CN202600936U - Remote controller with voice function - Google Patents
Remote controller with voice function Download PDFInfo
- Publication number
- CN202600936U CN202600936U CN 201120569359 CN201120569359U CN202600936U CN 202600936 U CN202600936 U CN 202600936U CN 201120569359 CN201120569359 CN 201120569359 CN 201120569359 U CN201120569359 U CN 201120569359U CN 202600936 U CN202600936 U CN 202600936U
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- telepilot
- signal
- phonetic function
- 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
Images
Abstract
The utility model relates to a remote controller with a voice function. The remote controller comprises a voice acquisition module and a voice recognition module, wherein the voice acquisition module transmits an acquired voice signal to a voice preprocessing module and performs noise reduction and signal amplification processing; and the voice recognition module performs pattern matching on the voice signal transmitted by the voice preprocessing module and converts the matched result into an electric signal through a recognition circuit; and the electric signal is compared with a control command relationship which is pre-stored in a storage module through a control module, and the comparison result is converted into a control command for output. According to the technical scheme, both hands of a player are relaxed, so that the player can naturally operate the game equipment, and the game experience can be brought to the player.
Description
Technical field
The utility model relates to a kind of speech recognition technology, particularly a kind of game control technology.
Background technology
Speech recognition is a cross discipline.Recent two decades comes, and speech recognition technology is obtained marked improvement, begins to move towards market from the laboratory.People estimate that in following 10 years, speech recognition technology will get into every field such as industry, household electrical appliances, communication, automotive electronics, medical treatment, home services, consumption electronic product.The speech recognition dictation machine is chosen as one of ten major issues of computing machine development in 1997 in the application in some fields by US News circle.A lot of experts think that speech recognition technology is one of areas of information technology ten big important developments in science and technology technology in the period of 2000 to 2010.The related field of speech recognition technology comprises: signal Processing, pattern-recognition, theory of probability and information theory, sound generating mechanism and hearing mechanism, artificial intelligence or the like.
Carry out speech exchange with machine, let machine understand what people say, this is the thing that people dream of for a long time.Speech recognition technology is exactly to let machine change voice signal into through identification and understanding process the hi-tech of corresponding text or order.Speech recognition technology mainly comprises Feature Extraction Technology, pattern match criterion and three aspects of model training technology.Speech recognition technology has also obtained quoting fully in the car networking, for example in the networking of wing truck, only needs with contact staff's oral account the destination can be set by a key and directly navigates, and is safe, convenient.
The inventor finds in invention the utility model process: present telepilot does not possess speech identifying function; Existing recreation is mostly controlled based on traditional mouse, keyboard, handle button, rocking bar etc.; When the complicacy sports class that needs a large amount of buttons to accomplish is played, because multiple factor player may be in a rush.But speech recognition application can be alleviated player's burden greatly in recreation.Such as use as the player can recognizing voice telepilot when playing the FPS recreation; Can accomplish the respective operations in the recreation through barking out voice passwords such as " squatting down ", " aiming ", " shooting ", control thereby no longer rely on keyboard, mouse handle button, rocking bar.The game experiencing that certain this voice operating brings also is brand-new.
The inventor is based on being engaged in this type of product design manufacturing abundant for many years practical experience and professional knowledge; And the utilization of cooperation scientific principle; Actively study innovation; In the hope of the stripped sense of the low coverage interactive device of founding a kind of new structure, can overcome the problem of the popularization existence of existing somatic sensation television game, make it have more practicality.Through constantly research, design, and, found out the utility model of true tool practical value finally through after studying sample and improvement repeatedly.
Summary of the invention
The purpose of the utility model is, comes the mode of operate game to bring better game experiencing to the player through voice.Technical matters to be solved is, how with speech recognition and convert digital signal into and be mapped to control recreation on the keyboard.This invention helps the popularization of speech recognition, is very suitable for practicality.
The purpose of the utility model and solve its technical matters and can adopt following technical scheme to realize.
