CN106453793A

CN106453793A - Voice response method and mobile device

Info

Publication number: CN106453793A
Application number: CN201611043429.4A
Authority: CN
Inventors: 霍彦军
Original assignee: Huawei Device Co Ltd
Current assignee: Huawei Device Co Ltd
Priority date: 2012-11-20
Filing date: 2012-11-20
Publication date: 2017-02-22
Anticipated expiration: 2032-11-20
Also published as: CN107249068A; WO2014078980A1; CN106453793B; CN103636183A; CN103636183B; CN107249068B; CN110636163A; CN106302931A; CN106302931B

Abstract

The invention discloses a voice response method and system, and a mobile device. The method comprises the steps of detecting an external call voice; when an external call voice value exceeds a preset voice reference value for starting a voice response function, searching whether a call voice sample matching the call voice exists or not; and if the call voice sample matching the call voice exists, carrying out preset response operation corresponding to the call voice sample. According to the method, the system and the device, the voice response can be realized without triggering a key, the usage of the mobile device is humanized, convenient and easy, and the cost is low.

Description

A kind of method of voice response and mobile device

Technical field

The present invention relates to electronic technology field, more particularly to a kind of method of voice response and mobile device.

Background technology

At present, voice response system has application on some mobile devices.The technology of general voice response system is thought Lu Shi：Set the mike of pickup voice on the mobile apparatus so as to response user speech inputs；In addition set one and start voice sound The function key answered.

First press " function key of voice response " during work to wake up mobile terminal, and inform that mobile device starts voice and rings Answer function.When user says one section against the mike of mobile device, mobile device can be recorded to word, then with prestore Speech data compare.If same or similar degree reaches more than requirement, trigger voice response.

As it was previously stated, general voice response system application scenarios are mostly to need to press one key to start voice response work( Can, the speech data that user input from mike end processed or compared, if having same or similar degree reach require with On speech data, then trigger speech recognition.

Inventor finds in long-term R ＆ D, and above-mentioned voice response system is very mechanical when using, not Hommization, even if having speech identifying function it is also desirable to user, first by individual start key, could trigger speech recognition.

Content of the invention

The invention mainly solves the technical problem of providing a kind of method of voice response and mobile device it is not necessary to pass through Button triggering just can automatic voice response function, realize voice response.

A first aspect of the present invention is：There is provided a kind of method of voice response, methods described includes：Detection is from the external world Call voice；When described extraneous voice size of calling exceedes the default phonetic reference value for starting voice response function When, search whether exist and the described call speech samples calling voice to match；If existing and described call speech samples phase The call speech samples of coupling, then the response operation corresponding with described call speech samples that execution prestores.

In conjunction with a first aspect, in the first possible implementation of first aspect：Described detection is exhaled from extraneous After calling out the step of voice, the described size when described extraneous call voice exceed default for starting voice response function Phonetic reference value when, search whether to exist with the described call call speech samples that match of voice before, also include：Judge Whether the described size calling voice exceedes the default phonetic reference value for starting voice response function.

In conjunction with the first possible implementation of first aspect, in the possible implementation of the second of first aspect In：Judge the step bag calling the size of voice whether to exceed the default phonetic reference value for starting voice response function Include：Judge to call whether voice corresponding measurement voltage or measurement electric current exceed the default electricity for starting voice response function Pressure or electric current.

In conjunction with the possible implementation of the second of first aspect, in the third possible implementation of first aspect In：Described judge call voice corresponding measurement voltage or measurement electric current whether exceed default for starting voice response function Voltage or the step of electric current include：Described call voice is converted to corresponding measurement voltage or measurement electric current；Judge to call Whether voice corresponding measurement voltage or measurement electric current exceed the default voltage for starting voice response function or electric current.

In conjunction with first aspect and first aspect the first possible implementation to the third possible implementation In any one, in the 4th kind of possible implementation of first aspect：Described search whether exist with described call voice Before the step of call speech samples matching, also include：Described call voice is converted to what mobile device was capable of identify that Call voice signal；The described step searching whether to exist with the described call speech samples calling voice to match is specially： Search whether exist and the described call speech samples calling voice signal to match.

In conjunction with first aspect and first aspect the first possible implementation to the 4th kind of possible implementation Any one, in the 5th kind of possible implementation of first aspect：Described looked for whether in mobile device with call The step of the call speech samples that the phonetic feature of voice signal matches is specially：Look for whether in described mobile device Reach the call speech samples of default similarity with the described phonetic feature similarity calling voice signal.

The 4th kind of possible implementation in conjunction with first aspect or the 5th kind of possible implementation, in first aspect In 6th kind of possible implementation：The described call speech samples searching whether to exist and described call voice signal matches Step before, also include：Setting is described to call speech samples and operates and preserve with calling the corresponding response of speech samples.

In conjunction with the 6th kind of possible implementation of first aspect, in the 7th kind of possible implementation of first aspect In：Described setting is called speech samples and calls the step that the corresponding response of speech samples operates and preserves to be specially：Receive Record the instruction calling speech samples；After receiving the instruction recording call speech samples, record one section of external sound conduct Call speech samples；After the completion of described call speech samples are recorded, output setting response corresponding with calling speech samples behaviour The prompting made；Receive according to setting described prompting and input with call speech samples corresponding response operation setting；Preserve institute State call speech samples and with call the corresponding described response operation setting of speech samples.

In conjunction with first aspect and first aspect the first possible implementation to the 7th kind of possible implementation Any one, in the 8th kind of possible implementation of first aspect：Methods described also includes：It is provided for starting voice sound Answer the phonetic reference value of function and preserve.

According to the second aspect of the invention, provide a kind of mobile device, including detection module, searching modul and response mould Block, wherein：Described detection module is used for detection from extraneous call voice；Described searching modul is used for when described extraneous exhaling When calling out voice size and exceeding the default phonetic reference value for starting voice response function, search whether exist and described call The call speech samples that voice matches；Described respond module is used for finding and described call speech samples when described searching modul During the call speech samples matching, the response operation corresponding with described call speech samples that execution prestores.

In conjunction with a second aspect of the present invention, in the first possible implementation of second aspect：Described equipment includes Judge module, for judging to call whether voice size exceedes the default phonetic reference value for starting voice response function, And will determine that result exports to described searching modul.

