Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In subsequent description, it is only using the suffix for indicating such as " module ", " component " or " unit " of elementBe conducive to explanation of the invention, itself there is no a specific meaning.Therefore, " module ", " component " or " unit " can mixGround uses.
Terminal can be implemented in a variety of manners.For example, terminal described in the present invention may include such as mobile phone, plateComputer, laptop, palm PC, personal digital assistant (Personal Digital Assistant, PDA), portableMedia player (Portable Media Player, PMP), navigation device, wearable device, Intelligent bracelet, pedometer etc. moveThe fixed terminals such as dynamic terminal, and number TV, desktop computer.
It will be illustrated by taking mobile terminal as an example in subsequent descriptions, it will be appreciated by those skilled in the art that in addition to specialExcept element for moving purpose, the construction of embodiment according to the present invention can also apply to the terminal of fixed type.
Referring to Fig. 1, a kind of hardware structural diagram of its mobile terminal of each embodiment to realize the present invention, the shiftingDynamic terminal 100 may include: RF (Radio Frequency, radio frequency) unit 101, WiFi module 102, audio output unit103, A/V (audio/video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit108, the components such as memory 109, processor 110 and power supply 111.It will be understood by those skilled in the art that shown in Fig. 1Mobile terminal structure does not constitute the restriction to mobile terminal, and mobile terminal may include components more more or fewer than diagram,Perhaps certain components or different component layouts are combined.
It is specifically introduced below with reference to all parts of the Fig. 1 to mobile terminal:
Radio frequency unit 101 can be used for receiving and sending messages or communication process in, signal sends and receivees, specifically, radio frequency listUplink information can be sent to base station by member 101, after the downlink information that in addition can also be sent base station receives, be sent to movementThe processor 110 of terminal is handled, and base station can be to the downlink information that radio frequency unit 101 is sent and be sent according to radio frequency unit 101Uplink information generate, be also possible to after the information update for detecting mobile terminal actively to push to radio frequency unit 101,For example, base station can be to the radio frequency unit 101 of mobile terminal after detecting that geographical location locating for mobile terminal changesThe message informing of geographical location variation is sent, radio frequency unit 101 can send out the message informing after receiving the message informingThe processor 110 for giving mobile terminal is handled, and the processor 110 of mobile terminal can control the message informing and be shown in movement eventuallyOn the display panel 1061 at end；In general, radio frequency unit 101 include but is not limited to antenna, at least one amplifier, transceiver,Coupler, low-noise amplifier, duplexer etc..In addition, radio frequency unit 101 can also by wireless communication with network and other setStandby communication, specifically may include: by wireless communication with the server communication in network system, for example, mobile terminal can be withFile resource is downloaded from server by wireless communication, for example application program can be downloaded from server, in mobile terminalAfter the downloading of a certain application program is completed, if the corresponding file resource of the application program updates in server, the serverIt can be by wireless communication to the message informing of mobile terminal push resource updates, to remind user to carry out more the application programNewly.Any communication standard or agreement, including but not limited to GSM (Global System of can be used in above-mentioned wireless communicationMobile communication, global system for mobile communications), GPRS (General Packet Radio Service, it is generalBe grouped wireless service), CDMA2000 (Code Division Multiple Access 2000, CDMA 2000), WCDMA(Wideband Code Division Multiple Access, wideband code division multiple access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access, TD SDMA), FDD-LTE (FrequencyDivision Duplexing-Long Term Evolution, frequency division duplex long term evolution) and TDD-LTE (TimeDivision Duplexing-Long Term Evolution, time division duplex long term evolution) etc..
WiFi belongs to short range wireless transmission technology, and mobile terminal can help user to receive and dispatch electricity by WiFi module 102Sub- mail, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Fig. 1 showsGo out WiFi module 102, but it is understood that, and it is not belonging to must be configured into for mobile terminal, it completely can be according to needIt to omit within the scope of not changing the essence of the invention.
Audio output unit 103 can be in call signal reception pattern, call mode, record mould in mobile terminal 100When under the isotypes such as formula, speech recognition mode, broadcast reception mode, by radio frequency unit 101 or WiFi module 102 it is received orThe audio data stored in memory 109 is converted into audio signal and exports to be sound.Moreover, audio output unit 103Audio output relevant to the specific function that mobile terminal 100 executes can also be provided (for example, call signal receives sound, disappearsBreath receives sound etc.).Audio output unit 103 may include loudspeaker, buzzer etc..
A/V input unit 104 is for receiving audio or video signal.A/V input unit 104 may include graphics processor(Graphics Processing Unit, GPU) 1041 and microphone 1042, graphics processor 1041 is in video acquisition modeOr the image data of the static images or video obtained in image capture mode by image capture apparatus (such as camera) carries outReason.Treated, and picture frame may be displayed on display unit 106.Through graphics processor 1041, treated that picture frame can be depositedStorage is sent in memory 109 (or other storage mediums) or via radio frequency unit 101 or WiFi module 102.MikeWind 1042 can connect in telephone calling model, logging mode, speech recognition mode etc. operational mode via microphone 1042Quiet down sound (audio data), and can be audio data by such acoustic processing.Audio that treated (voice) data canTo be converted to the format output that can be sent to mobile communication base station via radio frequency unit 101 in the case where telephone calling model.Microphone 1042 can be implemented various types of noises elimination (or inhibition) algorithms and send and receive sound to eliminate (or inhibition)The noise generated during frequency signal or interference.
