CN103366743A - Voice-command operation method and device - Google Patents
Voice-command operation method and device Download PDFInfo
- Publication number
- CN103366743A CN103366743A CN2012101031421A CN201210103142A CN103366743A CN 103366743 A CN103366743 A CN 103366743A CN 2012101031421 A CN2012101031421 A CN 2012101031421A CN 201210103142 A CN201210103142 A CN 201210103142A CN 103366743 A CN103366743 A CN 103366743A
- Authority
- CN
- China
- Prior art keywords
- voice command
- voice
- mobile device
- comparative result
- threshold condition
- 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
Images
Landscapes
- Telephone Function (AREA)
Abstract
The invention relates to a method and device used for operating a voice command. The voice-command operation method of the invention includes: acquiring and storing a voice command corresponding to an operation; acquiring a voice; identifying a voice command which matches the acquired voice; and providing an operation corresponding to the identified voice command. The voice-command operation device includes: an acquiring apparatus used for acquiring the voice command corresponding to the operation and acquiring the voice; a storing apparatus used for storing the voice command corresponding to the operation; an identifying apparatus used for identifying the voice command which matches the acquired voice; and a providing apparatus used for providing the operation corresponding to the identified voice command.
Description
Technical field
The present invention relates to operate voice command, relate more specifically to a kind of method and apparatus of self-defining operation voice command.
Background technology
Carry out speech exchange with machine, allow machine understand what you say, this is the thing that people dream of for a long time.The voice control technology is exactly to allow machine voice signal be changed into the hi-tech of corresponding text or order by identification and understanding process.Recent two decades comes, and the voice control technology obtains marked improvement, begins to move towards market from the laboratory.People estimate that Future Ten is in year, and the voice control technology will enter the every field such as industry, household electrical appliances, communication, automotive electronics, medical treatment, home services, consumption electronic product.Speech control system, namely come the operation of opertaing device with voice, more quick and easy with respect to manual control, can be used in many fields such as mobile device, Industry Control, voice dialing system, intelligent appliance, automotive electronics, acoustic control intelligent toy.
Also adopted more and more the voice control technology so that the operation of mobile device is more convenient in the present widely used mobile device, the user of lifting mobile equipment experiences.Specifically, the voice-operated implementation in the mobile device generally comprises three types: the recognition method of server identification, the local identification of mobile device and server+this locality.
In server identification, generally after this locality obtains the phonetic order of user's input, by the mobile network data are sent to server, at server end voice are processed and identified, literal order (collection) after the identification is sent back to mobile device, and for user selection or execution.
In this locality identification, instruction database of local storage and corresponding phonetic order (collection) thereof after the user input voice instruction, mate and identify by the phonetic order of storing with this locality, and then identify corresponding steering order (collection).
The mode of server+this locality generally is the subset at this locality storage dictionary, when receiving the user and input, at first mates with the instruction database of this locality and identifies, if do not store in this locality, then sends to server and mates and identify.
In the server recognition method, therefore identifying has larger limitation without using under the network state.In local recognition method, because the restriction of service ability generally is difficult to carry out the identification of full corpus.Openly applying for a patent " a kind of sound control method, device and portable terminal " (number of patent application: disclose 200710123046.6) and a kind ofly in current interface the interface control element is numbered, and then carried out voice-operated method.The method is numbered the button of current interface, menu etc., and the user only need to be by saying and numbering relevant simple steering order and can control software.Yet because there is larger difference everyone accent, audible frequency, tone tone color aspect, even for fixing instruction, the sound characteristic of collection all may be larger with the template difference, and then cause error.
In sum, in the voice control technology of existing portable terminal, be subject to the multifarious restriction of network or language, voice control effectively and is widely implemented.
On the other hand, mobile device popularizes so that the user produces increasing personalized, private and interesting requirement for mobile device.Simultaneously, voice-operated realization also there is simple, the compatible good and low requirement of cost.
Summary of the invention
For the problems referred to above, the application is devoted to realize satisfying the method and apparatus of the above self-defining operation voice command that requires.
Relate to according to an aspect of the present invention a kind of method that operates voice command, comprising: obtain and store the voice command corresponding to operation; Obtain voice; Identify the voice command with the voice match of obtaining; The operation corresponding with the voice command of identifying is provided.
A preferred embodiment of the invention, wherein said identification are based on context and carry out.
A preferred embodiment of the invention also comprises: show operating list, to obtain voice command for the operation in this operating list.
A preferred embodiment of the invention, wherein said identification comprise described voice and described voice command are compared, and judge whether comparative result satisfies threshold condition.
A preferred embodiment of the invention if do not satisfy the comparative result of threshold condition, then provides the prompting that does not identify with the voice command of the voice match of obtaining.
A preferred embodiment of the invention, if the comparative result that satisfies threshold condition is arranged, the voice command corresponding with the best comparative result voice command that is identified as mating then.
A preferred embodiment of the invention wherein compares the distance that comprises between the described voice of calculating and the described voice command with described voice and described voice command.