In conjunction with the first possible implementation of a second aspect of the present invention, in the possible reality of the second of second aspect In existing mode：Described judge module specifically for judge call voice corresponding measurement voltage or measurement electric current whether exceed default The voltage for starting voice response function or electric current, and will determine that result exports to described searching modul.

In conjunction with the possible implementation of the second of a second aspect of the present invention, in the third possible reality of second aspect In existing mode：Described equipment includes the first modular converter, for obtaining described extraneous call voice from described detection module, will Described extraneous call voice is converted to corresponding measurement voltage or measurement electric current, and described call voice is measured electricity accordingly Pressure or measurement electric current are sent to described judge module；Described judge module is specifically for judging the described call corresponding measurement of voice Whether voltage or measurement electric current exceed the default voltage for starting voice response function or electric current.

In conjunction with a second aspect of the present invention and second aspect the first possible implementation to the of second aspect Any one in three kinds of possible implementations, in the 4th kind of possible implementation of second aspect：Described equipment includes Second modular converter, for being converted to, by described call voice, the call voice signal that mobile device is capable of identify that；Described lookup Module is specifically for searching whether to exist and the described call speech samples calling voice signal to match.

In conjunction with a second aspect of the present invention and second aspect the first possible implementation to the of second aspect Any one in four kinds of possible implementations, in the 5th kind of possible implementation of second aspect：Described searching modul Specifically for searching whether to reach the vocative of default similarity with the described phonetic feature similarity calling voice signal Sound sample, and lookup result is exported to described respond module.

In conjunction with a second aspect of the present invention and second aspect the first possible implementation to the of second aspect Any one in five kinds of possible implementations, in the 6th kind of possible implementation of second aspect：Described equipment also wraps Include, setup module, for arrange described call speech samples and with call the corresponding response of speech samples operate and preserve.

In conjunction with the 6th kind of possible implementation of a second aspect of the present invention, in the 7th kind of possible reality of second aspect In existing mode：Described setup module include instruction reception unit, voice recording unit, Tip element, response arranging unit and Storage unit, wherein：Described instruction reception unit is used for receiving records the instruction calling speech samples；Described voice recording unit Call the instruction of speech samples for the recording according to instruction reception unit, record one section of extraneous sound as call voice sample This；Described Tip element is used for after described voice recording unit completes described call speech samples recording, and output arranges and exhales Call out the prompting of speech samples corresponding response operation；Described response arranging unit receives according to described in the output of described Tip element Prompting and input with call speech samples corresponding response operation setting；Described storage unit is used for preserving described voice recording Unit record call speech samples and preserve described response arranging unit input with call the corresponding response of speech samples Operation setting.

The 6th kind of possible implementation in conjunction with a second aspect of the present invention or the 7th kind of possible implementation, In 8th kind of possible implementation of two aspects：Described setup module is additionally operable to arrange a voltage threshold and is used for opening as described The voltage of dynamic voice response function simultaneously preserves.

A third aspect of the present invention, provides a kind of mobile device, be connected including processor and with described processor Memorizer, on-off circuit and A/D change-over circuit, also include voice pickup circuit, described voice pickup circuit respectively with described On-off circuit and the electrical connection of described A/D change-over circuit, wherein：Described voice pickup circuit is used for detection from extraneous call Voice, is converted into corresponding measurement voltage, and sends described measurement voltage to described on-off circuit；Described on-off circuit is used In receiving described measurement voltage, judge whether measurement voltage exceedes the voltage for starting voice corresponding function, when described measurement When voltage exceedes the described voltage for starting voice response function, described processor is notified to start the finger of voice response function Order, and described measurement voltage is sent to described A/D change-over circuit；Described A/D change-over circuit is used for surpassing when described measurement voltage When crossing the described voltage for starting voice response function, measure, by described, the call that voltage conversion is capable of identify that for mobile device Voice signal, and send described call voice signal to described processor；Described processor is used for starting voice response function, and Obtain from described A/D change-over circuit and call voice signal, look for whether special with the voice calling voice signal in memory Levy the call speech samples matching, when having with the described call speech samples calling voice signal to match, control is carried out The response operation corresponding with calling speech samples prestoring.

In conjunction with a third aspect of the present invention, in the first possible implementation of the third aspect：Described on-off circuit Including bleeder circuit and voltage comparator, wherein：Described bleeder circuit is electrically connected with described voltage comparator, for by partial pressure The voltage output that circuit produces gives described voltage comparator；Described bleeder circuit includes first resistor and second resistance, and described One resistance is connected with described second resistance, and one end of wherein said first resistor is electrically connected with voltage source, the other end and described the One end electrical connection of two resistance, the other end ground connection of described second resistance, for being allocated to the voltage from voltage source；The It is connected voltage comparator between one resistance and second resistance, produce for starting language between first resistor and second resistance simultaneously The voltage of sound response function；

Described voltage comparator includes：

First port, is electrically connected with described bleeder circuit, for receiving from described bleeder circuit in first resistor and the Between two resistance produce the described voltage for starting voice corresponding function and input described voltage comparator；Second port, Electrically connect with described voice pickup circuit, for receiving the measurement voltage being converted to by extraneous voice and inputting described voltage ratio Compared with device；3rd port, is electrically connected with described processor, for when described measurement voltage exceed described in be used for starting the corresponding work(of voice During the voltage of energy, send the instruction starting voice response function to described processor；4th port, with described A/D change-over circuit Electrical connection, for when being used for, described in measuring voltage and exceeding, the voltage starting voice corresponding function, by described measurement voltage output To described A/D change-over circuit.

It is different from prior art, the beneficial effect of embodiment of the present invention is：On the one hand detect by making mobile device Mate flow process from the extraneous phonetic feature that voice to start below of calling, and then make mobile device is prestored and vocative Sound sample responds operation accordingly, rather than by way of button triggering in prior art, makes the use more people of mobile device Property, it is more convenient, be more easy to use；On the other hand, by the strong and weak change of the extraneous voice of sensing, only when extraneous voice size reach pre- If phonetic reference value for starting voice response function when just control and wake up voice response function, realize dynamic response, keep away Exempt to open the electric quantity loss that voice response function causes for a long time, make the power consumption of mobile device lower.And, mobile device responds The response mode variation that user calls, to user's more enriching experiences.