Mobile terminal 100 further includes at least one sensor 105, such as optical sensor, motion sensor and other biographiesSensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environmentThe light and shade of light adjusts the brightness of display panel 1061, and proximity sensor can close when mobile terminal 100 is moved in one's earDisplay panel 1061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generalFor three axis) size of acceleration, it can detect that size and the direction of gravity when static, can be used to identify the application of mobile phone posture(such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, percussion) etc.；The fingerprint sensor that can also configure as mobile phone, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer,The other sensors such as hygrometer, thermometer, infrared sensor, details are not described herein.
Display unit 106 is for showing information input by user or being supplied to the information of user.Display unit 106 can wrapDisplay panel 1061 is included, specifically, active matrix organic light-emitting diode (Active Matrix/Organic can be usedLight-Emitting Diode, AMOLED), the shapes such as passive organic electric exciting light-emitting diode (Passive matrix OLED)Formula configures display panel 1061.
User input unit 107 can be used for receiving the number or character information of input, and generate the use with mobile terminalFamily setting and the related key signals input of function control.Specifically, user input unit 107 may include touch panel 1071 withAnd other input equipments 1072.Touch panel 1071, also referred to as touch screen collect the touch operation of user on it or nearby(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 1071 or in touch panel 1071Neighbouring operation), and corresponding attachment device is driven according to preset formula.Touch panel 1071 may include touch detectionTwo parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation bandThe signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by itIt is converted into contact coordinate, then gives processor 110, and order that processor 110 is sent can be received and executed.In addition, canTo realize touch panel 1071 using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch panel1071, user input unit 107 can also include other input equipments 1072.Specifically, other input equipments 1072 can wrapIt includes but is not limited in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating stick etc.It is one or more, specifically herein without limitation.
Further, touch panel 1071 can cover display panel 1061, when touch panel 1071 detect on it orAfter neighbouring touch operation, processor 110 is sent to determine the type of touch event, is followed by subsequent processing device 110 according to touch thingThe type of part provides corresponding visual output on display panel 1061.Although in Fig. 1, touch panel 1071 and display panel1061 be the function that outputs and inputs of realizing mobile terminal as two independent components, but in certain embodiments, it canThe function that outputs and inputs of mobile terminal is realized so that touch panel 1071 and display panel 1061 is integrated, is not done herein specificallyIt limits.For example, when by radio frequency unit 101 receive the message informing of a certain application program when, processor 110 can control byThe message informing is shown in a certain predeterminable area of display panel 1061, a certain area of the predeterminable area and touch panel 1071Domain is corresponding, can be in corresponding region on display panel 1061 by carrying out touch control operation to a certain region of touch panel 1071The message informing of display is controlled.
Interface unit 108 be used as at least one external device (ED) connect with mobile terminal 100 can by interface.For example,External device (ED) may include wired or wireless headphone port, external power supply (or battery charger) port, wired or nothingLine data port, memory card port, the port for connecting the device with identification module, audio input/output (I/O) endMouth, video i/o port, ear port etc..Interface unit 108 can be used for receiving the input from external device (ED) (for example, numberIt is believed that breath, electric power etc.) and the input received is transferred to one or more elements in mobile terminal 100 or can be withFor transmitting data between mobile terminal 100 and external device (ED).
Memory 109 can be used for storing software program and various data.Memory 109 can mainly include storing program areaThe storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one functionSound playing function, image player function etc.) etc.；Storage data area can store according to mobile phone use created data (such asAudio data, phone directory etc.) etc..In addition, memory 109 may include high-speed random access memory, it can also include non-easyThe property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 110 is the control centre of mobile terminal, utilizes each of various interfaces and the entire mobile terminal of connectionA part by running or execute the software program and/or module that are stored in memory 109, and calls and is stored in storageData in device 109 execute the various functions and processing data of mobile terminal, to carry out integral monitoring to mobile terminal.PlaceManaging device 110 may include one or more processing units；Preferably, processor 110 can integrate application processor and modulatedemodulate is mediatedManage device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainProcessing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 110.
Mobile terminal 100 can also include the power supply 111 (such as battery) powered to all parts, it is preferred that power supply 111Can be logically contiguous by power-supply management system and processor 110, to realize management charging by power-supply management system, putThe functions such as electricity and power managed.
Although Fig. 1 is not shown, mobile terminal 100 can also be including bluetooth module etc., and details are not described herein.
Embodiment to facilitate the understanding of the present invention, the communications network system that mobile terminal of the invention is based below intoRow description.
Referring to Fig. 2, Fig. 2 is a kind of communications network system architecture diagram provided in an embodiment of the present invention, the communication network systemSystem is the LTE system of universal mobile communications technology, which includes UE (User Equipment, the use of successively communication connectionFamily equipment) (the land Evolved UMTS Terrestrial Radio Access Network, evolved UMTS 201, E-UTRANGround wireless access network) 202, EPC (Evolved Packet Core, evolved packet-based core networks) 203 and operator IP operation204。
Specifically, UE201 can be above-mentioned terminal 100, and details are not described herein again.
E-UTRAN202 includes eNodeB2021 and other eNodeB2022 etc..Wherein, eNodeB2021 can be by returningJourney (backhaul) (such as X2 interface) is connect with other eNodeB2022, after UE201 is connect with eNodeB2021, can receiveTo the PUSH message notice sent by eNodeB2021, eNodeB2021 may be coupled to EPC203, and eNodeB2021 can be mentionedFor the access of UE201 to EPC203.