A preferred embodiment of the invention, if the described distance that satisfies threshold condition is arranged, the voice command corresponding with the minor increment voice command that is identified as mating then.
Relate to according to an aspect of the present invention a kind of device that operates voice command, comprising: deriving means, for obtaining corresponding to the voice command that operates and obtaining voice; Memory storage is used for storage corresponding to the voice command of operation; Recognition device is for the voice command of identification with the voice match of obtaining; Generator is used for providing the operation corresponding with the voice command of identifying.
A preferred embodiment of the invention, wherein said recognition device are configured to based on the context and identify.
A preferred embodiment of the invention also comprises: exhibiting device is used for showing operating list, to obtain voice command for the operation in this operating list.
A preferred embodiment of the invention, wherein said recognition device are configured to described voice and described voice command are compared, and judge whether comparative result satisfies threshold condition.
A preferred embodiment of the invention, if described recognition device is judged the comparative result that does not satisfy threshold condition, then described generator is configured to provide the prompting that does not identify with the voice command of the voice match of obtaining.
A preferred embodiment of the invention, if described recognition device is judged the comparative result that satisfies threshold condition, the voice command corresponding with the best comparative result voice command that is identified as mating then.
A preferred embodiment of the invention, wherein said recognition device compares the distance that comprises between the described voice of calculating and the described voice command with described voice and described voice command.
A preferred embodiment of the invention, if described recognition device is judged the described distance that satisfies threshold condition, the voice command corresponding with the minor increment voice command that is identified as mating then.
Method and apparatus according to operation voice command of the present invention utilizes limited storage, computational resource, has realized practicality, individual character, the interesting voice operating of mobile device in mode low-cost and that realize easily.
Description of drawings
By reading with reference to the accompanying drawings detailed description hereinafter, above-mentioned and other purposes of exemplary embodiment of the invention, the feature and advantage easy to understand that will become.In the accompanying drawings, show some embodiments of the present invention in exemplary and nonrestrictive mode, wherein:
Fig. 1 shows a kind of process flow diagram that operates the method for voice command according to an embodiment of the invention;
Fig. 2 is the synoptic diagram that schematically shows according to the operating list of an embodiment of the invention;
Fig. 3 is the diagram that schematically shows the interface under the state of mobile device after the user has checked and accepted note.
Fig. 4 is the diagram that schematically shows the interface under the state of mobile device after finishing writing short message content.
Fig. 5 shows the block diagram according to the device 500 that is used for the operation voice command of one embodiment of the present invention.
Fig. 6 shows and will be benefited from exemplary embodiment of the invention and can be the block diagram of the mobile device 10 of exemplary embodiment of the invention exemplary device.
In the accompanying drawings, identical or corresponding label represents identical or corresponding part.
Embodiment
Below with reference to some illustrative embodiments principle of the present invention and spirit are described.Should be appreciated that providing these embodiments only is for those skilled in the art can being understood better and then realize the present invention, and be not to limit the scope of the invention by any way.
According to the embodiment of the present invention, a kind of method and apparatus that operates voice command has been proposed.
In this article, it will be appreciated that any name all only is used for distinguishing, so that describe, and do not have any limitation.
Below with reference to some representative embodiments of the present invention, explain in detail principle of the present invention and spirit.
At first with reference to figure 1, Fig. 1 shows a kind of process flow diagram that operates the method 100 of voice command according to an embodiment of the invention.After method 100 beginnings, at first carry out step S110, obtain and store the voice command corresponding to operation.
In a preferred embodiment of the invention, can show operating list, to obtain voice command for the operation in this operating list.Referring to Fig. 2, wherein provided a diagram of operating list.As seen from the figure, comprising clauses and subclauses such as " determining ", " retreating ", " telephone directory ", " game ", " note ", " storage ", " transmission ", " deletions ".More specifically, can also comprise in the operating list " on ", D score, " left side ", " right side ", " release ", " message registration ", " network service ", " calendar ", " alarm clock ", " counter ", " music ", " photograph album " and clauses and subclauses such as " callings ".Furthermore, can also comprise now each contact person's address, for example " Xiao Zhang ", " Lao Wang " etc. at " telephone directory " bar; And can comprise now the title of concrete game at " game " bar, such as " picture mosaic ", " fishing " etc.Below only show the content that operating list is comprised in the mode of example, those skilled in the art will understand the content that can also comprise other in the operating list as required according to the application's record.The example that more than provides is not to limit the scope of the invention by any way in order to make those skilled in the art understand better implementation of the present invention just.
In another embodiment of the present invention, whether can in each interface, inquire separately command set voice command for wherein.Those skilled in the art can understand and can adopt various ways prompting user input corresponding to the voice command of operation.
