CN107562403A - A kind of volume adjusting method, smart machine and storage medium - Google Patents
A kind of volume adjusting method, smart machine and storage medium Download PDFInfo
- Publication number
- CN107562403A CN107562403A CN201710678036.9A CN201710678036A CN107562403A CN 107562403 A CN107562403 A CN 107562403A CN 201710678036 A CN201710678036 A CN 201710678036A CN 107562403 A CN107562403 A CN 107562403A
- Authority
- CN
- China
- Prior art keywords
- current
- user
- volume
- active user
- volume adjusting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a kind of volume adjusting method, smart machine and storage medium.The voice signal in current environment is gathered in the present invention, active user's quantity in current environment is determined according to the voice signal, the current volume adjustment parameter according to corresponding to searching active user's quantity, volume adjusting is carried out by the current volume adjustment parameter.The present invention is by determining active user's quantity in current environment and the current volume adjustment parameter according to corresponding to searching active user's quantity, to realize volume adjusting is carried out automatically according to current volume adjustment parameter, also just meet because of personnel amount change in current spatial and different volume demands caused by social type change, can preferably solve existing intelligent sound box can not preferably carry out the technical problem of adaptive adjustment of parameter according to environmental change.
Description
Technical field
The present invention relates to electronics and computer realm, more particularly to a kind of volume adjusting method, smart machine and storage to be situated between
Matter.
Background technology
The intelligent sound box currently produced, it can preferably meet otherness demand of the people for sound effect.It is but existing
Some intelligent sound boxes can not adaptively be adjusted with the change of local environment, such as, when intelligent sound box is put inside and outside space
During music, if crowd enters the space and carries out certain language talk, need to carry out intelligent sound box certain adjustment,
For example volume or other operations are reduced, preferably to meet the needs of current crowd.However, existing intelligent sound box needs people
It is adjusted for ground, certain adjustment can not be carried out automatically, also, adjustment also can not necessarily meet the demand of current crowd.
So there is the technical problem for the adaptive adjustment that parameter can not be preferably carried out according to environmental change in existing intelligent sound box.
The above is only used for auxiliary and understands technical scheme, does not represent and recognizes that the above is existing skill
Art.
The content of the invention
It is a primary object of the present invention to provide a kind of volume adjusting method, smart machine and storage medium, it is intended to solve
The technical problem of the adaptive adjustment of parameter can not be preferably carried out according to environmental change in the prior art.
To achieve the above object, the present invention provides a kind of volume adjusting method, the described method comprises the following steps：
Gather the voice signal in current environment；
Active user's quantity in current environment is determined according to the voice signal；
The current volume adjustment parameter according to corresponding to searching active user's quantity；
Volume adjusting is carried out by the current volume adjustment parameter.
Preferably, after the active user's quantity determined according to the voice signal in current environment, methods described
Also include：
Judge whether active user's quantity is the first pre-set user quantity；
When active user's quantity is the first pre-set user quantity, current time is recorded, is judged described current
Whether the moment is in preset time period；
When the current time is in the preset time period, the voice signal in the collection current environment is returned
The step of.
Preferably, it is described judge current time whether in preset time period after, methods described also includes：
When the current time is not in the preset time period, equipment state is set to off closed state.
Preferably, the active user's quantity confirmed according to the voice signal in current environment, is specifically included：
Application on Voiceprint Recognition is carried out to the voice signal, to obtain the current voiceprint in the voice signal；
The current voiceprint is classified；
The vocal print number of types of the current voiceprint is counted as active user's quantity.
Preferably, the current volume adjustment parameter according to corresponding to searching active user's quantity, is specifically included：
Judge whether active user's quantity is the second pre-set user quantity；
When active user's quantity is the second pre-set user quantity, worked as in the first mapping relations according to described
Active user's mark corresponding to preceding voiceprint lookup, it is corresponding according to active user's identifier lookup in the second mapping relations
Current volume adjustment parameter, first mapping relations include the corresponding relation that voiceprint and user identify, described second
Mapping relations include the corresponding relation of user's mark and volume adjusting parameter.
Preferably, it is described that Application on Voiceprint Recognition is carried out to the voice signal, to obtain the current vocal print in the voice signal
After information, methods described also includes：
The current voiceprint is matched with each voiceprint in first mapping relations；
Using the current voiceprint matched not successfully as new voiceprint, and user new corresponding to generation marks
Know；
The new voiceprint and new user are identified into corresponding be saved into first mapping relations.
Preferably, it is described judge whether active user's quantity is the second pre-set user quantity after, methods described is also
Including：
When active user's quantity is not or not second pre-set user quantity, default volume value is obtained；
Correspondingly, it is described that volume adjusting is carried out by the current volume adjustment parameter, specifically include：
By volume adjusting to the default volume value.