EPC203 may include MME (Mobility Management Entity, mobility management entity) 2031, HSS(Home Subscriber Server, home subscriber server) 2032, other MME2033, SGW (Serving Gate Way,Gateway) 2034, PGW (PDN Gate Way, grouped data network gateway) 2035 and PCRF (Policy andCharging Rules Function, policy and rate functional entity) 2036 etc..Wherein, MME2031 be processing UE201 andThe control node of signaling, provides carrying and connection management between EPC203.HSS2032 is all to manage for providing some registersSuch as the function of home location register (not shown) etc, and preserves some related service features, data rates etc. and useThe dedicated information in family.All customer data can be sent by SGW2034, and PGW2035 can provide the IP of UE 201Address distribution and other functions, PCRF2036 are strategy and the charging control strategic decision-making of business data flow and IP bearing resourcePoint, it selects and provides available strategy and charging control decision with charge execution function unit (not shown) for strategy.
IP operation 204 may include internet, Intranet, IMS (IP Multimedia Subsystem, IP multimediaSystem) or other IP operations etc..
Although above-mentioned be described by taking LTE system as an example, those skilled in the art should know the present invention is not onlySuitable for LTE system, be readily applicable to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA withAnd the following new network system etc., herein without limitation.
Based on above-mentioned mobile terminal hardware configuration and communications network system, each embodiment of the present invention is proposed.
First embodiment
In order to solve the cumbersome slow, low efficiency of the matching process of speech recognition in the prior art, user experience is causedThe problem of difference.The present embodiment provides a kind of voice identification control method, this method is by obtaining when monitoring receives voice dataThe Pinyin information set for taking the default entry in terminal carries out identifying processing to the voice data received and determines that first is to be matchedPinyin information, then successively by the letter of letter and each Pinyin information in Pinyin information set in the first Pinyin information to be matchedIt is matched, and calculates the matching result of the first Pinyin information to be matched and each Pinyin information in matching process in real time, in turnThe matching process of the first Pinyin information to be matched and each Pinyin information is controlled according to matching result.Specifically it may refer to shown in Fig. 3,Fig. 3 is the basic flow chart of voice identification control method provided in this embodiment, which includes:
S301: when monitoring receives voice data, the Pinyin information set of the default entry in terminal is obtained.
It is understood that the present invention is suitable for any end by connecting/being built-in with microphone, support speech recognitionEnd, such as wearable device, smart phone, laptop, tablet computer etc., while will also be appreciated that voice numberIt is issued according to the vocal organs referred to by people, the voice data with the language-specific meaning that user is intended by.
It will be clear that the Pinyin information set reference of the default entry in terminal is stored default in terminalThe set of the Pinyin information of entry.In some embodiments, default entry includes the corresponding entry of all applications, example in terminalSuch as, if all applications installed in terminal are A, B, C, D, E, F, G, H, then default entry refer to be using A, B, C, D, E,F, the corresponding text information of G, H.In further embodiments, default entry includes the corresponding word of certain applications in terminalItem, for example, set all applications installed in terminal still as A, B, C, D, E, F, G, H, and default entry refers only to be using A,B, the corresponding text information of C, D, and do not refer to using the corresponding text information of E, F, G, H.In some other realityIt applies in example, default entry includes the entry in each application, for example, setting using as address list, the contact name in address list isA, b, c, d, e, f, g, then default entry reference is the corresponding text information of contact person a, b, c, d, e, f, g.
It is worth noting that, be only the explanation carried out by taking several frequently seen situation as an example to default entry here,In practical application, default entry carries out flexible setting by developer, naturally it is also possible to carry out customized setting by user.It can be withUnderstand, the end message that default entry includes is more, and the result of speech recognition is more acurrate.
It in the present embodiment, further include being pre-processed to default entry before monitoring receives voice data.Specifically, the text information of the default entry in terminal is converted into Pinyin information, for example, " wei will be converted to using " wechat "Xin ", or will be converted to " wei bo " using " microblogging ", or " mei yan xiang ji " will be converted to using " U.S. face camera "Etc.；Specifically, Pinyin information can also be converted to the digital information of the default entry in terminal, for example, will be using communicationThe contact person's " opening 3 " for recording the inside is converted to " zhang san ", " zhang shan ", or will be using the contact person inside address list" Lee 4 " are converted to " li si ", " ni shi " etc.；Specifically, working as the text information and/or number of the default entry in terminalAfter word information is converted to Pinyin information, Fuzzy processing can also be carried out to Pinyin information, it is to be understood that at blurringReason is commonly easily to obscure pronunciation for user, for example, flat tongue-sticks up tongue, pre-nasal sound --- rear nasal sound etc., here with specificExample is illustrated, for example, carrying out Fuzzy processing after being converted to " wei xin " using " wechat " to it and obtaining " weiXing ", or after " mei yan xiang ji " being converted to using " U.S. face camera ", Fuzzy processing is carried out to it and is obtained“mei yang xiang ji”、“mei yang xian ji”、“mei yang xian ji”、“mei yang xiangJing ", or after address book contact " Ni Ni " is converted to " ni ni ", it is carried out Fuzzy processing obtain " ni li "," li li ", " li ni " etc..
It is noted that being only the explanation carried out with some specific examples to pretreatment here, in practical applicationIn, adaptation adjustment need to be done as the case may be.In addition, it should be noted that in the present embodiment, default entry is carried outPretreatment is before speech recognition process, i.e., the voice data that speech recognition process need to only will acquire is converted to phonetic letterThen breath directly matches it with the Pinyin information for carrying out pretreated default entry, and without getting voiceDefault entry is pre-processed when data, namely in the present embodiment, pre- place has been carried out to the default entry in terminal in advanceReason only need to directly acquire the Pinyin information set that pretreated default entry is carried out in terminal in speech recognition process, greatlyIt saves greatly and in speech recognition process is carried out to default entry the pretreated time, and then greatly improve the speed of speech recognitionDegree.