In the method for the application's operation voice command, when the voice command that obtains and store corresponding to operation, the user can use own distinctive Extraordinary expression way.For example, the user can freely use dialect, rhythm, intonation and the self-defining appellation of oneself, even can be operating and setting " incantation ".For instance, for " release " operation, the user can store the voice of self-defining specific pronunciation, rhythm, and it for example can be user's motto, the fragment of song, and nonsensical voice etc.Another example is such as the appellation for the contact person in the address list, and the user can freely arrange their pet name, pet phrase etc. and represent corresponding contact person.Thus, the mode of this operation voice command of the present invention is not subjected to the impact of the language differences such as dialect, and has realized Extraordinary operation voice command.Further, also can in the situation of needs, realize the proprietary speech recognition of user, operate thereby only have specific user's sound could control corresponding mobile device that such as " release " etc., this has strengthened the privacy of mobile device operation.Simultaneously, the method language material of this operation voice command of the present invention is relatively simple, effectively conserve storage and computational resource.And what of the concrete language material content of the method for operation voice command of the present invention can be controlled by the user, and it is controlled that the degree of identifying as required also can realize the user, thereby can realize utilizing more flexibly storage space and computational resource.That is to say that the method for operation voice command of the present invention utilizes limited device resource to realize personalization, secret and the interest and appeal of portable terminal operation, brings abundanter user to experience.
Then the method advances to step S120, obtains voice.In mobile device, can directly receive user's voice via the microphone that disposes in the mobile device.Mobile device can prompting user begins to obtain voice and end is obtained.In one embodiment of the invention, the user can determine to begin to obtain the time point that voice are obtained in voice and end by pressing particular key.
And then the method advances to step S130, the voice command of the voice match of identifying and obtaining.In a preferred embodiment of the invention, described identification is based on context and carries out.Specifically, this identification is based on that the current state of equipment carries out, i.e. identification and that voice command of voice match to be identified in the voice command of the possible operation in the equipment current state, thus computational resource further saved, improve the efficient of speech recognition.For instance, be in the situation of mobile phone at this portable terminal, only provide by way of example example interface as shown in Figure 3 and Figure 4.In Fig. 3, schematically illustrate the interface under the state of mobile device after the user has checked and accepted note.In the situation of Fig. 3 example, possible operation be according to " deletion " shown in the example of Fig. 3, " transmission ", " text answer ", " callback ", " shearing address ", " determining ", " returning " and generally comprise " on ", D score etc.In Fig. 4, schematically illustrate the interface under the state of mobile device after finishing writing short message content.In the situation of Fig. 4 example, possible operation be according to " transmission " shown in the example of Fig. 4, " storage also send ", " storage ", " interpolation expression figure explanation ", " interpolation preset information ", " determining ", " returning " and generally comprise " on ", D score etc.
Below only provide by way of example the context of example, those skilled in the art it is contemplated that and also have much other contexts.The example that more than provides is not to be to limit the scope of the invention by any way in order to make those skilled in the art understand better implementation of the present invention.
Furthermore, in a specific embodiment, described identification comprises described voice and described voice command is compared, and judges whether comparative result satisfies threshold condition.If do not satisfy the comparative result of threshold condition, then provide the prompting that does not identify with the voice command of the voice match of obtaining.If the comparative result that satisfies threshold condition is arranged, the voice command corresponding with the best comparative result voice command that is identified as mating then.
In an exemplary specific embodiment, described voice and described voice command are compared the distance that comprises between the described voice of calculating and the described voice command.If the described distance that satisfies threshold condition is arranged, the voice command corresponding with the minor increment voice command that is identified as mating then.
Below only specifically describe by way of example a kind of method of calculating the distance between described voice and the described voice command.The distance of input voice and storaged voice order can be used dynamic time warping (Dynamic Time Wrapping, DTW, referring to Ralph Niels, Dynamic Time Wrapping, An intuitive way of handwriting recognition) the distance expression.The DTW distance is commonly used to the similarity of two different sequences of characteristic length.Represent voice command with A, O represents operation.Suppose to have stored the phonetic order relevant with current interface and operation to { (A at certain interface
1, O
1), (A
2, O
2) ..., (A
n, O
n).In one implementation, the digitized voice command of process can represent with a vector, as:
A
i=[a
1, a
2..., a
k], k ∈ N wherein
Wherein, N is natural number.
The voice to be identified of supposing input are Λ-[b
1, b
2..., b
m], its mouthful m ∈ N, N is natural number, then voice A to be identified with stored certain voice command A
iDistance can calculate by the following method:
Should be noted that and can calculate distance between the voice command of voice to be identified and storage with many algorithms, below only provide the description of several available algorithm in the mode of example:
(1) dynamic programming (Dynamic Programming) method.This is that a kind of operand is larger, but technical simpler, and just knowledge rate is higher method also.Distortion measure wherein can be with Euclidean distance (being suitable for short-time spectrum or cepstrum parameter), also can be with log-likelihood ratio distance (being suitable for the LPC parameter). and decision-making technique can be used the nearest-neighbor criterion.