According to a kind of telepilot that has phonetic function that the utility model proposes, said a kind of telepilot that has phonetic function comprises: voice acquisition module: be used to gather voice signal and be transferred to the voice pre-processing module; Voice pre-processing module: the voice signal that receives is carried out denoising, signal processing and amplifying; Sound identification module: the voice signal after the processing that will receive carries out pattern match, and the result that will match outputs to identification circuit; Identification circuit: convert the voice signal that matches to electric signal; Memory module: be used for storaged voice template data, control command corresponding relation data etc.; Control module: with electric signal be pre-stored in memory module in corresponding the comparing of control command relation, and convert comparing result to system order back output.
The purpose of the utility model and solve its technical matters and can also adopt following technical measures to come further to realize.
Preferable, aforesaid a kind of telepilot that has phonetic function, wherein said a kind of telepilot that has phonetic function also comprises: the power module that electric power resource is provided.
Preferable, aforesaid a kind of telepilot that has phonetic function, wherein said voice acquisition module can be a microphone.
Preferable, aforesaid a kind of telepilot that has phonetic function, wherein said a kind of telepilot that has phonetic function also comprises: wave point.
Preferable; Aforesaid a kind of telepilot that has phonetic function, wherein said wave point also comprises: based on the wave point of bluetooth, based on the wave point of 2.4GHz, based on the wave point of WIFI and based in the infrared wave point at least one.
By technique scheme; A kind of telepilot that has phonetic function of the utility model has advantage and beneficial effect at least: the utility model is gathered voice signal and is converted control command control recreation to through utilizing telepilot; Thereby make the implementation diversification of recreation; Improve the dirigibility of recreation implementation, helped the popularization of speech recognition; In addition, a kind of telepilot that has phonetic function of the utility model can make the user in recreation, carry out other motions of hand, helps user's wrist healthy, is very suitable for practicality.
In sum, the utility model has obvious improvement technically, and has tangible good effect, really is the new design of a novelty, progress, practicality.
Above-mentioned explanation only is the general introduction of the utility model technical scheme; In order more to know the technological means of understanding the utility model; And can implement according to the content of instructions, and for let the above-mentioned of the utility model with other purposes, feature and advantage can be more obviously understandable, below special act preferred embodiment; And conjunction with figs., specify as follows.
Description of drawings
Fig. 1 is a kind of telepilot synoptic diagram that has phonetic function of the utility model.
Fig. 2 is a kind of telepilot schematic diagram that has phonetic function of the utility model.
Embodiment
For further setting forth the utility model is to reach technological means and the effect that predetermined utility model purpose is taked; Below in conjunction with accompanying drawing and preferred embodiment; To its embodiment of the remote controller that has phonetic function, structure, characteristic and the effect thereof that proposes according to the utility model, specify as after.
Fig. 1 shows a kind of telepilot that has phonetic function of the utility model specific embodiment; This telepilot comprises: voice acquisition module 1, voice pre-processing module 2, sound identification module 3, identification circuit 4, memory module 5, control module 6, this a kind of telepilot that has phonetic function can also comprise except that other building blocks of components and parts other places that show among Fig. 1 in addition.For example: wave point, power module etc.Describe one by one in the face of a kind of each element that has the telepilot of phonetic function that the present invention relates to down.
Voice acquisition module 1 is mainly used in the collection voice signal, and the voice signal that collects is transferred to voice pre-processing module 2 carries out pre-service.Voice collecting can realize that through the voice collecting device for example common Mike just can gather voice signal, and cost is lower and be easy to realization.The utility model does not limit the type of collector.
Voice pre-processing module 2 is mainly used in the voice signal that voice acquisition module 1 is transmitted and removes noise treatment, signal processing and amplifying; Voice signal is after treatment discerned being transferred to sound identification module 3; Can improve the accuracy of voice signal identification; Draw correct recognition result, the speed that improves speech recognition also can be arranged simultaneously, give rapid reaction.
Sound identification module 3 mainly is that the pretreated voice signal and the reference template that receive are mated, and the reference template that matching fractional is the highest converts electric signal to as recognition result and through identification circuit 4.