Preferably, it is described to obtain default volume value, specifically include：
Obtain default volume value and record current volume value；
Correspondingly, described by after volume adjusting to the default volume value, methods described also includes：
Resurvey the voice signal in current environment；
Voice signal according to resurveying redefines active user's quantity in current environment；
When the active user's quantity redefined is the second pre-set user quantity, volume is recovered to described current
Volume value.
In addition, to achieve the above object, the present invention also provides a kind of smart machine, and the smart machine includes：Microphone,
Memory, processor and it is stored in the volume adjusting program that can be run on the memory and on the processor, the sound
The step of amount regulation program is arranged for carrying out the volume adjusting method.
In addition, to achieve the above object, the present invention also provides a kind of storage medium, and volume is stored with the storage medium
Program is adjusted, the step of described volume adjusting method is realized when the volume adjusting program is executed by processor.
The present invention is by determining active user's quantity in current environment and being searched according to active user's quantity corresponding
Current volume adjustment parameter, with realize automatically according to current volume adjustment parameter carry out volume adjusting, also just meet because ought
Personnel amount change and different volume demands caused by social type change, can preferably solve existing intelligence in front space
Audio amplifier can not preferably carry out the technical problem of the adaptive adjustment of parameter according to environmental change.
Brief description of the drawings
Fig. 1 is the smart machine structural representation for the hardware running environment that scheme of the embodiment of the present invention is related to；
Fig. 2 is the schematic flow sheet of volume adjusting method first embodiment of the present invention；
Fig. 3 is the schematic flow sheet of volume adjusting method second embodiment of the present invention；
Fig. 4 is the schematic flow sheet of volume adjusting method 3rd embodiment of the present invention；
Fig. 5 is the schematic flow sheet of volume adjusting method fourth embodiment of the present invention；
Fig. 6 is the schematic flow sheet of the embodiment of volume adjusting method the 5th of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
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.
Reference picture 1, Fig. 1 are the smart machine structural representation for the hardware running environment that scheme of the embodiment of the present invention is related to.
As shown in figure 1, the smart machine can include：Processor 1001, such as CPU, communication bus 1002, user interface
1003, network interface 1004, microphone 1005 and memory 1006.Wherein, communication bus 1002 be used for realize these components it
Between connection communication.User interface 1003 can include display screen (Display), and optional user interface 1003 can also include mark
Wireline interface, the wave point of standard.Network interface 1004 can optionally include wireline interface, wave point (such as WI- of standard
FI interfaces).Microphone 1005, for gathering the voice signal in current environment.Memory 1006 can be high-speed RAM storage
Device or stable memory (non-volatile memory), such as magnetic disk storage.Memory 1006 is optional
It can also be the storage device independently of aforementioned processor 1001.
The smart machine can be intelligent sound box or other can carry out volume adjusting and the electronics of exportable voice signal is set
It is standby.
It will be understood by those skilled in the art that the structure shown in Fig. 1 does not form the restriction to smart machine, can wrap
Include than illustrating more or less parts, either combine some parts or different parts arrangement.
As shown in figure 1, it can lead to as in a kind of memory 1006 of computer-readable storage medium including operating system, network
Believe module, Subscriber Interface Module SIM and volume adjusting program.
In the smart machine shown in Fig. 1, network interface 1004 is mainly used in connecting background server, is taken with the backstage
Business device enters row data communication；User interface 1003 is mainly used in connecting user terminal, enters row data communication with user terminal, described
User terminal can be mobile phone etc.；The smart machine calls the volume adjusting journey stored in memory 1006 by processor 1001
Sequence, and perform following operate：
Gather the voice signal in current environment；
Active user's quantity in current environment is determined according to the voice signal；
The current volume adjustment parameter according to corresponding to searching active user's quantity；
Volume adjusting is carried out by the current volume adjustment parameter.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
Judge whether active user's quantity is the first pre-set user quantity；
When active user's quantity is the first pre-set user quantity, current time is recorded, judges current time
Whether in preset time period；
When the current time is in the preset time period, the voice signal in the collection current environment is returned
The step of.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
When the current time is not in the preset time period, equipment state is set to off closed state.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
Application on Voiceprint Recognition is carried out to the voice signal, to obtain the current voiceprint in the voice signal；
The current voiceprint is classified；
The vocal print number of types of the current voiceprint is counted as active user's quantity.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
Judge whether active user's quantity is the second pre-set user quantity；
When active user's quantity is the second pre-set user quantity, worked as in the first mapping relations according to described
Active user's mark corresponding to preceding voiceprint lookup, it is corresponding according to active user's identifier lookup in the second mapping relations
Current volume adjustment parameter, first mapping relations include the corresponding relation that voiceprint and user identify, described second
Mapping relations include the corresponding relation of user's mark and volume adjusting parameter.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
The current voiceprint is matched with each voiceprint in first mapping relations；
Using the current voiceprint matched not successfully as new voiceprint, and user new corresponding to generation marks
Know；
The new voiceprint and new user are identified into corresponding be saved into first mapping relations.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
When active user's quantity is not or not second pre-set user quantity, default volume value is obtained；
Correspondingly, following operate also is performed：
By volume adjusting to the default volume value.