(2) vector quantization (Vector Quantization) method.It both can be used for waveform in the voice communication or the compression of parameter, also can be used for speech recognition.Especially Finite-State Vector Quantization (FSVQJ) method is more effective for speech recognition.Decision-making technique is generally used the minimum average B configuration distortion criterion.
(3) hidden markov model (HMM) method, the parameter of this model both can be used the discrete probability distribution function, also can be with up-to-date continuous probability density function (as: normal state gaussian density, Gaussian Autoregressive density etc.).Decision-making party rule maximum posteriori criterion.
(4) method of hybrid technology.For example: as first order identification (as pre-service, thereby drawing some candidates' recognition result), then, do last identification with DTW or HMM method again with vector quantization, therefore, the recognition methodss such as VQ (vector quantization)/DTW and VQ/HMM can be arranged.
Below only provide by way of example as above audio recognition method, those skilled in the art it is contemplated that and also have much other audio recognition methods.The example that more than provides is not to be to limit the scope of the invention by any way in order to make those skilled in the art understand better implementation of the present invention.
Shall also be noted that for threshold value relatively and can preset, also can be that the user is controlled.Be that the user can regulate the degree of speech recognition in the controlled situation of user in this threshold value.For instance, when threshold value was higher, the less fast computational speed of calculated amount can be made rapidly general speech recognition.When threshold value is low, speech recognition can be more accurately carried out, even the identification for specific user's voice can be realized, realize better privacy.In a specific embodiment of the present invention, the threshold value of the different corresponding speech recognitions of operation can be different.For instance, with the threshold value of the speech recognition of " release " this operational correspondence may be little, to realize that the specific user carries out release to equipment; On the other hand, the threshold value of the speech recognition corresponding with operation " determining ", " retreating " may be large, with the saving calculation resources.
At last, the method advances to step S140, and the operation corresponding with the voice command of identifying is provided.The operation of this correspondence can or can directly be carried out by mobile device for the user selection affirmation.
Below with reference to Fig. 5, Fig. 5 shows the block diagram according to the device 500 that is used for the operation voice command of one embodiment of the present invention.The device 500 that should be used for the operation voice command comprises deriving means 510, for obtaining corresponding to the voice command that operates and obtaining voice; Memory storage 520 is used for storage corresponding to the voice command of operation; Recognition device 530 is for the voice command of identification with the voice match of obtaining; Generator 540 is used for providing the operation corresponding with the voice command of identifying.
According to a preferred embodiment of the present invention, described device for the operation voice command also comprises: exhibiting device is used for showing operating list, to obtain voice command for the operation in this operating list.
According to a preferred embodiment of the present invention, wherein said recognition device is configured to based on the context and identifies.Specifically, this identification is based on that the current state of equipment carries out, i.e. that voice command of identification and voice match to be identified in the voice command of the possible operation in the equipment current state.
Furthermore, in a specific embodiment, described recognition device is configured to described voice and described voice command are compared, and judges whether comparative result satisfies threshold condition.If described recognition device is judged the comparative result that does not satisfy threshold condition, then described generator is configured to provide the prompting that does not identify with the voice command of the voice match of obtaining.If described recognition device is judged the comparative result that satisfies threshold condition, the voice command corresponding with the best comparative result voice command that is identified as mating then.
In an exemplary specific embodiment, described recognition device compares the distance that comprises between the described voice of calculating and the described voice command with described voice and described voice command.If described recognition device is judged the described distance that satisfies threshold condition, the voice command corresponding with the minor increment voice command that is identified as mating then.
The device that should be noted that operation voice command of the present invention can specific implementation be hardware, software, firmware and combination in any thereof.Especially, the device of this operation voice command can be realized with software code fully, thus user friendly download use, and need not the hardware of mobile device is made any additional modifications, thereby can realize at low cost, easily being conducive to the present invention it and using widely.
Then, show and from exemplary embodiment of the invention, to be benefited and can be the block diagram of the mobile device 10 of exemplary embodiment of the invention exemplary device with reference to figure 6.Yet, should be appreciated that as shown in the figure and mobile phone hereinafter described only is the example of the class mobile device of will be from exemplary embodiment of the invention being benefited, and be not used for limiting the scope of exemplary embodiment of the invention.Although illustrate several embodiments of mobile device 10 for giving an example purpose, for example the voice of the equipment of the other types of any combination of portable digital assistant (PDA), pager, mobile TV, game station, laptop computer, camera, video recorder, audio/video player, radio, GPS equipment or aforementioned means and so on and other types and text communication system can easily use exemplary embodiment of the invention.
In addition, although mobile device 10 can use several embodiments of the inventive method, the device except above-mentioned mobile device also can use the method for exemplary embodiment of the invention.In addition, although mainly combine the method and apparatus that mobile communication application has been described exemplary embodiment of the invention, but, should be appreciated that and can in mobile communications industry and beyond mobile communications industry, should be used for utilizing the method and apparatus of exemplary embodiment of the invention in conjunction with various other.