S302: identifying processing is carried out to the voice data received and obtains recognition result.
It will be clear that when monitoring receives voice data, it is also necessary to be identified to the voice data receivedProcessing obtains recognition result, it is to be understood that identifying processing can use existing any language identifying processing technology, be knownNot as a result, the emphasis of identifying processing and non-present invention, does not illustrate excessively herein.
It should be noted that can first obtain the spelling of the default entry in terminal when monitoring receives voice dataSound information aggregate, then identifying processing is carried out to the voice data received and obtains recognition result；Or it can be first to receivingVoice data carries out identifying processing and obtains recognition result, then obtains the Pinyin information set of the default entry in terminal；Or it obtainsWhile taking the Pinyin information set of the default entry in terminal, identifying processing is carried out to the voice data received and is identifiedAs a result.
S303: the first Pinyin information to be matched is determined according to recognition result.
It will be clear that determining that the first Pinyin information to be matched at least has following four mode according to recognition result:
Mode one: using the Pinyin information of all texts in recognition result as the first Pinyin information to be matched.
For a better understanding, being illustrated here with example, for example, setting recognition result as " east ", at this time will" zhang dong " is used as the first Pinyin information to be matched.
Mode two: extracting keyword from recognition result, using the Pinyin information of keyword as the first phonetic to be matchedInformation.
Still taking the above example as an example, if recognition result is " east ", " opening " is extracted from " east " at this time, at this time will" zhang " is used as the first Pinyin information to be matched.
Mode three: after the Pinyin informations of all texts in recognition result is carried out Fuzzy processing, as first toWith Pinyin information.
Still taking the above example as an example, if recognition result is " east ", Fuzzy processing is carried out to " zhang dong " at this time" zhan don ", " zang dong ", " zhan dong " are obtained, at this time by " zhan don ", " zang dong ", " zhanDong " is used as the first Pinyin information to be matched.
Mode four: extracting keyword from recognition result, after the Pinyin information of keyword is carried out Fuzzy processing, makeesFor the first Pinyin information to be matched.
Still taking the above example as an example, it if recognition result is " east ", is extracted " opening " from " east " at this time, it is right" zhang " carries out Fuzzy processing and obtains " zhan ", " zang ", " zan ", regard " zhan ", " zang ", " zan " as the at this timeOne Pinyin information to be matched.
It is worth noting that, being only common to determine the first Pinyin information to be matched according to recognition result with four kinds hereIt is illustrated for mode, the invention is not limited to these four modes, as long as in fact, can determine first according to recognition resultThe mode of Pinyin information to be matched is within the scope of the invention.
S304: successively by the word of letter and each Pinyin information in Pinyin information set in the first Pinyin information to be matchedMother matches.
For a better understanding, be illustrated here with example, for example, set the first Pinyin information to be matched as " li ni ",Simultaneously set Pinyin information present in Pinyin information set be respectively " zhang ming ", " zhang min ", " xiao hong "," li qiang ", " zhu tang yu ", " ni ni ", " ni ling ", at this time by " li ni " respectively with " zhang ming "," zhang min ", " xiao hong ", " li qiang ", " zhu tang yu ", " ni ni ", " ni ling " are matched, toolBody, when being matched " li ni " with " zhang ming ", by the first letter " l " of " li ni " and " zhangThe first letter " z " of ming " matches, by the second letter of the second letter " i " of " li ni " and " zhang ming "" h " matching matches the third of " li ni " alphabetical " n " with the 6th letter " m " of " zhang ming ", by " li ni "4th letter " i " matches with the 7th letter " i " of " zhang ming ", it is to be understood that subsequent successively by " li ni "With the matching process of other Pinyin informations in Pinyin information set and the matching process phase of " li ni " and " zhang ming "Together, which is not described herein again.
In the present embodiment, it can first be picked out from Pinyin information set and the first Pinyin information number of letters to be matchedLesser Pinyin information is differed to be matched, for example, accept upper example, picked out from above-mentioned Pinyin information set " ni ni "," ni ling ", at this time successively matches " li ni " and " ni ni ", " ni ling ".It will be evident that first from Pinyin information collectionIt is picked out in conjunction and differs the matched mode of lesser Pinyin information progress with the first Pinyin information number of letters to be matched, improvedMatched speed avoids unnecessary matching process, and also improves matched success rate, is more excellent mode.
It is worth noting that, being only the explanation carried out by taking specific example as an example here, in practical applications, need according to specificSituation do adaptation adjustment, meanwhile, in practical applications, the Pinyin information in Pinyin information set be often it is very much, here forFacilitate elaboration, only to include that a small amount of Pinyin information is illustrated in Pinyin information set.
S305: the matching result of the first Pinyin information to be matched and each Pinyin information in matching process, root are calculated in real timeThe matching process of the first Pinyin information to be matched and each Pinyin information is controlled according to matching result.
It will be clear that in the present embodiment, matching process can use existing arbitrary matching technique, such as editDistance technique, the present invention are specifically limited not to this.
In the present embodiment, the matching of the first Pinyin information to be matched and each Pinyin information in matching process is calculated in real timeAs a result, controlling the matching process of the first Pinyin information to be matched and each Pinyin information according to matching result, at least there is following twoKind mode.
Mode one, referring specifically to shown in Fig. 4:
S401: the correct matching rate of the first Pinyin information to be matched and each Pinyin information in matching process is calculated in real time.