Speech recognition process mainly comprises pre-service, feature extraction, the pattern match several sections of voice signal.Pre-service comprises processes such as pre-filtering, sampling and quantification, windowing, end-point detection, pre-emphasis.It is exactly characteristic parameter extraction that voice signal is discerned a most important ring.The characteristic parameter that extracts must satisfy following requirement: the characteristic parameter that extract (1) can be represented phonetic feature effectively, has good differentiation property; (2) between each rank parameter good independence is arranged; (3) characteristic parameter is wanted convenience of calculation, and high-efficient algorithm is preferably arranged, to guarantee the real-time implementation of speech recognition.
In the training stage, characteristic parameter carried out certain processing after, set up a model for each entry, save as ATL.At cognitive phase, voice signal obtains speech characteristic parameter through identical passage, generates test template, matees with reference template, and the reference template that matching fractional is the highest is as recognition result.Simultaneously, can also under the help of a lot of prioris, improve the accuracy rate of identification.
In fact be a database comparison function that pre-sets in the admission of the ATL of training stage, the sound wave of the sound that he can send to the user is distinguished, and sound wave comprises (1) frequency: the stretching of the spring that waveform table reveals.(2) amplitude: the peak swing in the one-period just, waveform table reveals the fluctuating of mountain peak formula.Our known amplitude is exactly a volume, and frequency is exactly a tone.This user's of ripple representative record the frequency of sound wave and the characteristics of amplitude are also stored, after receiving corresponding sound once more, with the frequency of sound template in storehouse contrast sound wave, representative records such as amplitude, contrast coupling, mark the highest as recognition result.This function can realize the differentiation that different people is said; Thereby realize the functional mode of a series of expansions according to the alternative sounds of different people; For example child uses cartoon style; The man uses the blue-black style, and the woman uses pink style, just can realize the function and the characteristics of a series of individual characteies like this through the ATL of training stage.
The speech recognition system schematic diagram is seen Fig. 2, and we can find out that the essence of speech recognition is exactly a kind of system's pattern of pattern-recognition among the figure, comprise Feature Extraction, the coupling of pattern, the element units that reference model storehouse or the like is basic.Voice signal is a kind of typical non-stationary signal kind in fact, includes respiratory air flow, and outside noise current can not directly be used for feature extraction with the voice signal that interference or the like is, need carry out the special processing in early stage.Early stage, processing comprised pre-filtering, and sampling and quantification divide frame, windowing, and pre-emphasis, breakpoint detects or the like.Can carry out the process of characteristic parameter extraction through the speech data of handling early stage.In training and recording process, characteristic parameter through after a series of processing, is obtained a model for each entry, deposit into ATL or sound bank.At cognitive phase, voice signal obtains speech parameter by identical passage, generates a test module, matees with reference or ATL, and optimum in will mating, reference or template that just mark is the highest are handled as the recognition result an of the best.Follow-up processing can also comprise the morphology of higher better level, and sentence structure is handled or the like with the syntax, thereby the signal speech that draws an input at last is transformed into text or order, new number, or the like.
The speech recognition system flow process is resolved, and speech recognition system can be a size, just at first by a phonetic entry the simplest; Thickness, or the like the sound that sends of different sound sources, need be near speech ciphering equipment, after being input to this equipment; At first carry out a pre-service, carry out filtering, sampling quantizes; Divide frame, windowing, the processing of technology such as pre-emphasis end points, thus the voice signal of input is relatively steadily better accepted with supply equipment; Equipment just can carry out feature extraction smoothly like this, carries out a tangible brightening to the voice signal of input and handles, and two stages are arranged afterwards, is respectively identification and training; In the training stage, be exactly the foundation in a kind of sound template storehouse, each voice signal all can be compared with preset in advance template sound bank after extracting, thereby carries out next step processing more accurately; Obtain parameter at the cognitive phase voice signal through identical passage, generate test template, mate with reference template; Mate a best result as last recognition result, thus process identification and two rank stages of training, all link of hitting measure estimation; At this time need carry out an estimation of estimating to the information of extracting, can mix in the processing procedure be the assessment of true measure, estimate estimate that total evaluation is intact after; Carry out a processing of recognition decision, middle meeting finally produce relatively accurate recognition result with reference to a processing that module is made a strategic decision of expertise.