But mobile device 10 can comprise the antenna 12 (perhaps a plurality of antennas) with transmitter 14 and receiver 16 operation communications.Mobile device 10 can also comprise respectively to transmitter 14 to be provided signal and receives the device of signals, for example controller 20 or other processing units from receiver 16.Signal comprises the signaling information according to the applicable cellular system air-interface standard, also comprises the data of user speech, reception and/or the data that generated by the user.In this regard, mobile device 10 can utilize one or more air-interface standard, communication protocol, modulation type and access style to operate.For example, mobile device 10 can operate according to any communication protocol in the communication protocols such as a plurality of first generation, the second generation, the third generation and/or the 4th generation.For example, mobile device 10 can be according to the second generation (2G) wireless communication protocol IS-136 (time division multiple access (TDMA) (TDMA)), GSM (global system for mobile communications) and IS-95 (CDMA (CDMA)) or according to for example Universal Mobile Telecommunications System (UMTS), CDMA2000, the third generation (3G) wireless communication protocol that wideband CDMA (WCDMA) and time-division-synchronization CDMA (TD-SCDMA) are such, according to the 3.9th generation (3.9G) wireless communication protocol such as evolved universal terrestrial radio access network (E-UTRAN), according to the 4th generation (4G) wireless communication protocol etc. operate.Replace (perhaps in addition), mobile device 10 can operate according to non-cellular communication mechanisms.For example, mobile device 10 can be communicated by letter in WLAN (wireless local area network) (WLAN) or other communication networks.In addition, mobile device 10 can for example be communicated by letter according to following technology, and these technology for example are radio frequency (RF), infrared ray (IrDA) or a plurality of different radio networking technology (comprise WLAN technology such as IEEE 802.11 (802.11a for example, 802.11b, 802.11g, 802.11n etc.), World Interoperability for Microwave Access, WiMax (WiMAX) technology such as IEEE 802.16 and/or wireless personal domain network (WPAN) technology such as IEEE 802.15, bluetooth (BT), ultra broadband (UWB) and/or similar techniques) in any technology.
Be appreciated that for example controller 20 such devices can comprise audio frequency and the required circuit of logic function of implementing mobile device 10.For example, controller 20 can comprise digital signal processor device, micro processor device and various AD converter, digital-to-analog converter and other support circuit.The control of mobile device 10 and the signal processing function respective capabilities according to them between these equipment is distributed.Therefore controller 20 also can comprise in order to before modulation and transmission message and data are carried out convolutional encoding and the function that interweaves.Controller 20 can also comprise internal voice coder and can comprise internal data modem.In addition, controller 20 can comprise the function that can be stored in one or more software program in the storer in order to operation.For example, controller 20 can operable communication program, for example conventional Web browser.Then connectivity program can allow mobile device 10 for example to come the sending and receiving web content according to WAP (wireless application protocol) (WAP), HTTP (HTTP) and/or similar agreement, for example location-based content and/or other web page contents.
Mobile device 10 can also comprise Subscriber Identity Module (UIM) 38.UIM 38 is generally the memory devices with internal processor.UIM 38 can be such as comprising Subscriber Identity Module (SIM), Universal Integrated Circuit Card (UICC), universal subscriber identity module (USIM), detachable Subscriber Identity Module (R-UIM) etc.UIM 38 is the storage cell relevant with the mobile subscriber usually.Except UIM 38, mobile device 10 can also be equipped with storer.For example, mobile device 10 can comprise volatile memory 40, for example comprises the volatile random access memory (RAM) for the cache area of temporary transient storage data.Mobile device 10 also can comprise and can embed and/or demountable other nonvolatile memories 42.In addition or the ground that replaces, nonvolatile memory 42 can also comprise Electrically Erasable Read Only Memory (EEPROM), flash memory etc., the nonvolatile memory that for example can obtain from the Lexar Media company in the SanDisk company in Sani Wei Er city, California or California Fei Limeng city.Storer can be stored by mobile device 10 and be used for implementing many information of function of mobile device 10 and any information and the data in the data.For example, storer can comprise the identifier that can identify uniquely mobile device 10, International Mobile Station Equipment Identification (IMEI) code for example, and can be with the current time position of the adjacent mobile device that receives and this current moment unique identification association store with neighbouring device.Particularly, storer can be stored the application program of carrying out for by controller 20, and this controller is determined the current location of mobile device 10.