For a better understanding, being illustrated here with example, for example, setting the first Pinyin information to be matched as " liNing ", while setting Pinyin information present in Pinyin information set is respectively " zhang min ", " xiao hong ", " liQiang ", " zhu tang yu ", " ni ni ", " ni ling " pick out " ni ling " progress from Pinyin information setMatch, will " li ning " and " ni ling " carry out matched during, calculate the correct of " li nin " and " ni ling " in real timeMatching rate, specifically, by " first letter " l " of li ning " matched with the first letter " n " of " ni ling " when, currentlyCorrect matching rate be 0%, when the second letter " i " of " li ning " is matched with the second letter " i " of " ni ling ",Current correct matching rate is 16.7%, and the third of the third of " li ning " alphabetical " n " and " ni ling " is alphabetical " l "When matching, current correct matching rate is 16.7%, by the 4th letter " i " of " li ning " and the 4th of " ni ling "When alphabetical " i " matching, current correct matching rate is 33.4%, will " the 5th letter " n " of li ning " and " ni ling "The matching of the 5th letter " n " when, current correct matching rate is 50.1%, will the 6th letter " g " of " li ning " andWhen the 6th letter " g " matching of " ni ling ", current correct matching rate is 66.8%.
S402: it is default correct to judge whether the correct matching rate of the first Pinyin information to be matched and the first Pinyin information is greater thanRate threshold value, the first Pinyin information are any Pinyin information in Pinyin information set；
If so, S403 is executed, if it is not, continuing to execute S402.
It is understood that in the matching process, when correct matching rate is calculated every time, just will be calculated justTrue matching rate is compared with default accuracy threshold value, example in undertaking, further, will if default accuracy threshold value is 50%When the first letter " l " of " li nin " is matched with the first letter " n " of " ni ling ", current correct matching rate is obtainedIt is 0%, by it compared with default accuracy threshold value 50%, it will be apparent that, it is not greater than default accuracy threshold value at this time, continues " liWhen the second letter " i " of nin " is matched with the second letter " i " of " ni ling ", obtaining current correct matching rate is16.7%, it will be apparent that, it is not greater than default accuracy threshold value yet at this time, continues the third of " li nin " alphabetical " n " and " niWhen the third of ling " alphabetical " l " matching, current correct matching rate is 16.7%, by itself and default accuracy threshold value 50%Compare, it will be apparent that, it is not greater than default accuracy threshold value yet at this time, continues the 4th letter " i " of " li nin " and " niWhen the 4th letter " i " matching of ling ", current correct matching rate is 33.4%, it will be apparent that, it is greater than yet preset just at this timeTrue rate threshold value, when continuing to match the 5th letter " n " of " li nin " with the 5th letter " n " of " ni ling ", currentCorrect matching rate is 50.1%, it will be apparent that, it is greater than default accuracy threshold value at this time, executes S403 at this time.
S403: interrupting the matching process of the first Pinyin information to be matched and the first Pinyin information, and the first Pinyin information is madeFor this speech recognition result.
It is understood that being preset just when the correct matching rate of the first Pinyin information to be matched and the first Pinyin information is greater thanWhen true rate threshold value, the matching process of the first Pinyin information to be matched and the first Pinyin information is interrupted, example in undertaking, further,Interruption general " the 6th letter " g " of li ning " and the 6th matched process of letter " g " of " ni ling ", at this time by " niResult of the ling " as this speech recognition.
Mode two, referring specifically to shown in Fig. 5:
S501: the erroneous matching rate of the first Pinyin information to be matched and each Pinyin information in matching process is calculated in real time.
For a better understanding, being illustrated here with example.For a better understanding, be illustrated here with example,For example, setting the first Pinyin information to be matched as " li ning ", while setting Pinyin information present in Pinyin information set and being respectively" zhang ming ", " xiao hong ", " li qiang ", " zhu tang yu ", " ni ni ", " ni ling ", by " liNing " is matched with " zhang ming ", during " li ning " and " zhang ming " is carried out matched, in real timeCalculate the erroneous matching rate of " li ning " and " zhang ming ", specifically, by the first letter " l " of " li ning " andWhen first letter " z " matching of " zhang ming ", current erroneous matching rate is 16.7%, by the second of " li ning "When a letter " i " matches with the second letter " h " of " zhang ming ", current erroneous matching rate is 33.4%, by " liWhen the third of ning " alphabetical " n " is matched with the 6th letter " m " of " zhang ming ", current erroneous matching rate is50.1%, when the 4th letter " i " of " li ning " is matched with the 7th letter " i " of " zhang ming ", current mistakeError hiding rate is 50.1%, and the 5th letter " n " of " li ning " is matched with the 8th letter " n " of " zhang ming "When, current erroneous matching rate is 50.1%, by the 6th letter " g " of " li ning " and the 9th of " zhang ming "When alphabetical " g " matching, current erroneous matching rate is 50.1%.
S502: judge whether the erroneous matching rate of the first Pinyin information to be matched and the second Pinyin information is greater than default mistakeRate threshold value, the second Pinyin information are any Pinyin information in Pinyin information set；
If so, S503 is executed, if it is not, continuing to execute S502.
It is understood that in the matching process, when erroneous matching rate is calculated every time, the mistake that just will be calculatedError hiding rate is compared with default error rate threshold, example in undertaking, further, will if default error rate threshold is 50%When the first letter " l " of " li ning " is matched with the first letter " z " of " zhang ming ", current mistake is obtainedIt is 16.7% with rate, it is compared with default error rate threshold 16.7%, it will be apparent that, it is not greater than default error rate threshold at this timeValue when continuing to match the second letter " i " of " li ning " with the second letter " h " of " zhang ming ", obtains currentErroneous matching rate be 33.4%, it will be apparent that, be greater than default error rate threshold yet at this time, continue the third of " li ning "When a letter " n " matches with the 6th letter " m " of " zhang ming ", obtaining current erroneous matching rate is 50.1%, brightAobvious, it is greater than default error rate threshold at this time, executes S503 at this time.