Brief description

Fig. 1 is the flow chart of voice response method one embodiment of the present invention；

Fig. 2 is the flow chart of another embodiment of voice response method of the present invention；

Fig. 3 is that in another embodiment of voice response method of the present invention, setting is called speech samples and called speech samples The flow chart that corresponding response operates and preserves；

Fig. 4 is the concrete application flow chart of sound equipment induction method one embodiment of the present invention；

Fig. 5 is the theory diagram of mobile device one embodiment of the present invention；

Fig. 6 is the theory diagram of setup module in mobile device one embodiment of the present invention；

Fig. 7 is the structural representation of another embodiment of mobile device of the present invention；

Fig. 8 is the circuit diagram of the concrete application of mobile device one embodiment.

Specific embodiment

Refering to Fig. 1, Fig. 1 is the flow chart of voice response method one embodiment of the present invention, and method includes：

Step S101：Detection is from extraneous call voice；

Mobile device passes through voice pick device, such as mike, the extraneous call voice of real-time detection.

Step S102：Join when the size of extraneous call voice exceedes the default voice for starting voice response function When examining value, search whether the call speech samples existing with calling voice to match；

Phonetic reference value can be represented by the size of curtage naturally it is also possible to be otherwise.Extraneous Whether the size calling voice exceedes the default phonetic reference value for starting voice response function, can be by relatively more extraneous Call the corresponding measurement electric current that is converted to of voice or measurement voltage, with default for starting voice response function Curtage is carried out.For example default call voice work(for starting when extraneous call voice corresponding measurement voltage exceedes During the voltage of energy, then start voice response function, search whether there are and call the call speech samples that voice matches；When outer When calling voice corresponding measurement electric current to exceed the default electric current for starting call phonetic function of boundary, then start voice and ring Answer function, search whether the call speech samples existing with calling voice to match.Led to phonetic reference value in following embodiments As a example overvoltage represents.

After starting voice response function, can continue obtain extraneous call by starting sound-recording function or otherwise Voice, is converted to, by calling voice, the call voice signal that mobile device is capable of identify that；Specifically can will continue the outer of acquisition The call voice on boundary is converted to measurement voltage, and then the vocative message that measurement voltage conversion is capable of identify that for mobile device Number.

When being mated, typically search whether the call voice existing with calling the phonetic feature of voice signal to match Sample.Mentioned here match refer to and call the phonetic feature similarity of voice signal reach default similarity or with On, default similarity needs to be configured according to user, and such as 85% or 75% etc., the present invention is without limitation.When depositing When with the call speech samples calling voice to match, carry out step S103, otherwise, it is extraneous that return to step S101 continues detection Call voice.

In actual application it is possible to occur propagandaing directed to communicate half when could start voice response function, that is, Start voice response function after may can only get second half call voice remaining, at this moment then only obtain remaining this A part is called voice and is carried out changing, mates.Here conversion includes for the call voice of acquisition being converted to measurement voltage, enters And two steps of call voice signal that measurement voltage conversion is capable of identify that for mobile device.Extraneous call voice is corresponded to The call voice signal that is capable of identify that for mobile device of measurement voltage conversion after, looked for whether in mobile device and exhaled Call out the call speech samples that the phonetic feature of voice signal matches.

On the other hand it is also possible to occur in the last situation that could start voice response function calling voice, due to The follow-up call voice obtaining is possible to cannot be carried out mating very little, at this moment can not be responded it is also possible to be passed through other side Formula, analogy setting starts chimes of doom etc., points out user to send call voice again.

Step S103：The response operation corresponding with calling speech samples that execution prestores；

When existing with the call speech samples calling voice to match, it is corresponding with calling speech samples that execution prestores Response operation.Done response operation can be play prestore with call the corresponding voice responsive of speech samples or execution and exhale Call out the corresponding action of speech samples.

The call speech samples such as prestoring are " dear ", and the response operation corresponding with calling speech samples prestoring is Play the voice of " I here ".Then when extraneous voice is " dear ", mobile device plays the voice of " I here ".Move The owner of dynamic equipment can find the mobile device of oneself quickly.The call speech samples again such as prestoring are " to dial ××× Phone ", corresponding response operation is the phone of automatic dialing ×××.When extraneous voice is " dialing the phone of ××× ", Then the action of the phone of ××× is dialed in execution.

It is appreciated that embodiment of the present invention one is to be started by making mobile device detect from extraneous call voice Phonetic feature coupling flow process below, so make that mobile device prestored with call that speech samples are corresponding to respond operation, Rather than by way of button triggering in prior art, make mobile device using more humane, be more convenient, be more easy to use；Two By the strong and weak change of the extraneous voice of sensing, only when extraneous voice size reach default for starting voice response function Just control during phonetic reference value and wake up voice response function, realize dynamic response, it is to avoid long-time voice response function of opening is made The electric quantity loss becoming, makes the power consumption of mobile device lower.

Additionally, mobile device responds the response mode variation that user calls, bring more enjoyment to user's life.

Refer to Fig. 2, another embodiment of voice response method of the present invention includes：

Step S201：Setting is called speech samples and is operated and preserve with calling the corresponding response of speech samples；

Operate and be stored in mobile device end setting call speech samples and with calling the corresponding response of speech samples In mobile device；

Step S202：It is provided for starting the phonetic reference value of voice response function and preserving；

Pre-set a phonetic reference value for starting voice response function, here using voltage as phonetic reference value As a example.Assume people when propaganda directed to communicate voltage be 350mV, then the voltage that can be provided for starting voice response function is 350mV, it is of course also possible to be provided for starting the voltage of voice response function according to the demand of user oneself, such as arranges low It is the voltage for starting voice response function in 350mV or the slightly above voltage of 350mV.In actual application, such as When fruit mobile device system itself has had the voltage for starting voice response function of acquiescence, then do not need to be used again In the setting steps of the voltage starting voice response function, directly with mobile device system acquiescence for starting voice response work( The voltage of energy is as the voltage for starting voice response function；

What deserves to be explained is, the sequencing of above-mentioned steps S201 and step S202 can be exchanged that is to say, that being gone back After being first provided for starting the phonetic reference value of voice response function and preserving, then arrange call speech samples and with exhale Call out the corresponding response of speech samples to operate and preserve；

Step S203：Detection is from extraneous call voice；

Step S204：When extraneous voice size of calling exceedes the default phonetic reference for starting voice response function During value, search whether the call speech samples existing with calling voice to match；

Step S205：The response operation corresponding with calling speech samples that execution prestores；

Aforesaid way, by advance inside mobile device setting call speech samples and with call speech samples corresponding Response operation, user can be configured to these parameters according to personal like, so that the realization of voice response more individual character Change, response mode becomes more flexible and changeable also according to the personal settings of user simultaneously, to the more rich experience of user.