Processing after speech recognition system finishes, the thing that after a series of speech recognition systems of voice process of input, also need launch near order carries out mating with the mapping of keyboard or case, and this process is a key link.
Identification circuit 4 is mainly used in and converts voice signal to electric signal, all is connected with sound identification module 3, control module 6, memory module 5.Identification circuit 4 receives behind the voice signal that voice module 3 transmits through comparing with the electric signal corresponding relation that is pre-stored in the memory module 5, draws correct electric signal at last and outputs to control module 6.Identification circuit 4 also can the pre-stored voice signal and the corresponding relation of electric signal identifying information, and after the voice signal that transmits was confirmed through corresponding relation, the identification information that transfers out request signal carried out next step affirmation to memory module 5.Also can store the correspondence relationship information of signal identifying information and game control command id information in the identification circuit 4 in advance; Like this; Identification circuit 4 can be determined the exectorial identification information of needs output according to this correspondence relationship information of its storage behind the voice messaging of determining effector's execution.The utility model does not limit concrete structure, the voice signal beacon information of identification circuit 4, the concrete implementation of command id information or the like of playing.
Memory module 5 all is connected with control module 6, identification circuit 4, is the semiconductor memory cell that is used for the store data and instruction, and memory module 5 is mainly used in buffered data, exchanges data, instruction and program corresponding relation and canned data etc.Memory module 5 is the correspondence relationship information of storage of speech signals identification information and game control command id information in advance; Such as: the voice signal identifying information is for to the right; Corresponding game control command id information is the right button of remote-controller function button; The voice signal identifying information is for going out fist, and the game control command id information that mark is corresponding is telepilot ok key etc.Memory module 5 can comprise volatile storage medium and non-volatile storage medium.The capacity of memory module 5 can be provided with according to the actual needs of terminal device.The utility model does not limit the concrete model of memory module 5 etc.
Control module 6 is connected with identification circuit 4, memory module 5, is mainly used in the logic, relation, control command etc. of the whole telepilot of control.When control module 6 receives after identification circuit 4 sends electric signal; Control module 6 can with its be pre-stored in the affirmation of comparing of control command corresponding relation in the memory module 5, and the control command signal after will confirming is transferred to opposite equip. through wave point.
Wave point is arranged in the telepilot, is mainly used in the transmission of data.The control command that control module 6 transmits is transferred to opposite equip. through wave point, carries out control operation.
Power module is that each parts of whole telepilot provide electric power resource, and power module can comprise: alkaline battery or rechargeable battery etc.
The above only is the preferred embodiment of the utility model; Be not that the utility model is done any pro forma restriction; Though the utility model discloses as above with preferred embodiment; Yet be not in order to limit the utility model; Any professional and technical personnel of being familiar with makes a little change or is modified to the equivalent embodiment of equivalent variations when the technology contents of above-mentioned announcement capable of using in not breaking away from the utility model technical scheme scope, is the content that does not break away from the utility model technical scheme in every case;, all still belong in the scope of the utility model technical scheme any simple modification, equivalent variations and modification that above embodiment did according to the technical spirit of the utility model.
Claims (5)
1. a telepilot that has phonetic function is characterized in that, said telepilot comprises: voice acquisition module: be used to gather voice signal and be transferred to the voice pre-processing module;
Voice pre-processing module: the voice signal that receives is carried out denoising, signal processing and amplifying;
Sound identification module: the voice signal after the processing that will receive carries out pattern match, and the result that will match outputs to identification circuit;
Identification circuit: convert the voice signal that matches to electric signal;
Memory module: be used for storaged voice template data, control command corresponding relation data;
Control module: with electric signal be pre-stored in memory module in corresponding the comparing of control command relation, and convert comparing result to system order back output.
2. a kind of telepilot that has phonetic function as claimed in claim 1 is characterized in that, said a kind of telepilot that has phonetic function also comprises: the power module that electric power resource is provided.
3. a kind of telepilot that has phonetic function as claimed in claim 1 is characterized in that said voice acquisition module can be a microphone.