Further, processor 1001 can call the volume adjusting program stored in memory 1006, also perform following
Operation：
Obtain default volume value and record current volume value；
Correspondingly, following operate also is performed：
Resurvey the voice signal in current environment；
Voice signal according to resurveying redefines active user's quantity in current environment；
When the active user's quantity redefined is the second pre-set user quantity, volume is recovered to described current
Volume value.
By determining active user's quantity in current environment and being searched according to active user's quantity in the present embodiment
Corresponding current volume adjustment parameter, volume adjusting is carried out automatically according to current volume adjustment parameter to realize, is also just met
Because of personnel amount change in current spatial and different volume demands caused by social type change, can preferably solve existing
Intelligent sound box can not preferably carry out the technical problem of the adaptive adjustment of parameter according to environmental change.
Based on above-mentioned hardware configuration, the embodiment of volume adjusting method of the present invention is proposed.
Reference picture 2, Fig. 2 are the schematic flow sheet of volume adjusting method first embodiment of the present invention.
In the first embodiment, the volume adjusting method comprises the following steps：
Step S10：Gather the voice signal in current environment；
It is understood that in order to realize smart machine can according to the change of current environment adaptively to adjust volume,
The voice signal in current environment can first be gathered.For example intelligent sound box can carry out the collection of voice signal by a microphone.
Step S20：Active user's quantity in current environment is determined according to the voice signal；
In the specific implementation, after the voice signal is collected, active user's number can be carried out by the voice signal
The judgement of amount.For the judgment mode of active user's quantity, the mode of Application on Voiceprint Recognition can be taken to carry out sentencing for number of users
It is disconnected, wherein, the Application on Voiceprint Recognition can be converted into voice signal electric signal, then enter the processing of horizontal electrical signal by hardware or software
And user is identified, by the number of counting user to determine active user's quantity；When the voice signal collected is once to gather
During the voice signal crossed, it is used to identify user because intelligent sound box can carry out voice signal storage, in actual use, for
Once the user of the intelligent sound box was used, then need not can be re-recognized, can be by current voice signal and the voice signal of storage
Matched, by statistical match to the quantity of voice signal be active user's quantity, the present embodiment is for determining number of users
The mode of amount is not restricted.
Step S30：The current volume adjustment parameter according to corresponding to searching active user's quantity；
In the specific implementation, the corresponding relation of active user's quantity and volume adjusting parameter can be established, by according to current
Current volume adjustment parameter corresponding to the acquisition of active user's quantity.Active user's quantity refers to the current persons count detected,
The volume adjusting parameter refers to pre-set to adjust the concrete numerical value of the parameters,acoustic of intelligent sound box.Such as by advance
When number is two people, turning down sound volume is to volume value 25 for setting, then in the actual application environment of intelligent sound box, when according to collection
When the voice signal arrived judges number for two people, then according to corresponding to volume adjusting parameter, by turning down sound volume to volume value 25.
It should be appreciated that when intelligent sound box can judge active user's quantity by voice signal, that is, show this
The number of quantity carries out talk activity, and if before the activity of having conversation, intelligent sound box is just carrying out the outer of music
Put, the now broadcasting of music will cause certain interference for talk activity.So can be by judging active user's quantity simultaneously
The volume adjusting parameter according to corresponding to being found active user's quantity, you can be well adapted for the volume needs of various social lives
And the adaptive adjustment of volume is realized according to various social lives.
Step S40：Volume adjusting is carried out by the current volume adjustment parameter.
It is understood that after current volume adjustment parameter corresponding to being found according to active user's quantity, you can root
The regulation of volume is carried out according to the current volume adjustment parameter.
By determining active user's quantity in current environment and being searched according to active user's quantity in the present embodiment
Corresponding current volume adjustment parameter, volume adjusting is carried out automatically according to current volume adjustment parameter to realize, is also just met
Because of personnel amount change in current spatial and different volume demands caused by social type change, can preferably solve existing
Intelligent sound box can not preferably carry out the technical problem of the adaptive adjustment of parameter according to environmental change.
Reference picture 3, Fig. 3 is the schematic flow sheet of volume adjusting method second embodiment of the present invention, based on shown in above-mentioned Fig. 2
Embodiment, propose the second embodiment of volume adjusting method of the present invention.