Wherein, in another embodiment, speech samples and response behaviour corresponding with calling speech samples are called in setting The concrete steps made and preserve refer to Fig. 3, as illustrated, including following sub-step：

Sub-step S301：Receive and record the instruction calling speech samples；

Mobile device receives the instruction calling speech samples from the recording that user operation produces；

Sub-step S302：Record one section of external sound as call speech samples；

Mobile device receives after recording the instruction calling speech samples, records one section of external sound as call according to instruction Speech samples.Call speech samples can be the address or other voice that user is oneself mobile device takes.Such as right The mike mobile device gives a call " dear " or " love machine " etc. as call speech samples or against movement The mike of equipment gives a call action command, such as " dials the phone of ××× " etc., and the here present invention is not to calling voice The concrete form of sample and content are limited；

Sub-step S303：The prompting of output setting response corresponding with calling speech samples operation；

After the completion of calling speech samples to record, mobile device output setting response corresponding with calling speech samples operation Prompting；

Sub-step S304：Receive according to prompting and input with call speech samples corresponding response operation setting；

Inputted according to the prompting of the setting of sub-step S303 output response corresponding with calling speech samples operation Operation, mobile device receives input with call speech samples corresponding response operation setting, response operation with corresponding call Speech samples correspond to, such as call speech samples be " dear " or " love machine ", response operation could be arranged to " " or The sound of the response of " I here ", it is of course also possible to arrange some flighty sound or one section of music as the sound of response Sound；If call speech samples are " dialing the phone of ××× " such action command, response operation could be arranged to execution and dials Make a call ××× etc. corresponding response action；

Sub-step S305：Preserve call speech samples and with call speech samples corresponding response operation setting；

The call recording speech samples and response operation setting corresponding with calling speech samples are preserved to movement Equipment, completes to arrange.

It is noted that above-mentioned setting up procedure is a kind of embodiment of setting up procedure of the present invention, in practical application In, record and call voice sample operations and carry out strictly distinguishing successively with call speech samples corresponding response operation setting Order is that is to say, that record the instruction (i.e. above-mentioned sub-step S301) calling speech samples afterwards it is also possible to first carry out receiving Response operation setting carries out calling speech samples to record again.And, also it is not necessarily intended to call speech samples recording to complete and ring Preserved again after the completion of answering operation setting, can be retained separately, that is, call speech samples recording to carry out again after completing and preserving Response operation setting simultaneously preserves, or first carries out carrying out calling recording and protecting of speech samples after response operation setting preserves again Deposit.

Refer to Fig. 4, be the concrete application flow chart of voice response method one embodiment of the present invention, the voice of the present invention Application on mobile phone for the response method includes：

Step S401：Receive extraneous sound；

Mobile phone constantly receives the sound in the external world by mike.

Certainly, before this, first system setting can be carried out to mobile phone.First in the setting menu of mobile phone, setting is opened The voltage of dynamic voice response function and setting call speech samples and with call speech samples corresponding response operation setting And be saved on mobile phone, the similarity of voice match can also be configured simultaneously and preserve.Certainly, in actual application In, if limited the voltage of startup voice response function inside cell phone system, do not need to reset voltage, directly Using the voltage of system default as the voltage of voice response function on.

Step S402：Sound is processed；

After external sound is through mobile microphone, external sound corresponding measurement voltage or measurement electric current can be converted to.

Corresponding for external sound measurement voltage is sent to voltage comparator be compared.

Step S403：Carry out voltage ratio relatively；

Mobile phone will be changed by external sound by internal voltage comparator after measurement voltage and being used for of pre-setting Start the voltage of voice response function or the voltage of the startup voice response function of system default is compared.If measurement voltage Exceed the default voltage for starting voice response function on voice response function, then execution step S404, if measurement Voltage is not above the default voltage for starting voice response function on voice response function, then execution step S406；

Step S404：Start voice response function, carry out voice match；

When measurement voltage exceedes the default voltage for starting voice response function, start voice response function, continue Continued access is received external sound and is converted to the acoustical signal that mobile phone is capable of identify that, finds the language matching with acoustical signal in mobile phone Sound sample.After starting voice response function, can stop carrying out voltage ratio relatively to save electricity；

Step S405：If finding the speech samples that similarity reaches more than 85%, execute sound corresponding with speech samples Should operate, otherwise, not execute response operation；

Step S406：Do not execute operation；

When measurement voltage is not above the default voltage for starting voice response function, do not execute operation, such as If mobile phone is in holding state originally, keep holding state, and continue to external sound.

So that mobile device does not need button triggering to realize voice response, make the use of mobile device by with upper type More humane, be more convenient, be more easy to use.For example, user can pre-set " dear " conduct and call speech samples, corresponding sound Should reply as " dear, I here ".When someone calls out " dear ", mobile device will reply that " dear, I am at this In ", very hommization；Especially in daily life, Home Alone, often forgets which the phone of oneself puts, does not have again Other mobile phone can dial the phone of oneself, and at this moment, as long as barking out default call voice, phone will automatic language Sound equipment is answered, and does a corresponding response or plays one section of default response music, user can be made to quickly find the phone of oneself； Again for example, cellphone subscriber can arrange " phoning Zhang San " as calling speech samples, and corresponding response is set to directly dial Make a call Zhang San, as long as user cries out " phoning Zhang San " against the mobile phone of oneself, the phone of mobile phone just automatic dialing Zhang San, Very convenient, especially do not see keyboard to those or will not be provided convenience with the user that cell phone address book is called.

Refer to Fig. 5, the theory diagram of mobile device one embodiment of the present invention, mobile device include detection module 51, Searching modul 52 and respond module 53, wherein：

Detection module 51 is used for detection from extraneous call voice；

Constantly detect the call voice in the external world by detection module 51.