Mobile device 10 can also comprise the alignment sensor 36 of communicating by letter with controller 20, for example GPS (GPS) module.Alignment sensor 36 can be for any device, equipment or the circuit that the location of mobile device 10 are carried out location positioning.Alignment sensor 36 can comprise for all hardware that the location of mobile device 10 is carried out location positioning.Alternatively or additionally, alignment sensor 36 can utilize the memory devices of mobile device 10 to store the instruction of carrying out for controller 20, and its file layout is to determine the required software in position of mobile device 10.Although the alignment sensor 36 of this example can be the GPS module, but alignment sensor 36 can comprise or alternatively be embodied as for example agps system (assistant GPS) sensor or positioning client terminal, and this assistant GPS sensor or positioning client terminal can communicate by letter to receive and/or send the information of using for when determining the location of mobile device 10 with the network equipment such as aerial or ground transaucer.In this regard, the location of mobile device 10 also can be by GPS, residential quarter ID, signal triangulation or other mechanism are determined as mentioned above.In an example embodiment, alignment sensor 36 comprises passometer or inertial sensor.Like this, alignment sensor 36 can be determined for example position take the longitude of mobile device 10 and dimension direction and short transverse as reference or with respect to the location of reference point such as impact point or starting point of mobile device 10.Then in the future the information of self-align sensor 36 is sent to storer or another memory devices of mobile device 10, in order to be stored as position history or positional information.In addition, alignment sensor 36 can utilize controller 20 via transmitter 14/ receiver 16 sending/receiving positional informations, for example location of mobile device 10.
The described block diagram of Fig. 6 illustrates just to the purpose of example, is not to be limitation of the present invention.In some cases, can add as required or reduce wherein some equipment.
Embodiments of the present invention can realize by the combination of hardware, software or software and hardware.Hardware components can utilize special logic to realize; Software section can be stored in the storer, and by suitable instruction execution system, for example microprocessor or special designs hardware are carried out.Those having ordinary skill in the art will appreciate that above-mentioned equipment and method can and/or be included in the processor control routine with computer executable instructions realizes, for example such as the mounting medium of disk, CD or DVD-ROM, provide such code such as the programmable memory of ROM (read-only memory) (firmware) or such as the data carrier of optics or electronic signal carrier.Equipment of the present invention and module thereof can be by such as VLSI (very large scale integrated circuit) or gate array, realize such as the semiconductor of logic chip, transistor etc. or such as the hardware circuit of the programmable hardware device of field programmable gate array, programmable logic device etc., also can use the software of being carried out by various types of processors to realize, also can by the combination of above-mentioned hardware circuit and software for example firmware realize.
Although should be noted that and mention some devices or sub-device in above-detailed, this division only is not enforceable.In fact, according to the embodiment of the present invention, the feature of above-described two or more devices and function can be specialized in a device.Otherwise, the feature of an above-described device and function can Further Division for to be specialized by a plurality of devices.
In addition, although described in the accompanying drawings the operation of the inventive method with particular order,, this is not that requirement or hint must be carried out these operations according to this particular order, or the operation shown in must carrying out all could realize the result of expectation.On the contrary, the step of describing in the process flow diagram can change execution sequence.Additionally or alternatively, can omit some step, a plurality of steps be merged into a step carry out, and/or a step is decomposed into a plurality of steps carries out.
Although described the present invention with reference to some embodiments, should be appreciated that the present invention is not limited to disclosed embodiment.The present invention is intended to contain interior included various modifications and the equivalent arrangements of spirit and scope of claims.The scope of claims meets the most wide in range explanation, thereby comprises all such modifications and equivalent structure and function.
Claims (16)
1. method that operates voice command comprises:
Obtain and store the voice command corresponding to operation;
Obtain voice;
Identify the voice command with the voice match of obtaining;
The operation corresponding with the voice command of identifying is provided.
2. method according to claim 1, wherein said identification is based on context and carries out.
3. method according to claim 1 also comprises:
Show operating list, to obtain voice command for the operation in this operating list.
4. method according to claim 1 and 2, wherein said identification comprise described voice and described voice command are compared, and judge whether comparative result satisfies threshold condition.
5. method according to claim 4 if do not satisfy the comparative result of threshold condition, then provides the prompting that does not identify with the voice command of the voice match of obtaining.
6. method according to claim 4, if the comparative result that satisfies threshold condition is arranged, the voice command corresponding with the best comparative result voice command that is identified as mating then.
7. method according to claim 4 wherein compares the distance that comprises between the described voice of calculating and the described voice command with described voice and described voice command.
8. method according to claim 7, if the described distance that satisfies threshold condition is arranged, the voice command corresponding with the minor increment voice command that is identified as mating then.
9. device that operates voice command comprises:
Deriving means is for obtaining corresponding to the voice command that operates and obtaining voice;
Memory storage is used for storage corresponding to the voice command of operation;
Recognition device is for the voice command of identification with the voice match of obtaining;
Generator is used for providing the operation corresponding with the voice command of identifying.
10. device according to claim 9, wherein said recognition device is configured to based on the context and identifies.
11. device according to claim 9 also comprises:
Exhibiting device is used for showing operating list, to obtain voice command for the operation in this operating list.
12. according to claim 9 or 10 described devices, wherein said recognition device is configured to described voice and described voice command are compared, and judges whether comparative result satisfies threshold condition.
13. device according to claim 12, if described recognition device is judged the comparative result that does not satisfy threshold condition, then described generator is configured to provide the prompting that does not identify with the voice command of the voice match of obtaining.
14. device according to claim 12, if described recognition device is judged the comparative result that satisfies threshold condition, the voice command corresponding with the best comparative result voice command that is identified as mating then.