In a second embodiment, after the step S20, methods described also includes：
Step S201：Judge whether active user's quantity is the first pre-set user quantity；
It is understood that if smart machine is intelligent sound box, in order to improve the service efficiency of equipment, that is, avoid using the head of a household
Time occurs without using the intelligent sound box but intelligent sound box still in the situation of broadcast state, can pass through the voice signal of user
To judge to whether there is in current environment user to realize that the open and close for Intelligent volume controls.Wherein, will determine that described
Whether active user's quantity is the first pre-set user quantity, and the first pre-set user quantity can be zero, that is, judge current environment
In whether there is user.
When active user's quantity is the first pre-set user quantity, step S202 is performed.
Step S202：Current time is recorded, judges current time whether in preset time period；
In the specific implementation, user may the short time leave intelligent sound box where use environment, in order to avoid intelligent sound
The sensitive reaction of case so that user return after need secondary opening, certain preset time period can be set, to meet user
Otherness use demand.
It should be appreciated that in order to carry out the judgement of preset time period to intelligent sound box, current time is can record, than
Such as, current time 13：40, it is 30 minutes to set preset time period.When judging that user is not present in currently used environment
When, i.e., when active user's quantity is the first pre-set user quantity, into the judgement flow of preset time period.Wherein,
It can judge that number of users records for 0 current time to first time, can be by 13：40 are recorded as initial time.
Certainly, if active user's quantity is not the first pre-set user quantity, without being carried out to preset time period
Judge.
When the current time is in the preset time period, return to step S10.
In the specific implementation, when judging that current time is in preset time period, then cycle detection is carried out, such as, when
The preceding moment is 13：When 50, because preset time period is 30 minutes and initial time is 13：40, then the time range limited as
13：40 to 14:10, then judge current time 13：50 13：40 to 14:In 10 time range, then cycle detection sound is believed
Number, until 14:10.If there is the voice signal of user in midway, by initial time 13：40 are initialized as 0, until true again
Determine the situation that number of users is 0 to occur, be defined as initial time at the time of again will be current.
Further, after step S202, when the current time is not in the preset time period, step is performed
S203。
Step S203：Equipment state is set to off closed state.
If it is understood that until 14:10 still think that the number of users in currently used environment is 0, i.e. preset time
Still without user in 30 minutes cycles, then equipment state can be set to off to closed state can close the intelligent sound box to stop
Subsequent operation.Certainly, before the intelligent sound box is closed, user also can first be prompted to prevent the mistake of intelligent sound box from closing.
Wherein, the equipment state be intelligent sound box running status, it is predeterminable have opening, closed mode and other.
In the present embodiment by detect in preset time period whether with the presence of the first pre-set user quantity user, when one
It can then stop subsequent operation when number of users is still judged after individual preset time period for the first pre-set user quantity, can be preferably
The automatic closing of smart machine is realized, also, can also improve the standby time of smart machine.
Reference picture 4, Fig. 4 is the schematic flow sheet of volume adjusting method 3rd embodiment of the present invention, based on shown in above-mentioned Fig. 2
Embodiment, propose the 3rd embodiment of volume adjusting method of the present invention.
In the third embodiment, the step S20, is specifically included：
Step S201 '：Application on Voiceprint Recognition is carried out to the voice signal, to obtain the letter of the current vocal print in the voice signal
Breath；
It is understood that in order to confirm active user's quantity in current environment, can be realized by sound groove recognition technology in e
Confirmation for user.Wherein, the sound groove recognition technology in e generally comprise sound collecting, noise suppressed and efficient voice detection,
Feature extraction, sound modeling can go out different use in area very well with identifying the sport technique segment matched by means of sound groove recognition technology in e
The voice signal that family is said.So current voiceprint can be extracted from the voice signal of collection, the current voiceprint
Refer to the parameter information for recording user voice feature, the sound of different user can be distinguished.
Step S202 '：The current voiceprint is classified；
In the specific implementation, the sound that sends of multiple users may be included in due to voice signal, so, can be according to sound
The difference of feature carries out the difference to voiceprint, can preferably determine number of users.
Step S203 '：The vocal print number of types of the current voiceprint is counted as active user's quantity.
It is understood that current voiceprint can be classified by the difference of sound characteristic, sorted vocal print
Information represents different users, and vocal print number of types also just represents active user's quantity.Certainly, when number of users is excessive
When, voiceprint is obtained with determining that number of users will produce larger amount of calculation, for this kind of situation, in practical operation, when
When number of users is more than certain quantitative value, active user's quantity directly can be confirmed as into a fixed quantitative value.Such as when
When actual user's quantity in space is 10, it is contemplated that Application on Voiceprint Recognition has certain operation with active user's determination of amount and missed
Difference, and finally determine current volume adjustment parameter when, number of users be 10 or other similar quantitative values there will be no it is larger
Consumer's Experience difference.So, can be directly by default use when active user's quantity of confirmation is more than pre-set user amount threshold
Family amount threshold is as active user's quantity.