Searching modul 52 is used for exceeding the default language for starting voice response function when extraneous voice size of calling During sound reference value, search whether the call speech samples existing with calling voice to match；

, pass through when calling voice size to exceed the default phonetic reference value for starting voice response function when extraneous Searching modul 52 searches whether the call speech samples existing with calling voice to match, and Query Result is exported to response mould Block 53.

The phonetic reference value for starting voice response function here presetting at is to pre-set for starting voice sound Answer the reference value of function, reference value can be with being voltage or electric current represents.When extraneous call voice size exceedes default use When starting the phonetic reference value of voice response function, then start voice response function, search whether to deposit by searching modul 52 In the call speech samples matching with call voice.

Respond module 53 is used for, when searching modul 52 finds with the call speech samples calling speech samples to match, holding The response operation corresponding with described call speech samples that row prestores.

When exist with call voice match call speech samples when, respond module 53 execution prestore with call voice Sample corresponding response operation.Done response operation can be play prestore with call the corresponding voice responsive of speech samples Or execution and the call corresponding action of speech samples.

Please continue to refer to Fig. 5, in another embodiment of mobile device of the present invention, also include the first modular converter 54 and sentence Disconnected module 55, wherein：

Judge module 55 be used for judge the external world call voice size whether exceed default for starting voice response work( The phonetic reference value of energy；

Whether judge module 55 exceedes specifically for the call voice corresponding measurement voltage judging the external world or measurement electric current The default voltage for starting voice response function or electric current.

First modular converter 54 is used for obtaining the call voice in the external world from detection module 51, and extraneous call voice is turned It is changed to corresponding measurement voltage or measurement electric current, and voice measures voltage accordingly or measurement electric current is sent to judgement mould by calling Block 55；So that extraneous call voice is converted to corresponding measurement voltage as a example explanation in the present embodiment.

First modular converter 54 obtains the call voice in the external world, voice will be called to be converted to corresponding measurement voltage, will exhale Call out voice and measure voltage accordingly and be sent to judge module 55 and judged.

Judge module 55 specifically for judge call voice corresponding measurement voltage whether exceed default for starting language The voltage of sound response function, and will determine that result exports to searching modul 52；

Judge module 55 receives the call voice corresponding measurement voltage being converted to through the first modular converter 54, and judges Call whether voice corresponding measurement voltage exceedes the default electricity for starting voice response function on voice response function Pressure.Exceed the default electricity for starting voice response function on voice response function when calling voice corresponding measurement voltage During pressure, searching modul 52 is notified to make a look up and the call speech samples calling voice to match.

Please continue to refer to Fig. 5, in another embodiment of mobile device of the present invention, also include the second conversion module 56, be used for Voice will be called to be converted to the call voice signal that mobile device is capable of identify that, specifically can just call voice to survey accordingly The call voice signal that amount voltage conversion is capable of identify that for mobile device.

When judge module 55 judged result be call voice corresponding measurement voltage exceed default for starting voice During the voltage of response function, it is sent to the second modular converter 56 by calling voice corresponding measurement voltage.Second modular converter 56 Voice will be called to measure the call voice signal that voltage conversion is capable of identify that for mobile device accordingly, and by exhaling of being converted to Call out voice signal to export to searching modul 52.

Searching modul 52 is specifically for searching whether the call speech samples existing with calling voice signal to match.Look into Look for and whether have the call speech samples reaching default similarity with the phonetic feature similarity calling voice signal, and will search Result exports to described respond module 53.

Mentioned here match refer to and call the phonetic feature similarity of voice signal reach default similarity or More than, default similarity needs to be configured according to user, and such as 85% or 75% etc., the present invention is without limitation.

Please continue to refer to Fig. 5, in another embodiment of mobile device of the present invention, also include setup module 57, for arranging Call speech samples and operate and preserve with calling the corresponding response of speech samples.

Setup module 57 can be used for setting and calls speech samples and response operation corresponding with calling speech samples simultaneously Preserve.On the other hand, setup module 57 can be also used for being provided for the phonetic reference value of startup voice response function and preserving.

Carry out the related setting of voice response by setup module 57 in advance on the mobile apparatus, including to call voice sample This and with call speech samples corresponding response operation setting, and be provided for start voice response function phonetic reference Value.Such as when mobile device system does not limit the rated voltage starting voice response function, a voltage threshold conduct is set Start the phonetic reference value of voice response function.In addition, setup module 57 can be also used for being set or adjusted in actual applications Similarity when extraneous voice is mated with default call speech samples etc..

Refer to Fig. 6, be the theory diagram of setup module in another embodiment of voice response system of the present invention, mould is set Block 600 includes instruction reception unit 61, voice recording unit 62, Tip element 63, response arranging unit 64 and storage unit 65, wherein：

Instruction reception unit 61 is used for receiving records the instruction calling speech samples；

Receive the instruction calling speech samples from the recording that user operation produces by instruction reception unit 61.

The instruction of speech samples is called in the recording that voice recording unit 62 is used for according to instruction reception unit 61, records one section Extraneous sound is as call speech samples；

Voice recording unit 62 calls the instruction of speech samples according to recording, and records one section of external sound as call voice Sample.Call speech samples can be the address or other voice that user is oneself mobile device takes.Such as against shifting The mike of dynamic equipment gives a call " dear " or " love machine " etc. as call speech samples or against mobile device Mike give a call action command, such as " dial the phone of ××× " etc., the here present invention is not to calling speech samples Concrete form and content be limited.

Tip element 63 is used for after voice recording unit 62 completes to call speech samples to record, and output is arranged and vocative The prompting of sound sample corresponding response operation；

After the completion of calling speech samples to record, Tip element 63 output setting response corresponding with calling speech samples behaviour The prompting made.

It is corresponding with calling speech samples that response arranging unit 64 reception inputs according to the prompting of Tip element 63 output Response operation setting；

Setting response corresponding with the calling speech samples operation that response arranging unit 64 exports according to Tip element 63 Prompting, receives input with call speech samples corresponding response operation setting, response operation with corresponding call speech samples Corresponding, such as call speech samples to be " dear " or " love machine ", response operation could be arranged to " " or " I am at this The sound of the response of youngster ", it is of course also possible to arrange some flighty sound or one section of music as the sound of response；If exhaling Calling out speech samples is " dialing the phone of ××× " such action command, and response operation could be arranged to execution and dials ××× The corresponding response action such as phone.