S503: the matching process of the first Pinyin information to be matched and the second Pinyin information is interrupted.
It is understood that when the erroneous matching rate of the first Pinyin information to be matched and the first Pinyin information is greater than default mistakeAccidentally when rate threshold value, the matching process of the first Pinyin information to be matched and the first Pinyin information is interrupted, example in undertaking, further,Interruption matches the 5th letter " n " of " li ning " with the 8th letter " n " of " zhang ming ", and by " liThe 6th letter " g " of ning " and the 9th matched process of letter " g " of " zhang ming ".
It is worth noting that, being only the explanation carried out with specific example here, in practical applications, need as the case may beDo adaptation adjustment, simultaneously, it should be noted that in practical applications, preset accuracy threshold value and default error rate threshold byDeveloper carries out flexible setting according to experiment or experience.
Finally, it should be noted that four kinds of modes for determining the first Pinyin information to be matched according to recognition result of above-mentioned introductionSequential relationship.Specifically, using the Pinyin information of texts all in recognition result as the first Pinyin information to be matched, according to matchingAs a result after the matching process for controlling Pinyin information to be matched and each Pinyin information, also need to judge whether deposit in Pinyin information setMeet the first preset condition in the matching result of at least one Pinyin information and the first Pinyin information to be matched, first herein is pre-What if condition referred to is that the first Pinyin information to be matched is matched with each Pinyin information in Pinyin information set, phonetic letterIt whether there is the Pinyin information for reaching the first preset matching degree threshold value with the matching degree of the first Pinyin information to be matched in breath set,If it exists, just directly it will reach preset matching with the matching degree of the first Pinyin information to be matched at this time without carrying out subsequent stepThe Pinyin information of degree threshold value then extracts keyword if it does not exist as this speech recognition result from recognition result again,Using the Pinyin information of keyword as the second Pinyin information to be matched, successively by the alphabetical and spelling in the second Pinyin information to be matchedThe letter of each Pinyin information in sound information aggregate is matched, at this point, still needing to judge in Pinyin information set with the presence or absence of extremelyThe matching result of a few Pinyin information and the second Pinyin information to be matched meets the second preset condition, the default item of second hereinWhen what part referred to is that the second Pinyin information to be matched is matched with each Pinyin information in Pinyin information set, Pinyin information collectionWith the presence or absence of the Pinyin information for reaching the second preset matching degree threshold value with the matching degree of the second Pinyin information to be matched in conjunction, if depositingJust without carrying out subsequent step, directly preset matching degree threshold will reached with the matching degree of the second Pinyin information to be matched at this timeThe Pinyin information of value if it does not exist then believes the phonetic of all texts in recognition result as this speech recognition resultAfter breath carries out Fuzzy processing, as third Pinyin information to be matched, or keyword is extracted from recognition result, by keywordPinyin information carry out Fuzzy processing after, as third Pinyin information to be matched, then successively by third Pinyin information to be matchedIn letter matched with the letter of each Pinyin information in Pinyin information set, obtain the result of this speech recognition.
It is worth noting that, the first preset matching degree threshold value and the second preset matching degree threshold value can be identical, it can also notIt is identical, in practical applications, the first preset matching degree threshold value and the second preset matching degree threshold value by developer according to experiment orExperience carries out flexible setting.
The sequential relationship of four kinds of modes that the first Pinyin information to be matched is determined according to recognition result according to the above descriptionIt is found that in the present embodiment, first carrying out full word matching, then carry out part matching, finally carrying out fuzzy matching, can preferably mentionThe speed of high speech recognition, and then the efficiency of speech recognition is improved, namely when phonetic letter existing during full word is matchedWhen breath reaches preset matching degree threshold value with the matching degree of Pinyin information to be matched, by the Pinyin information directly as this voiceRecognition result is not deposited just without carrying out subsequent part matching process and fuzzy matching procedure when during full word is matchedWhen the matching degree of Pinyin information and Pinyin information to be matched reaches matching degree threshold value, just execution part is matched at this time, when in portionWhen the matched matching degree of existing Pinyin information and Pinyin information to be matched in the process being divided to reach preset matching degree threshold value, by thisPinyin information matches just without carrying out subsequent fuzzy matching procedure when in part directly as this speech recognition resultDuring when reaching matching degree threshold value there is no the matching degree of Pinyin information and Pinyin information to be matched, just execute at this time fuzzyMatching, obtains this speech recognition result.
Voice identification control method provided in this embodiment, this method is by obtaining when monitoring receives voice dataThe Pinyin information set of default entry in terminal carries out identifying processing to the voice data received and obtains recognition result, andThe first Pinyin information to be matched is determined according to recognition result, then successively believes the letter in the first Pinyin information to be matched with phoneticThe letter of each Pinyin information in breath set is matched, and calculate in real time the first Pinyin information to be matched in matching process withThe matching result of each Pinyin information, and then according to the matching of matching result the first Pinyin information to be matched and each Pinyin information of controlProcess.It solves the cumbersome slow, low efficiency of matching process of speech recognition in the prior art, causes asking for user experience differenceTopic.Namely in the present embodiment, by calculating the first Pinyin information to be matched in matching process and each Pinyin information in real timeMatching result, and then controlled according to matching process of the matching result to the first Pinyin information to be matched and each Pinyin information,Reduce unnecessary matching process during speech recognition match, while avoiding the waste of unnecessary matching resource, greatlyThe speed of speech recognition is improved greatly, and also improves the efficiency of speech recognition, so that the experience satisfaction of user is more preferable.
