversion; Actuator is responsible for the control signal that implementation controller sends.
2. simple speech recognition system as claimed in claim 1, it is characterized in that, described voice collection module is connected with trigger module, and voice collection module, trigger module are all connected with storer, and storer, controller, actuator connect successively.
3. simple speech recognition system as claimed in claim 1, it is characterized in that, described voice collection module is microphone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510663604.9A CN105336330A (en) | 2015-10-15 | 2015-10-15 | Simple voice recognizing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510663604.9A CN105336330A (en) | 2015-10-15 | 2015-10-15 | Simple voice recognizing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105336330A true CN105336330A (en) | 2016-02-17 |
Family
ID=55286817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510663604.9A Pending CN105336330A (en) | 2015-10-15 | 2015-10-15 | Simple voice recognizing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105336330A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536413A (en) * | 2017-03-06 | 2018-09-14 | 北京君正集成电路股份有限公司 | A kind of audio data collecting method and apparatus |
| CN108536412A (en) * | 2017-03-06 | 2018-09-14 | 北京君正集成电路股份有限公司 | A kind of audio data collecting method and apparatus |
| CN110046045A (en) * | 2019-04-03 | 2019-07-23 | 百度在线网络技术（北京）有限公司 | The data package processing method and device that voice wakes up |
| WO2019221667A1 (en) * | 2018-05-18 | 2019-11-21 | Schneider Electric Asia Pte Ltd | A relay device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102665319A (en) * | 2012-03-21 | 2012-09-12 | 北京百纳威尔科技有限公司 | Control system and method for illuminating lamp of mobile terminal device and mobile terminal device |
| CN103295572A (en) * | 2012-08-13 | 2013-09-11 | 深圳市路畅科技股份有限公司 | Speech recognition method and car-mounted multimedia navigator system with speech recognition function |
| CN103761967A (en) * | 2014-01-08 | 2014-04-30 | 上海应用技术学院 | Embedded speech recognition system |
| US20150046161A1 (en) * | 2013-08-07 | 2015-02-12 | Lenovo (Singapore) Pte. Ltd. | Device implemented learning validation |
| CN104599669A (en) * | 2014-12-31 | 2015-05-06 | 乐视致新电子科技（天津）有限公司 | Voice control method and device |
| CN104900228A (en) * | 2015-04-30 | 2015-09-09 | 重庆理工大学 | Suspicious door opening sound identification apparatus and identification method |
-
2015
- 2015-10-15 CN CN201510663604.9A patent/CN105336330A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102665319A (en) * | 2012-03-21 | 2012-09-12 | 北京百纳威尔科技有限公司 | Control system and method for illuminating lamp of mobile terminal device and mobile terminal device |
| CN103295572A (en) * | 2012-08-13 | 2013-09-11 | 深圳市路畅科技股份有限公司 | Speech recognition method and car-mounted multimedia navigator system with speech recognition function |
| US20150046161A1 (en) * | 2013-08-07 | 2015-02-12 | Lenovo (Singapore) Pte. Ltd. | Device implemented learning validation |
| CN103761967A (en) * | 2014-01-08 | 2014-04-30 | 上海应用技术学院 | Embedded speech recognition system |
| CN104599669A (en) * | 2014-12-31 | 2015-05-06 | 乐视致新电子科技（天津）有限公司 | Voice control method and device |
| CN104900228A (en) * | 2015-04-30 | 2015-09-09 | 重庆理工大学 | Suspicious door opening sound identification apparatus and identification method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536413A (en) * | 2017-03-06 | 2018-09-14 | 北京君正集成电路股份有限公司 | A kind of audio data collecting method and apparatus |
| CN108536412A (en) * | 2017-03-06 | 2018-09-14 | 北京君正集成电路股份有限公司 | A kind of audio data collecting method and apparatus |
| CN108536412B (en) * | 2017-03-06 | 2021-01-08 | 北京君正集成电路股份有限公司 | Audio data acquisition method and equipment |
| WO2019221667A1 (en) * | 2018-05-18 | 2019-11-21 | Schneider Electric Asia Pte Ltd | A relay device |
| CN112437955A (en) * | 2018-05-18 | 2021-03-02 | 施耐德电气公司亚洲 | Relay device |
| CN110046045A (en) * | 2019-04-03 | 2019-07-23 | 百度在线网络技术（北京）有限公司 | The data package processing method and device that voice wakes up |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3522153B1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
| CN105336330A (en) | Simple voice recognizing system | |
| CN103529726A (en) | Intelligent switch with voice recognition function | |
| CN104866067A (en) | Low power consumption control method and electronic device | |
| CN206259172U (en) | Voice control system | |
| CN104766462A (en) | Sound wave remote control system and sound wave remote control method | |
| CN107357174A (en) | A kind of distributed intelligence audio amplifier speech control system | |
| CN210836546U (en) | Infrared power saving module of voice system microwave sound wave | |
| CN207181990U (en) | A kind of distributed intelligence audio amplifier speech control system | |
| CN204013463U (en) | The power switching circuit of nonspecific voice identification of a kind of single live wire | |
| CN203134110U (en) | Ceiling lamp type intelligent charging voice remote controller | |
| CN203552695U (en) | Voice control system of electric curtain | |
| CN109036415A (en) | A kind of speech control system of intelligent refrigerator | |
| CN202714700U (en) | Voice-control electric curtain | |
| CN107450499A (en) | A kind of intelligent home control system | |
| CN204516039U (en) | A kind of multifunctional remote controlller | |
| WO2018023518A1 (en) | Smart terminal for voice interaction and recognition | |
| CN208188598U (en) | A kind of intelligent home voice group control system | |
| CN203909526U (en) | Switch based on technology of voice wakeup | |
| CN202679498U (en) | Television set capable of controlling switching with voice | |
| CN215594274U (en) | Double-microphone offline voice module applied to intelligent closestool | |
| CN205247898U (en) | Intelligence speech control box | |
| CN213650714U (en) | Voice-controlled classification garbage can | |
| CN108510980A (en) | A kind of voice identification control method learnt | |
| CN204496692U (en) | A kind of sound wave remote controlling system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160217 |