Storage unit 65 is used for preserving the call speech samples of voice recording unit 62 recording and preservation response setting is single Unit 64 input with call speech samples corresponding response operation setting.

Storage unit 65 by the call recording speech samples and with call speech samples corresponding response operation setting Preserve, complete to arrange.

It is noted that above-mentioned setting up procedure is a kind of embodiment of setting up procedure of the present invention, in practical application In, record and call voice sample operations and carry out strictly distinguishing successively with call speech samples corresponding response operation setting Order is that is to say, that carry out it is also possible to first carry out response operation setting after receiving the instruction recording call speech samples again Speech samples are called to record.And, storage unit 65 is also not necessarily intended to call speech samples recording to complete and respond operation to set Preserved again after the completion of putting, can be retained separately, that is, call speech samples recording to carry out response operation again after completing and preserving Arrange and preserve, or first carry out responding the Record and Save carrying out call speech samples after operation setting preserves again.

Refer to Fig. 7, be the structural representation of mobile device one embodiment of the present invention, mobile device 700 includes processing Device 701 and the memorizer 702 being connected with processor 701, on-off circuit 705 and A/D change-over circuit 704, also include sound Sound pick-up circuit 703, voice pickup circuit 703 is electrically connected with on-off circuit 705 respectively：

Be stored with memorizer 702 call speech samples and call speech samples corresponding response operation setting.

Voice pickup circuit 703 is used for detection from extraneous call voice, is converted into corresponding measurement voltage, and Send measurement voltage to on-off circuit 705；

On-off circuit 705 be used for receive measurement voltage, judge measure voltage whether exceed default for start voice sound Answer the voltage of function, when measurement voltage exceedes the default voltage for starting voice response function, notifier processes device 701 opens Dynamic voice response function, and measurement voltage is sent to A/D change-over circuit 704；

A/D change-over circuit 704 is used for when measurement voltage exceedes the default voltage for starting voice response function, will The call voice signal that measurement voltage conversion is capable of identify that for mobile device, and send call voice signal to processor 701；

Processor 701 is used for receiving the notice of on-off circuit 705, starts voice response function, and from A/D change-over circuit 704 obtain and call voice signals, look for whether the exhaling of matching of phonetic feature with call voice signal in memorizer 702 Call out speech samples, when have with call voice signal match call speech samples when, control prestored with call voice Sample corresponding response operation.

Please continue to refer to Fig. 7, the on-off circuit 705 of the mobile device embodiment of the present invention include bleeder circuit 72 and Voltage comparator 71, wherein：Bleeder circuit 72 is electrically connected with voltage comparator 71, will be used for starting the voltage of voice response function Export to voltage comparator 71；Bleeder circuit 72 can further include first resistor and second resistance (as Fig. 8 resistance R1 and R2), first resistor is connected with second resistance, and one end of wherein first resistor is electrically connected with voltage source, the other end and second resistance One end electrical connection, second resistance the other end ground connection, for being allocated to the voltage from voltage source.First resistor and the Connect voltage comparator 71 between two resistance, produce between first resistor and second resistance for starting voice response work(simultaneously The voltage of energy.

Described voltage comparator 71 includes：

First port, is electrically connected with bleeder circuit 72, for receiving what described bleeder circuit 72 exported at first port For starting voltage the input voltage comparator 71 of voice response function；

Second port, is electrically connected with voice pickup circuit 703, for receiving the measurement voltage being converted to by extraneous voice And input voltage comparator 71；

3rd port, is electrically connected with described processor 701, for exporting the described voltage for starting voice response function With comparing result after voltage comparator 71 contrast for the described measurement voltage.

Refer to Fig. 8, be a kind of circuit diagram of the concrete application of mobile device of the present invention one embodiment, specific as follows：

In present embodiment, mobile device is mobile phone, and mobile phone includes voice pickup circuit 83, bleeder circuit 80, voltage ratio relatively Device 81, A/D change-over circuit 82 and master chip 84, memorizer 85：

Wherein, master chip 84 is the concrete application of the processor of above-mentioned mobile device embodiment, bleeder circuit 80 and electricity Pressure comparator 81 collectively constitutes the concrete application of the on-off circuit of above-mentioned mobile device embodiment.

Wherein, voice pickup circuit 83 includes mike 801 and electrostatic equipment 802, and mike 801 detection is from the external world Sound, extraneous sound is converted to measurement voltage by electrostatic equipment 802.

Bleeder circuit 80 further includes first resistor 807 and second resistance 808, first resistor 807 and second resistance 808 Series connection, one end of wherein first resistor 807 is electrically connected with voltage source, and the other end is electrically connected with one end of second resistance 808, and second The other end ground connection of resistance 808, for being allocated to the voltage from voltage source；First resistor 807 and second resistance 808 it Between connect voltage comparator 81, produce between first resistor 807 and second resistance 808 for starting voice response function simultaneously Voltage.

Voltage comparator 81 further includes first port 804, with bleeder circuit 80 in first resistor 807 and second resistance Electrically connect between 808, produce for starting language between first resistor 807 and second resistance 808 for receiving bleeder circuit 80 The voltage of sound response function input voltage comparator 81；Second port 803, is electrically connected with one end of electrostatic equipment 802, is used for Receive the measurement voltage being converted to by extraneous voice input voltage comparator 81；3rd port 806, is electrically connected with master chip 84 Connect, for when measurement voltage exceedes the default voltage for starting voice response function, notifying master chip 84, specifically may be used So that master chip 84 is notified by high level or low level；4th port 805, is electrically connected with A/D change-over circuit 82, for when survey When amount voltage exceedes the default voltage for starting voice response function, voltage output will be measured to A/D change-over circuit 82；

Mike 801 is electrically connected with one end of electrostatic equipment 802, by the extraneous voice transfer detecting to electrostatic equipment 802；The other end of electrostatic equipment 802 is electrically connected by second port 803 with voltage comparator 81, will be changed by extraneous voice and The measurement voltage output obtaining is to voltage comparator 81.

A/D change-over circuit 82 one end is electrically connected with voltage comparator 81, and the other end is electrically connected with master chip 84, for when survey When amount voltage exceedes the default voltage for starting voice response function, measurement voltage conversion is capable of identify that for mobile device Call voice signal, and to master chip 84 send call voice signal.

Be stored with memorizer 85 call speech samples and call speech samples corresponding response operation setting.