15. device according to claim 12, wherein said recognition device compares the distance that comprises between the described voice of calculating and the described voice command with described voice and described voice command.
16. device according to claim 15, if described recognition device is judged the described distance that satisfies threshold condition, the voice command corresponding with the minor increment voice command that is identified as mating then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101031421A CN103366743A (en) | 2012-03-30 | 2012-03-30 | Voice-command operation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101031421A CN103366743A (en) | 2012-03-30 | 2012-03-30 | Voice-command operation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103366743A true CN103366743A (en) | 2013-10-23 |
Family
ID=49367944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101031421A Pending CN103366743A (en) | 2012-03-30 | 2012-03-30 | Voice-command operation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103366743A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103795715A (en) * | 2014-01-20 | 2014-05-14 | 冯丽娟 | Privacy protection method, privacy recovery method and privacy protection system |
| CN104735634A (en) * | 2013-12-24 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Pay account linking management method, mobile terminal, server and system |
| WO2015103836A1 (en) * | 2014-01-07 | 2015-07-16 | 深圳市中兴微电子技术有限公司 | Voice control method and device |
| CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
| CN106992009A (en) * | 2017-05-03 | 2017-07-28 | 深圳车盒子科技有限公司 | Vehicle-mounted voice exchange method, system and computer-readable recording medium |
| WO2017177766A1 (en) * | 2016-04-12 | 2017-10-19 | 深圳市京华信息技术有限公司 | Virtual reality device control method and apparatus, and virtual reality device and system |
| CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
| CN108369772A (en) * | 2015-12-17 | 2018-08-03 | 达泰多公司 | Method and apparatus for analyzing and distributing voice command |
| CN109346081A (en) * | 2018-12-20 | 2019-02-15 | 广州河东科技有限公司 | Voice control method, device, equipment and storage medium |
| CN109788039A (en) * | 2018-12-26 | 2019-05-21 | 合肥凯捷技术有限公司 | A kind of interactive system for vehicle-mounted voice storage method |
| CN109859748A (en) * | 2019-01-15 | 2019-06-07 | 福建天眼视讯网络科技有限公司 | Intercom based on the automatic recognition of speech realizes system and method |
| CN111326145A (en) * | 2020-01-22 | 2020-06-23 | 南京雷鲨信息科技有限公司 | Speech model training method, system and computer readable storage medium |
| CN114974232A (en) * | 2021-02-27 | 2022-08-30 | 博泰车联网(南京)有限公司 | Voice information processing method and related product |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1090708A (en) * | 1992-09-16 | 1994-08-17 | 德山曹达株式会社 | Antibacterial Agents and Their Utilization |
| CN1319223A (en) * | 1998-09-21 | 2001-10-24 | 汤姆森多媒体公司 | System comprising remote controlled apparatus and voice-operated remote control device for apparatus |
| CN1385783A (en) * | 2001-05-14 | 2002-12-18 | 索尼电脑娱乐美国公司 | System and method for controllnig role by menu driven speech sound in game environment |
| CN1425980A (en) * | 2003-01-14 | 2003-06-25 | 杨宏惠 | Personalized opening computer voice log-in method |
| CN1674540A (en) * | 2004-03-25 | 2005-09-28 | 联想(北京)有限公司 | Method for central controlling home appliances based on home appliances control center |
| CN1993732A (en) * | 2004-08-06 | 2007-07-04 | 皇家飞利浦电子股份有限公司 | A method for a system of performing a dialogue communication with a user |
| CN101516005A (en) * | 2008-02-23 | 2009-08-26 | 华为技术有限公司 | Speech recognition channel selecting system, method and channel switching device |
| CN101557432A (en) * | 2008-04-08 | 2009-10-14 | Lg电子株式会社 | Mobile terminal and menu control method thereof |
| CN101625857A (en) * | 2008-07-10 | 2010-01-13 | 新奥特（北京）视频技术有限公司 | Self-adaptive voice endpoint detection method |
| CN102254551A (en) * | 2010-05-20 | 2011-11-23 | 盛乐信息技术（上海）有限公司 | Voiceprint authentication apparatus |
-
2012
- 2012-03-30 CN CN2012101031421A patent/CN103366743A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1090708A (en) * | 1992-09-16 | 1994-08-17 | 德山曹达株式会社 | Antibacterial Agents and Their Utilization |
| CN1319223A (en) * | 1998-09-21 | 2001-10-24 | 汤姆森多媒体公司 | System comprising remote controlled apparatus and voice-operated remote control device for apparatus |
| CN1385783A (en) * | 2001-05-14 | 2002-12-18 | 索尼电脑娱乐美国公司 | System and method for controllnig role by menu driven speech sound in game environment |
| CN1425980A (en) * | 2003-01-14 | 2003-06-25 | 杨宏惠 | Personalized opening computer voice log-in method |
| CN1674540A (en) * | 2004-03-25 | 2005-09-28 | 联想(北京)有限公司 | Method for central controlling home appliances based on home appliances control center |