Meanwhile in the present embodiment, the default entry in terminal is pre-processed in advance, in speech recognition processThe Pinyin information set for carrying out pretreated default entry in terminal only need to be directly acquired, is greatly saved in speech recognitionIn journey is carried out to default entry the pretreated time, further improves the speed of speech recognition.
Second embodiment
The present embodiment is on the basis of first embodiment, to this hair by taking a kind of specific voice identification control method as an exampleBright work further illustrates, and specifically may refer to Fig. 6.
S601: judge whether to receive voice data；
If so, S602 is executed, if it is not, continuing to execute S601.
If user has input voice data a according to self demand, by " voice assistant ", at this point, acquisition user is currently defeatedThe voice data a entered.
S602: the Pinyin information set of the default entry in terminal is obtained.
Example in undertaking further if the Pinyin information collection of the default entry in terminal is combined into A, obtains phonetic letter at this timeCease set A.
S603: identifying processing is carried out to the voice data received and obtains recognition result.
Example in undertaking further carries out identifying processing to obtain recognition result being " mobile phone house keeper " to voice data a.
It is worth noting that, S602, S603 have no timing limitation, commutative sequence is executed, can also be performed simultaneously.
S604: using the Pinyin information of all texts in recognition result as the first Pinyin information to be matched.
" shou ji guan jia " is further used as the first Pinyin information to be matched by example in undertaking.
S605: successively by the word of letter and each Pinyin information in Pinyin information set in the first Pinyin information to be matchedMother matches.
Example in undertaking, further, if the Pinyin information in Pinyin information set A is respectively " shou ji guanJia ", " shou ji zhu shou ", " shou ji shang dian ", " shou ji guan li zhu shou ", byIn one Pinyin information " shou ji guan jia " to be matched letter respectively with " shou ji guan jia ", " shou jiZhu shou ", " shou ji shang dian ", the letter in " shou ji guan li zhu shou " are matched, becauseMatching process is identical, following only with one specifically by the first Pinyin information " shou ji to be matched in order not to repeat to repeatLetter in guan jia " be illustrated for matched process with Pinyin information " shou ji guan jia " letter.
S606: the correct matching rate of the first Pinyin information to be matched and each Pinyin information in matching process is calculated in real time.
Example in undertaking further by the letter in the first Pinyin information " shou ji guan jia " to be matched and is spelledWhen letter in message breath " shou ji guan jia " is matched, the first Pinyin information " shou ji to be matched is calculated in real timeCorrect matching rate in guan jia " and the matching process of Pinyin information " shou ji guan jia " each letter.
S607: it is default correct to judge whether the correct matching rate of the first Pinyin information to be matched and the first Pinyin information is greater thanRate threshold value, the first Pinyin information are any Pinyin information in Pinyin information set；
If so, S608 is executed, if it is not, executing S605.
Example in undertaking, further, if being matched in the first Pinyin information " shou ji guan jia " to be matchedIt has been greater than default accuracy threshold value when ten letters, has executed S608 at this time.
S608: interrupting the matching process of the first Pinyin information to be matched and the first Pinyin information, and the first Pinyin information is madeFor this speech recognition result.
Example in undertaking, further, interrupting at this time will be in the first Pinyin information " shou ji guan jia " to be matchedLetter carries out matched process with the letter in Pinyin information " shou ji guan jia ", directly by Pinyin information " shou jiSpeech recognition result of the guan jia " as this.
Voice identification control method provided in this embodiment, this method is by obtaining when monitoring receives voice dataThe Pinyin information set of default entry in terminal carries out identifying processing to the voice data received and obtains recognition result, andThe first Pinyin information to be matched is determined according to recognition result, then successively believes the letter in the first Pinyin information to be matched with phoneticThe letter of each Pinyin information in breath set is matched, and calculate in real time the first Pinyin information to be matched in matching process withThe matching result of each Pinyin information, and then according to the matching of matching result the first Pinyin information to be matched and each Pinyin information of controlProcess.It solves the cumbersome slow, low efficiency of matching process of speech recognition in the prior art, causes asking for user experience differenceTopic.Namely in the present embodiment, by calculating the first Pinyin information to be matched in matching process and each Pinyin information in real timeMatching result, and then controlled according to matching process of the matching result to the first Pinyin information to be matched and each Pinyin information,Reduce unnecessary matching process during speech recognition match, while avoiding the waste of unnecessary matching resource, greatlyThe speed of speech recognition is improved greatly, and also improves the efficiency of speech recognition, so that the experience satisfaction of user is more preferable.
3rd embodiment
Shown in Figure 7 the present embodiment provides a kind of terminal, terminal provided in this embodiment includes processor 701, depositsReservoir 702 and communication bus 703.
Wherein, the communication bus 703 in the present embodiment is logical for realizing the connection between processor 701 and memory 702Letter, processor 701 is then for executing one or more first program stored in memory 702, to perform the steps of
When monitoring receives voice data, the Pinyin information set of the default entry in terminal is obtained；
Identifying processing is carried out to the voice data received and obtains recognition result；
The first Pinyin information to be matched is determined according to recognition result；
Successively by the first Pinyin information to be matched letter with Pinyin information set in each Pinyin information letter intoRow matching；
The matching result for calculating the first Pinyin information to be matched and each Pinyin information in matching process in real time, according to matchingAs a result the matching process of the first Pinyin information to be matched and each Pinyin information is controlled.