Each ingredient works in the following manner：

The mike 801 of mobile phone receives the sound in the external world, after electrostatic equipment 802 converts sound into measurement voltage, by outer The voltage V1 that boundary's sound is converted to passes through electrostatic equipment 802 via second port 803 input voltage comparator 81；Bleeder circuit 80 include first resistor 807 and 808 two resistance of second resistance, after two electric resistance partial pressures, produce electricity between the resistances Pressure V2, V2 is as the voltage starting voice response function.V2 is via first port 804 input voltage comparator 81；Voltage ratio is relatively Voltage V1 and V2 is contrasted by device 81, when V1 is more than V2, notifies master chip 84 to be processed by the 3rd port 806.

Master chip 84 is used for receiving the notice of the 3rd port 806, starts voice response function, and from A/D change-over circuit 82 Obtain and call voice signal, look for whether in memorizer 85 and the vocative calling the phonetic feature of voice signal to match Sound sample, when have with call voice signal match call speech samples when, control prestored with call speech samples Corresponding response operation.

By with upper type, in the original circuit design of mobile phone, set up a bleeder circuit and connect with bleeder circuit The voltage comparator connecing, that is, enable mobile phone dynamic voice response function.In general, the voltage V1 producing when people propagandas directed to communicate is about 350mV (being probably 200mV when people speaks), therefore, design circuit when, can control bleeder circuit partial pressure produce voltage V2 be 350mV is as the voltage starting voice response function.Certainly, in practical application, to be carried out according to the actual parameter of mike Calculate, the voltage of control voltage V2.When the voltage that the voice in the external world produces exceedes the voltage V2 of this partial pressure generation, just call out The voice response function of awake interior of mobile phone.

On the other hand, when surrounding does not have extraneous voice, the power consumption of bleeder circuit almost can be reduced by circuit design To 0；When there being extraneous voice, but when extraneous voice is not enough to wake up voice response function, bleeder circuit power consumption is only about 0.1-0.2mA, and can further be reduced by this power consumption of optimization circuits, to standby impact very little.Logical Cross this mode and sense the strong and weak change of extraneous voice, only voltage after extraneous voice is changed reach default for starting language Master chip is just notified to start voice response function during the voltage of sound response function, it is to avoid long-time voice response function of opening causes Electric quantity loss, make mobile phone more humane, be more convenient, be more easy to use.Meanwhile, the bleeder circuit set up and potentiometer are adopted It is all common components, low cost of manufacture.

By the description of above-mentioned embodiment, the present invention, with respect to prior art, has advantages below：On the one hand pass through to make Mobile device detection mates flow process from the extraneous phonetic feature that voice to start below of calling, and then so that mobile device is carried out Prestore with call that speech samples are corresponding responds operation, rather than by way of button triggering in prior art, make movement Equipment using more humane, be more convenient, be more easy to use；On the other hand, by the strong and weak change of the extraneous voice of sensing, only work as the external world Voltage after voice conversion reaches just to control during the default voltage for starting voice response function and wakes up voice response function, Realize dynamic response, it is to avoid the electric quantity loss that long-time unlatching voice response function causes, make the power consumption of mobile device lower.And And, mobile device responds the response mode variation that user calls, to user's more enriching experiences.

In addition, the embodiment of the method for the voice response of the present invention is it is only necessary to increase on the basis of original mobile device If a bleeder circuit and voltage comparator can be achieved with, what the bleeder circuit set up and voltage comparator were adopted is all Common components, low cost of manufacture, possible implementation is simple.When extraneous voice is not enough to wake up voice response function, should Partial circuit hardly works, and consumption electricity is few, and the stand-by time of mobile device is not affected.

It should be understood that disclosed system in several embodiments provided by the present invention, apparatus and method, can To realize by another way.For example, device embodiments described above are only schematically, for example, described mould Block or the division of unit, only a kind of division of logic function, actual can have other dividing mode when realizing, for example multiple Unit or assembly can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not execute.Another Point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, device or The INDIRECT COUPLING of unit or communication connection, can be electrical, mechanical or other forms.

The described unit illustrating as separating component can be or may not be physically separate, show as unit The part showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple On NE.Some or all of unit therein can be selected according to the actual needs to realize present embodiment scheme Purpose.

In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention, also may be used To be that unit is individually physically present it is also possible to two or more units are integrated in a unit.Above-mentioned integrated Unit both can be to be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.

If described integrated unit is realized and as independent production marketing or use using in the form of SFU software functional unit When, can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially The part in other words prior art being contributed or all or part of this technical scheme can be in the form of software products Embody, this computer software product is stored in a storage medium, including some instructions with so that a computer Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) execution the present invention each The all or part of step of embodiment methods described.And aforesaid storage medium includes：USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD Etc. various can be with the medium of store program codes.

The above only in order to technical scheme to be described, is not intended to limit；Although with reference to aforementioned embodiments The present invention has been described in detail, it will be understood by those within the art that：It still can be to aforementioned each enforcement Technical scheme described in mode is modified, or carries out equivalent to wherein some technical characteristics；And these modification or Person replaces, and does not make the essence of appropriate technical solution depart from the spirit and scope of the present invention each embodiment technical scheme.

Claims

1. a kind of method that mobile terminal is responded to voice is it is characterised in that include：

Described mobile terminal detects in the standby state from extraneous call voice；

If existing in described mobile terminal and the described speech samples calling voice to match, described mobile terminal playing prestores Voice responsive corresponding with described speech samples.

2. method according to claim 1 is it is characterised in that detection is from extraneous call voice in the standby state.

3. the method according to any one of claim 1-2 is not it is characterised in that methods described is triggered by button.

4. the method according to any one of claim 1-3 is it is characterised in that described voice responsive makes the use of mobile device Described mobile device is found at family.

5. the method according to any one of claim 1-4 is it is characterised in that described voice responsive is " I here ".

6. the method according to any one of claim 1-5 it is characterised in that described match for described speech samples with exhale The phonetic feature similarity calling out voice reaches 75% or more.

7. the method according to any one of claim 1-6 is it is characterised in that described phonetic reference value is by user setup.

8. the method according to any one of claim 1-7 it is characterised in that described speech samples corresponding response operation by User setup.

9. method according to claim 8, it is characterised in that first carrying out responding operation setting, then carries out speech samples Receive.