In the specific implementation, for example, when the active user's quantity identified according to voice signal is 8, pre-set user number
It is 2 to measure threshold value, then active user's quantity can be defined as into 2.Because current volume corresponding to being searched according to active user's quantity
It is 2 or 8 for quantity in terms of Consumer's Experience during adjustment parameter, the volume adjusting parameter of setting there will be no larger difference,
So taking this kind to set, the meter of equipment on the basis of ensureing to determine volume adjusting parameter according to number of users, can be reduced
Calculation amount.
The step S30, is specifically included：
Step S301：Judge whether active user's quantity is the second pre-set user quantity；
It is understood that wherein, the second pre-set user quantity can be 1, when judging active user's quantity for 1
When, the regulation for intelligent sound box can be realized according to the volume adjusting parameter set before the user, what this kind of mode was set
Volume is more bonded the use habit of user.
When active user's quantity is the second pre-set user quantity, step S302 is performed.
Step S302：The active user according to corresponding to being searched the current voiceprint identifies in the first mapping relations,
In the second mapping relations according to corresponding to active user's identifier lookup current volume adjustment parameter.
In the specific implementation, wherein, first mapping relations include voiceprint and the corresponding relation of user's mark, institute
The first mapping relations and the can be pre-set by stating the second mapping relations and including user's mark and the corresponding relation of volume adjusting parameter
Two mapping relations.The corresponding relation that first mapping relations include voiceprint and user identifies, the voiceprint are
The sound characteristic of user, for recording user identity by way of sound, the user, which is identified as, determines the one of user identity
Segment identification, user's mark can be that a unique and unordered piece of digital encodes；Second mapping relations identify including user
With the corresponding relation of volume adjusting parameter, the volume adjusting parameter is the parameters,acoustic specific targets pre-set, such as, institute
It can be volume value 25 or 70 to state volume adjusting parameter, wherein the number range of the volume value can be set according to the specific of smart machine
Put and be adjusted.
It is understood that after current voiceprint is extracted from voice signal, can according to current voiceprint come
It is determined that corresponding active user mark, determined further according to active user's mark corresponding to current volume adjustment parameter, it is also just real
Show according to the sound of user come volume value accustomed to using before determining user.
In the present embodiment, by carrying out Application on Voiceprint Recognition to voice signal, active user's quantity can be preferably determined；And
And by determining volume adjusting parameter according to the voiceprint extracted, the user's root for using the smart machine can be allowed
According to before using when the user volume value that voluntarily sets realize the volume adjusting for intelligent sound box, that is, facilitating user makes
With, also meet user custom volume demand.
Reference picture 5, Fig. 5 is the schematic flow sheet of volume adjusting method fourth embodiment of the present invention, based on shown in above-mentioned Fig. 4
Embodiment, propose the fourth embodiment of volume adjusting method of the present invention.
In the third embodiment, afterwards, methods described also includes the step S201 '：
Step S2011：The current voiceprint is matched with each voiceprint in first mapping relations；
In the specific implementation, may be included for the first time using the use of the equipment in the voice signal that smart machine collects
Family, determination of the smart machine for number of users, will can be set using this for the first time in voice signal when being used for the ease of next time
The voiceprint of standby user is stored.Wherein, by the current voiceprint and each sound in first mapping relations
Line information is matched, and the user of equipment was not used for determination.
Step S2012：Using the current voiceprint matched not successfully as new voiceprint, and corresponding to generation
New user's mark；
It is understood that the voiceprint matched not successfully illustrates not storing the voiceprint in smart machine, therefore
And represent that the current voiceprint matched not successfully is the sound sent for the first time using the user of the equipment, it can generate
One new user's mark.
Step S2013：The new voiceprint and new user are identified to correspond to and are saved into first mapping relations
In.
The first mapping pass is being saved into the specific implementation, the new voiceprint and new user are identified to correspond to
In system, in the follow-up of smart machine in use, when it needs to be determined that number of users is with corresponding volume adjusting parameter, you can according to
The voiceprint of the new user stored determines to realize.
After the step S301, when active user's quantity is not or not second pre-set user quantity, step is performed
Rapid S302 '.
It is understood that for example, when the second pre-set user quantity is 1, and active user's quantity is not 1 situation
Under, due to the bad volume adjusting parameter determined needed for multiple users, can by a default volume value is set realize for
The volume adjusting of more people's occasions.It is additionally, since and multiple users is defined as by voice signal, represents that active user is handed over
Stream, typically can be arranged to a relatively low volume value by the default volume value, to reduce the interference for user's exchange activity.