4. a kind of telepilot that has phonetic function as claimed in claim 1 is characterized in that, described a kind of telepilot that has phonetic function also comprises wave point.
5. a kind of telepilot that has phonetic function as claimed in claim 4; It is characterized in that said radio interface module comprises: based on the wave point of bluetooth, based on the wave point of 2.4GHz, based on the wave point of WIFI and based in the infrared wave point at least one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201120569359 CN202600936U (en) | 2011-12-31 | 2011-12-31 | Remote controller with voice function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201120569359 CN202600936U (en) | 2011-12-31 | 2011-12-31 | Remote controller with voice function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202600936U true CN202600936U (en) | 2012-12-12 |
Family
ID=47318462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201120569359 Expired - Fee Related CN202600936U (en) | 2011-12-31 | 2011-12-31 | Remote controller with voice function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202600936U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103293691A (en) * | 2013-06-09 | 2013-09-11 | 歌尔声学股份有限公司 | Three-dimensional (3D) glasses with voice recognition function |
| CN103458287A (en) * | 2013-09-02 | 2013-12-18 | 四川长虹电器股份有限公司 | System and method for game voice control based on digital television remote control technology |
| CN106210978A (en) * | 2016-07-25 | 2016-12-07 | 中科创达软件股份有限公司 | A kind of acoustic control mike |
-
2011
- 2011-12-31 CN CN 201120569359 patent/CN202600936U/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103293691A (en) * | 2013-06-09 | 2013-09-11 | 歌尔声学股份有限公司 | Three-dimensional (3D) glasses with voice recognition function |
| CN103458287A (en) * | 2013-09-02 | 2013-12-18 | 四川长虹电器股份有限公司 | System and method for game voice control based on digital television remote control technology |
| CN106210978A (en) * | 2016-07-25 | 2016-12-07 | 中科创达软件股份有限公司 | A kind of acoustic control mike |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103730116B (en) | Intelligent watch realizes the system and method that intelligent home device controls | |
| CN112863547B (en) | Virtual resource transfer processing method, device, storage medium and computer equipment | |
| CN103745722B (en) | Voice interaction smart home system and voice interaction method | |
| US10061389B2 (en) | Gesture recognition system and gesture recognition method | |
| CN110364144A (en) | A kind of speech recognition modeling training method and device | |
| CN107423809A (en) | The multi-modal exchange method of virtual robot and system applied to net cast platform | |
| CN103366784B (en) | There is multi-medium play method and the device of Voice command and singing search function | |
| CN202590338U (en) | Handle with voice function | |
| CN104123930A (en) | Guttural identification method and device | |
| CN202600936U (en) | Remote controller with voice function | |
| CN105182763A (en) | Intelligent remote controller based on voice recognition and realization method thereof | |
| CN207321416U (en) | A kind of pickup component, sound pick-up and television set wake up and far say voice system | |
| Saraswat et al. | An incremental learning based gesture recognition system for consumer devices using edge-fog computing | |
| WO2018023515A1 (en) | Gesture and emotion recognition home control system | |
| CN102760312A (en) | Intelligent door control system with speech recognition | |
| CN105582669A (en) | Motion sensing game bracelet system based on motion template feature matching | |
| WO2018023523A1 (en) | Motion and emotion recognizing home control system | |
| WO2018023514A1 (en) | Home background music control system | |
| CN109285544A (en) | Speech monitoring system | |
| CN103137126A (en) | Intelligent electronic device based on voice control and voice control method | |
| CN102739844A (en) | Realization method for playing music through detecting motion trail of mobile terminal equipment | |
| WO2018023513A1 (en) | Home control method based on motion recognition | |
| CN115331658A (en) | Voice recognition method | |
| CN205451769U (en) | Wear speech recognition system of smart machine and wear smart machine | |
| WO2018023518A1 (en) | Smart terminal for voice interaction and recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| DD01 | Delivery of document by public notice |
Addressee: Beijing Dexin Interactive Network Technology Co.,Ltd. Document name: Notification of Termination of Patent Right |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121212 Termination date: 20151231 |
|
| EXPY | Termination of patent right or utility model |