| CN1993732A (en) * | 2004-08-06 | 2007-07-04 | 皇家飞利浦电子股份有限公司 | A method for a system of performing a dialogue communication with a user |
| CN101516005A (en) * | 2008-02-23 | 2009-08-26 | 华为技术有限公司 | Speech recognition channel selecting system, method and channel switching device |
| CN101557432A (en) * | 2008-04-08 | 2009-10-14 | Lg电子株式会社 | Mobile terminal and menu control method thereof |
| CN101625857A (en) * | 2008-07-10 | 2010-01-13 | 新奥特（北京）视频技术有限公司 | Self-adaptive voice endpoint detection method |
| CN102254551A (en) * | 2010-05-20 | 2011-11-23 | 盛乐信息技术（上海）有限公司 | Voiceprint authentication apparatus |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104735634A (en) * | 2013-12-24 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Pay account linking management method, mobile terminal, server and system |
| WO2015103836A1 (en) * | 2014-01-07 | 2015-07-16 | 深圳市中兴微电子技术有限公司 | Voice control method and device |
| CN103795715A (en) * | 2014-01-20 | 2014-05-14 | 冯丽娟 | Privacy protection method, privacy recovery method and privacy protection system |
| CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
| CN108369772A (en) * | 2015-12-17 | 2018-08-03 | 达泰多公司 | Method and apparatus for analyzing and distributing voice command |
| WO2017177766A1 (en) * | 2016-04-12 | 2017-10-19 | 深圳市京华信息技术有限公司 | Virtual reality device control method and apparatus, and virtual reality device and system |
| CN106992009A (en) * | 2017-05-03 | 2017-07-28 | 深圳车盒子科技有限公司 | Vehicle-mounted voice exchange method, system and computer-readable recording medium |
| CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
| CN109346081A (en) * | 2018-12-20 | 2019-02-15 | 广州河东科技有限公司 | Voice control method, device, equipment and storage medium |
| CN109788039A (en) * | 2018-12-26 | 2019-05-21 | 合肥凯捷技术有限公司 | A kind of interactive system for vehicle-mounted voice storage method |
| CN109859748A (en) * | 2019-01-15 | 2019-06-07 | 福建天眼视讯网络科技有限公司 | Intercom based on the automatic recognition of speech realizes system and method |
| CN109859748B (en) * | 2019-01-15 | 2021-06-04 | 福建天眼视讯网络科技有限公司 | Intercom implementation system and method based on voice automatic identification |
| CN111326145A (en) * | 2020-01-22 | 2020-06-23 | 南京雷鲨信息科技有限公司 | Speech model training method, system and computer readable storage medium |
| CN114974232A (en) * | 2021-02-27 | 2022-08-30 | 博泰车联网(南京)有限公司 | Voice information processing method and related product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103366743A (en) | Voice-command operation method and device | |
| CN107895578B (en) | Voice interaction method and device | |
| US20180218735A1 (en) | Speech recognition involving a mobile device | |
| KR100958961B1 (en) | Voice interface for NFC applications | |
| EP2087446B1 (en) | Adaptive databases | |
| CN114830228A (en) | Account associated with a device | |
| US20060173859A1 (en) | Apparatus and method for extracting context and providing information based on context in multimedia communication system | |
| CN104834847A (en) | Identity verification method and device | |
| KR101696555B1 (en) | Text location search system in image information or geographic information using voice recognition function and method thereof | |
| CN107623614A (en) | Method and apparatus for pushed information | |
| CN108986790A (en) | The method and apparatus of voice recognition of contact | |
| CN107221330A (en) | Punctuate adding method and device, the device added for punctuate | |
| JP5283947B2 (en) | Voice recognition device for mobile terminal, voice recognition method, voice recognition program | |
| CN104978045B (en) | A kind of Chinese character input method and device | |
| CN106341539A (en) | Automatic evidence obtaining method of malicious caller voiceprint, apparatus and mobile terminal thereof | |
| CN105139848B (en) | Data transfer device and device | |
| KR20150060300A (en) | System for command operation using speech recognition and method thereof | |
| JP2009175630A (en) | Speech recognition device, mobile terminal, speech recognition system, speech recognition device control method, mobile terminal control method, control program, and computer readable recording medium with program recorded therein | |
| CN105898002A (en) | Application unlocking method and apparatus for mobile terminal and mobile terminal | |
| WO2019101099A1 (en) | Video program identification method and device, terminal, system, and storage medium | |
| CN105096962B (en) | A kind of information processing method and terminal | |
| KR100920442B1 (en) | How to Retrieve Information from Your Mobile Device | |
| US20070129949A1 (en) | System and method for assisted speech recognition | |
| CN114465975B (en) | Content pushing method, device, storage medium and chip system | |
| KR100554442B1 (en) | Mobile communication terminal with speech recognition function, phoneme modeling method and speech recognition method therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20131023 |