Step S302 '：Obtain default volume value；
The step S302 ' afterwards, performs step S40 '.
Step S40 '：By volume adjusting to the default volume value.
In the specific implementation, for example, if the volume value scope of smart machine is 0 to 100, the default volume value can be set
For 10, that is, it is arranged to a relatively low volume.When identifying that number of users is more than 1 from current spatial, you can volume is adjusted
For 10, to reduce volume user's exchange activity is more swimmingly carried out.
In the present embodiment first mapping is saved into by identifying the new voiceprint and new user to correspond to
Relation, serve the voiceprint for gathering new user in real time and be used for the effect of follow-up user's identification, equipment can be reduced
Operand；Meanwhile by being arranged on the regulative mode of volume when active user's quantity is not the second pre-set user quantity, can
Preferably to meet the volume demand under multi-user scene.
Reference picture 6, Fig. 6 is the schematic flow sheet of the embodiment of volume adjusting method the 5th of the present invention, based on shown in above-mentioned Fig. 5
Embodiment, propose the 5th embodiment of volume adjusting method of the present invention.
In the 5th embodiment, the step S302 ', specifically include：
Step S302 "：Obtain default volume value and record current volume value.
It is understood that in order to adapt to conversion of the multi-user scene to former usage scenario, in other words, when the original of user makes
When with scene being that the intelligent sound box is used alone in party A-subscriber, the volume of intelligent sound box will be joined by volume adjusting corresponding to party A-subscriber
Number be adjusted to determine current volume, if but multiple users are now entered in the use environment of intelligent sound box, and
Multiple users are in communication state, then change for the volume demand of intelligent sound box, then need intelligent sound box can
To carry out adaptive change according to the conversion of scene.But after adaptations generation, if multiple users leave again, need
Party A-subscriber is restored to be used alone under the scene of the audio amplifier, then can be by recording current volume value in advance and may recognize that
Scene changes are to meet the demand.The current volume value is the running current volume parameter of smart machine.
Afterwards, methods described also includes the step S40 '：
Step S401：Resurvey the voice signal in current environment；
It should be appreciated that in order that intelligent sound box can learn the volume demand of real-time change, adjusted to volume
After section, the voice signal in current environment can be still acquired, and the voice signal collected is designated as new sound and believed
Number.
Step S402：Voice signal according to resurveying redefines active user's quantity in current environment；
In the specific implementation, after the voice signal resurveyed is received, can be gone to determine to work as according to new voice signal
Active user's quantity in preceding environment, by determining that active user's quantity can determine current usage type quickly, such as,
If it is still more people to detect number of users again, need not recover to history volume value, to facilitate users to continue to exchange.
Step S403：When the active user's quantity redefined is the second pre-set user quantity, volume is recovered
To the current volume value.
It is understood that if former usage scenario, which is party A-subscriber, is using the equipment, in order to accelerate the reaction of intelligent sound box speed
Degree, when the active user's quantity redefined is the second pre-set user quantity, such as, the second pre-set user quantity is 1,
It can then assert that the unique user is party A-subscriber, volume is recovered to the current volume value.The current volume value is that A is used
Volume value after volume adjusting parameter regulation corresponding to family, because the volume value of current volume value record is former usage scenario
Middle volume value.
Certainly, it can also be gone to determine user according to voiceprint again, and determine the volume adjusting parameter of corresponding user, this reality
Example is applied not to be restricted this.
When the acoustic environment that smart machine uses is changed and is finally recovered to initial acoustic environment in the present embodiment
When, can be adaptively extensive by volume value to realize by resurveying new voice signal and carrying out the judgement for user identity
The multiple extremely current volume value, meets the use demand that user is different when the use environment of smart machine changes.
In addition, the embodiment of the present invention also proposes a kind of storage medium, volume adjusting program is stored with the storage medium,
Following operation is realized when the volume adjusting program is executed by processor：
Gather the voice signal in current environment；
Active user's quantity in current environment is determined according to the voice signal；
The current volume adjustment parameter according to corresponding to searching active user's quantity；
Volume adjusting is carried out by the current volume adjustment parameter.
Further, following operation is also realized when the volume adjusting program is executed by processor：
Judge whether active user's quantity is the first pre-set user quantity；
When active user's quantity is the first pre-set user quantity, current time is recorded, judges current time
Whether in preset time period；
When the current time is in the preset time period, the voice signal in the collection current environment is returned
The step of.
Further, following operation is also realized when the volume adjusting program is executed by processor：
When the current time is not in the preset time period, equipment state is set to off closed state.
Further, following operation is also realized when the volume adjusting program is executed by processor：
Application on Voiceprint Recognition is carried out to the voice signal, to obtain the current voiceprint in the voice signal；
The current voiceprint is classified；
The vocal print number of types of the current voiceprint is counted as active user's quantity.