10. method according to claim 8 is it is characterised in that arrange speech samples and the corresponding response of speech samples Operation is specially：

Receive the instruction of recorded speech sample；

After the instruction receiving recorded speech sample, record one section of external sound as speech samples；

After the completion of described speech samples are recorded, the prompting of output setting response corresponding with speech samples operation；

Receive the response operation setting corresponding with speech samples inputting according to the described prompting of setting；

Preserve described speech samples and described response operation setting corresponding with speech samples.

11. methods according to any one of claim 1-10 are it is characterised in that method further includes：Cannot be carried out Timing, points out user to send call voice again.

12. methods according to any one of claim 1-11 are it is characterised in that further include：In detection from the external world Call voice step after, judge described call voice size whether exceed default for starting voice response function Phonetic reference value.

13. methods according to any one of claim 1-12 are it is characterised in that further include：

Described call voice is converted to the call voice signal that mobile device is capable of identify that.

The method that a kind of 14. mobile terminals are responded to voice is it is characterised in that include：

Described mobile terminal starts voice response function；

Described mobile terminal continues to obtain extraneous call voice；

Described mobile terminal will call voice to be converted to the call voice signal that mobile device is capable of identify that.

15. methods according to claim 14 are it is characterised in that further include：

16. methods according to any one of claim 14-15 are it is characterised in that detection is from the external world in the standby state Call voice.

17. methods according to any one of claim 14-16 are not it is characterised in that methods described is triggered by button.

18. methods according to any one of claim 14-17 are it is characterised in that described voice responsive makes mobile device User find described mobile device.

19. methods according to any one of claim 14-18 are it is characterised in that described voice responsive is " I here ".

20. methods according to any one of claim 14-19 are it is characterised in that described match for described speech samples Reach 75% or more with the phonetic feature similarity calling voice.

21. methods according to any one of claim 14-20 are it is characterised in that described phonetic reference value is by user setup.

22. methods according to any one of claim 14-21 are it is characterised in that the corresponding response of described speech samples is grasped Make by user setup.

23. methods according to claim 22 are it is characterised in that first carry out responding operation setting, then carry out speech samples Reception.

24. methods according to claim 22 are it is characterised in that arrange speech samples and the corresponding response of speech samples Operation is specially：

Receive the instruction of recorded speech sample；

25. methods according to any one of claim 14-24 are it is characterised in that method further includes：Cannot be carried out Timing, points out user to send call voice again.

26. methods according to any one of claim 14-25 are it is characterised in that further include：In detection from the external world Call voice step after, judge described call voice size whether exceed default for starting voice response function Phonetic reference value.

27. methods according to any one of claim 14-26 are it is characterised in that further include：

A kind of 28. mobile devices, including processor and computer read/write memory medium it is characterised in that described computer can Reading storage medium is stored with and executes the instruction of following steps：

29. mobile devices according to claim 28 are it is characterised in that detection is from extraneous call in the standby state Voice.

30. mobile devices according to any one of claim 28-29 are not it is characterised in that described mobile device passes through to press Key triggers.

31. mobile devices according to any one of claim 28-30 are it is characterised in that described voice responsive makes to move The user of equipment finds described mobile device.

32. mobile devices according to any one of claim 28-31 are it is characterised in that described voice responsive is that " I am at this Youngster ".

33. mobile devices according to any one of claim 28-32 are it is characterised in that described match for described voice Sample reaches 75% or more with the phonetic feature similarity calling voice.

34. mobile devices according to any one of claim 28-33 are it is characterised in that described phonetic reference value is by user Setting.

35. mobile devices according to any one of claim 28-34 are it is characterised in that the corresponding sound of described speech samples Should operate by user setup.

36. mobile devices according to claim 35 are it is characterised in that first carry out responding operation setting, then carry out voice The reception of sample.

37. mobile devices according to claim 35 are it is characterised in that setting speech samples and speech samples are corresponding Response operation is specially：

Receive the instruction of recorded speech sample；

38. mobile devices according to any one of claim 28-37 are it is characterised in that described instruction further includes：No When method is mated, user is pointed out to send call voice again.

39. mobile devices according to any one of claim 28-38 are it is characterised in that described instruction further includes：? Detection after the step of extraneous call voice, judge the size of described call voice whether exceed default for starting The phonetic reference value of voice response function.

40. mobile devices according to any one of claim 28-39 are it is characterised in that described instruction further includes：

A kind of 41. mobile devices, including processor and computer read/write memory medium it is characterised in that described computer can Reading storage medium is stored with and executes the instruction of following steps：

Described mobile terminal starts voice response function；

Described mobile terminal continues to obtain extraneous call voice；

42. mobile devices according to claim 41 are it is characterised in that described instruction further includes：

43. mobile devices according to any one of claim 41-42 are derived from it is characterised in that detecting in the standby state Extraneous call voice.

44. mobile devices according to any one of claim 41-43 are not it is characterised in that described mobile device passes through to press Key triggers.

45. mobile devices according to any one of claim 41-44 are it is characterised in that described voice responsive makes to move The user of equipment finds described mobile device.

46. mobile devices according to any one of claim 41-45 are it is characterised in that described voice responsive is that " I am at this Youngster ".

47. mobile devices according to any one of claim 41-46 are it is characterised in that described match for described voice Sample reaches 75% or more with the phonetic feature similarity calling voice.

48. mobile devices according to any one of claim 41-47 are it is characterised in that described phonetic reference value is by user Setting.

49. mobile devices according to any one of claim 41-48 are it is characterised in that the corresponding sound of described speech samples Should operate by user setup.

50. mobile devices according to claim 49 are it is characterised in that first carry out responding operation setting, then carry out voice The reception of sample.

51. mobile devices according to claim 49 are it is characterised in that setting speech samples and speech samples are corresponding Response operation is specially：

Receive the instruction of recorded speech sample；

52. mobile devices according to any one of claim 41-51 are it is characterised in that described instruction further includes：No When method is mated, user is pointed out to send call voice again.

53. mobile devices according to any one of claim 41-52 are it is characterised in that described instruction further includes：? Detection after the step of extraneous call voice, judge the size of described call voice whether exceed default for starting The phonetic reference value of voice response function.

54. mobile devices according to any one of claim 41-53 are it is characterised in that described instruction further includes：