It is worth noting that, not fully expounding the institute in embodiment one, two in the present embodiment in order not to burden explanationThere is example, it is understood that, all examples in embodiment one, two are suitable for the present embodiment.
The present embodiment also provides a kind of computer readable storage medium, computer-readable recording medium storage have one orMultiple programs, one or more program can be executed by one or more processor, as above state speech recognition controlled to realizeThe step of method.
Terminal provided in this embodiment and computer readable storage medium can also realize a kind of specific speech recognition controlMethod processed, for details, reference can be made to shown in Fig. 8:
S801: judge whether to receive voice data；
If so, S802 is executed, if it is not, continuing to execute S801.
If user has input voice data b according to self demand, by " voice assistant ", at this point, acquisition user is currently defeatedThe voice data b entered.
S802: the Pinyin information set of the default entry in terminal is obtained.
Example in undertaking further if the Pinyin information collection of the default entry in terminal is combined into B, obtains phonetic letter at this timeCease set B.
S803: identifying processing is carried out to the voice data received and obtains recognition result.
Example in undertaking further carries out identifying processing to obtain recognition result being " Zhang Mingming " to voice data b.
It is worth noting that, S802, S803 have no timing limitation, commutative sequence is executed, can also be performed simultaneously.
S804: using the Pinyin information of all texts in recognition result as the first Pinyin information to be matched.
" zhang ming ming " is further used as the first Pinyin information to be matched by example in undertaking.
S805: successively by the word of letter and each Pinyin information in Pinyin information set in the first Pinyin information to be matchedMother matches.
Example in undertaking, further, if Pinyin information in Pinyin information set B be respectively " zhou xiao ling "," zhang min ", " zhang mi ", " li lei ", " zhou xiao ling ", by the first Pinyin information " zhang to be matchedLetter in ming ming " is respectively and in " zhou xiao ling ", " zhang ming ", " zhang mi ", " li lei "Letter is matched, following only with one specifically by the first phonetic to be matched in order not to repeat to repeat because matching process is identicalLetter in information " zhang ming ming " said for matched process with " zhou xiao ling " letterIt is bright.
S806: the erroneous matching rate of the first Pinyin information to be matched and each Pinyin information in matching process is calculated in real time.
Example in undertaking, further, by the first Pinyin information " zhang ming ming " to be matched letter withWhen letter in " zhou xiao ling " is matched, the first Pinyin information " zhang ming to be matched is calculated in real timeLetter in ming " and the erroneous matching rate in the matching process of " zhou xiao ling " each letter.
S807: judge whether the erroneous matching rate of the first Pinyin information to be matched and the second Pinyin information is greater than default mistakeRate threshold value, the second Pinyin information are any Pinyin information in Pinyin information set；
If so, S808 is executed, if it is not, executing S805.
Example in undertaking, further, if being matched to the 6th in the first Pinyin information " zhang ming ming " to be matchedIt has been greater than default error rate threshold when a letter, has executed S808 at this time.
S808: the matching process of the first Pinyin information to be matched and the second Pinyin information is interrupted.
Example in undertaking is further interrupted at this time by the word in the first Pinyin information " zhang ming ming " to be matchedFemale letter with " zhou xiao ling " carries out matched process.
S809: judge to reach with the presence or absence of at least one with the first Pinyin information matching degree to be matched in Pinyin information setThe Pinyin information of first preset matching degree threshold value；
If so, S8010 is executed, if it is not, executing S8011.
Example in undertaking, if being not present and the first Pinyin information " zhang ming ming " to be matched in Pinyin information set BMatching degree reach the Pinyin information of the first preset matching degree threshold value, execute S8011 at this time.
S8010: the Pinyin information for reaching the first preset matching degree threshold value with the first Pinyin information matching degree to be matched is madeFor speech recognition result.
S8011: extracting keyword from recognition result, believes the Pinyin information of keyword as the second phonetic to be matchedBreath.
Example in undertaking further extracts keyword " Zhang Ming " from recognition result " Zhang Mingming ", obtain second toWith Pinyin information " zhang ming ".
The same S805-S8010 of subsequent step, difference are the first Pinyin information to be matched replacing with the second phonetic to be matchedInformation, the first preset matching degree threshold value replace with the second preset matching degree threshold value, are not repeated herein and repeat.
Terminal provided in this embodiment and computer readable storage medium, by obtaining when monitoring receives voice dataThe Pinyin information set for taking the default entry in terminal carries out identifying processing to the voice data received and obtains recognition result,And the first Pinyin information to be matched is determined according to recognition result, then successively by the letter and phonetic in the first Pinyin information to be matchedThe letter of each Pinyin information in information aggregate is matched, and calculates the first Pinyin information to be matched in matching process in real timeWith the matching result of each Pinyin information, and then according to matching result control the first Pinyin information to be matched and each Pinyin informationWith process, reduce unnecessary matching process during speech recognition match, while avoiding unnecessary matching resourceWaste, substantially increases the speed of speech recognition, so compared to the prior art, terminal provided in this embodiment and computer canThe efficiency that storage medium largely improves speech recognition is read, so that the experience satisfaction of user is more preferable.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-rowHis property includes, so that the process, method, article or the device that include a series of elements not only include those elements, andAnd further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsicElement.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to doThere is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment sideMethod can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many casesThe former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior artThe part contributed out can be embodied in the form of software products, which is stored in a storage mediumIn (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, serviceDevice, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specificEmbodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the artUnder the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very muchForm, all of these belong to the protection of the present invention.