Further, following operation is also realized when the volume adjusting program is executed by processor：
Judge whether active user's quantity is the second pre-set user quantity；
When active user's quantity is the second pre-set user quantity, worked as in the first mapping relations according to described
Active user's mark corresponding to preceding voiceprint lookup, it is corresponding according to active user's identifier lookup in the second mapping relations
Current volume adjustment parameter, first mapping relations include the corresponding relation that voiceprint and user identify, described second
Mapping relations include the corresponding relation of user's mark and volume adjusting parameter.
Further, following operation is also realized when the volume adjusting program is executed by processor：
The current voiceprint is matched with each voiceprint in first mapping relations；
Using the current voiceprint matched not successfully as new voiceprint, and user new corresponding to generation marks
Know；
The new voiceprint and new user are identified into corresponding be saved into first mapping relations.
Further, following operation is also realized when the volume adjusting program is executed by processor：
When active user's quantity is not or not second pre-set user quantity, default volume value is obtained；
Correspondingly, following operation is also realized：
By volume adjusting to the default volume value.
Further, following operation is also realized when the volume adjusting program is executed by processor：
Obtain default volume value and record current volume value；
Correspondingly, following operation is also realized：
Resurvey the voice signal in current environment；
Voice signal according to resurveying redefines active user's quantity in current environment；
When the active user's quantity redefined is the second pre-set user quantity, volume is recovered to described current
Volume value.
By determining active user's quantity in current environment and being searched according to active user's quantity in the present embodiment
Corresponding current volume adjustment parameter, volume adjusting is carried out automatically according to current volume adjustment parameter to realize, is also just met
Because of personnel amount change in current spatial and different volume demands caused by social type change, can preferably solve existing
Intelligent sound box can not preferably carry out the technical problem of the adaptive adjustment of parameter according to environmental change.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of volume adjusting method, it is characterised in that the described method comprises the following steps：
Gather the voice signal in current environment；
Active user's quantity in current environment is determined according to the voice signal；
The current volume adjustment parameter according to corresponding to searching active user's quantity；
Volume adjusting is carried out by the current volume adjustment parameter.
2. the method as described in claim 1, it is characterised in that described that working as in current environment is determined according to the voice signal
After preceding number of users, methods described also includes：
Judge whether active user's quantity is the first pre-set user quantity；
When active user's quantity is the first pre-set user quantity, current time is recorded, judges the current time
Whether in preset time period；
When the current time is in the preset time period, the step of the voice signal in the collection current environment is returned
Suddenly.
3. method as claimed in claim 2, it is characterised in that described to judge the current time whether in preset time period
After interior, methods described also includes：
When the current time is not in the preset time period, equipment state is set to off closed state.
4. the method as described in claim 1, it is characterised in that described that working as in current environment is confirmed according to the voice signal
Preceding number of users, is specifically included：
Application on Voiceprint Recognition is carried out to the voice signal, to obtain the current voiceprint in the voice signal；
The current voiceprint is classified；
The vocal print number of types of the current voiceprint is counted as active user's quantity.
5. method as claimed in claim 4, it is characterised in that described current according to corresponding to searching active user's quantity
Volume adjusting parameter, is specifically included：
Judge whether active user's quantity is the second pre-set user quantity；
When active user's quantity is the second pre-set user quantity, according to the current sound in the first mapping relations
Active user corresponding to line information searching identifies, and is worked as in the second mapping relations according to corresponding to active user's identifier lookup
Preceding volume adjusting parameter, the corresponding relation that first mapping relations include voiceprint and user identifies, second mapping
Relation includes the corresponding relation of user's mark and volume adjusting parameter.
6. method as claimed in claim 5, it is characterised in that it is described that Application on Voiceprint Recognition is carried out to the voice signal, to obtain
After current voiceprint in the voice signal, methods described also includes：
The current voiceprint is matched with each voiceprint in first mapping relations；
Using the current voiceprint matched not successfully as new voiceprint, and user new corresponding to generation identifies；
The new voiceprint and new user are identified into corresponding be saved into first mapping relations.
7. method as claimed in claim 5, it is characterised in that described to judge whether active user's quantity is second default
After number of users, methods described also includes：
When active user's quantity is not or not second pre-set user quantity, default volume value is obtained；
Correspondingly, it is described that volume adjusting is carried out by the current volume adjustment parameter, specifically include：
By volume adjusting to the default volume value.
8. method as claimed in claim 7, it is characterised in that it is described to obtain default volume value, specifically include：
Obtain default volume value and record current volume value；
Correspondingly, described by after volume adjusting to the default volume value, methods described also includes：
Resurvey the voice signal in current environment；
Voice signal according to resurveying redefines active user's quantity in current environment；
When the active user's quantity redefined is the second pre-set user quantity, volume is recovered to the current volume
Value.
9. a kind of smart machine, it is characterised in that the smart machine includes：Microphone, memory, processor and it is stored in institute
The volume adjusting program that can be run on memory and on the processor is stated, the volume adjusting program is held by the processor
The step of volume adjusting method as any one of claim 1 to 8 is realized during row.
10. a kind of storage medium, it is characterised in that volume adjusting program, the volume adjusting are stored with the storage medium
The step of volume adjusting method as any one of claim 1 to 8 is realized when program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710678036.9A CN107562403A (en) | 2017-08-09 | 2017-08-09 | A kind of volume adjusting method, smart machine and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710678036.9A CN107562403A (en) | 2017-08-09 | 2017-08-09 | A kind of volume adjusting method, smart machine and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107562403A true CN107562403A (en) | 2018-01-09 |
Family
ID=60975191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710678036.9A Pending CN107562403A (en) | 2017-08-09 | 2017-08-09 | A kind of volume adjusting method, smart machine and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107562403A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040660A (en) * | 2018-10-15 | 2018-12-18 | 四川省有线广播电视网络股份有限公司 | The system of adjust automatically video conferencing system sub-venue terminal volume |
| CN109348059A (en) * | 2018-10-31 | 2019-02-15 | 努比亚技术有限公司 | Volume adjusting method, mobile terminal and computer readable storage medium |
| CN109614069A (en) * | 2018-11-30 | 2019-04-12 | 河南职业技术学院 | Computer based volume control method and volume adjusting apparatus |
| CN110225396A (en) * | 2018-03-01 | 2019-09-10 | 深圳Tcl数字技术有限公司 | A kind of method, system and the storage medium of volume adjustment |
| CN110347367A (en) * | 2019-07-15 | 2019-10-18 | 百度在线网络技术（北京）有限公司 | Volume adjusting method, terminal device, storage medium and electronic equipment |
| CN110753288A (en) * | 2018-07-23 | 2020-02-04 | 中国电信股份有限公司 | Method and system for automatically adjusting sound volume of sound box |
| CN111491251A (en) * | 2019-12-26 | 2020-08-04 | 马艺 | Sound box array operation control platform |
| CN111522285A (en) * | 2020-06-26 | 2020-08-11 | 深圳全景空间工业有限公司 | Environment data sharing method for smart home |
| CN111930336A (en) * | 2020-07-29 | 2020-11-13 | 歌尔科技有限公司 | Volume adjusting method and device of audio device and storage medium |
| CN114339387A (en) * | 2020-09-27 | 2022-04-12 | 深圳Tcl新技术有限公司 | Parameter adjusting method, intelligent terminal and storage medium |
| CN114708872A (en) * | 2022-03-22 | 2022-07-05 | 青岛海尔科技有限公司 | Voice instruction response method and device, storage medium and electronic device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120131462A1 (en) * | 2010-11-24 | 2012-05-24 | Hon Hai Precision Industry Co., Ltd. | Handheld device and user interface creating method |
| CN103369274A (en) * | 2013-06-28 | 2013-10-23 | 青岛歌尔声学科技有限公司 | Intelligent television regulating system and television regulating method thereof |
| CN103688531A (en) * | 2011-07-26 | 2014-03-26 | 索尼公司 | Control device, control method and program |
| CN103809554A (en) * | 2012-11-05 | 2014-05-21 | 索尼公司 | Audio illumination apparatus and storage medium |
| CN103945062A (en) * | 2014-04-16 | 2014-07-23 | 华为技术有限公司 | User terminal volume adjusting method, device and terminal |
| CN105406828A (en) * | 2014-08-22 | 2016-03-16 | 小米科技有限责任公司 | Sound equipment adjustment method and device |
| CN105607507A (en) * | 2016-03-21 | 2016-05-25 | 美的集团股份有限公司 | Smart sofa, smart home system and smart home control method |
| CN106921912A (en) * | 2017-04-26 | 2017-07-04 | 北京中鼎思宏科技有限公司 | Vehicle audio method for controlling volume, device and car audio system |
-
2017
- 2017-08-09 CN CN201710678036.9A patent/CN107562403A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120131462A1 (en) * | 2010-11-24 | 2012-05-24 | Hon Hai Precision Industry Co., Ltd. | Handheld device and user interface creating method |
| CN103688531A (en) * | 2011-07-26 | 2014-03-26 | 索尼公司 | Control device, control method and program |
| CN103809554A (en) * | 2012-11-05 | 2014-05-21 | 索尼公司 | Audio illumination apparatus and storage medium |
| CN103369274A (en) * | 2013-06-28 | 2013-10-23 | 青岛歌尔声学科技有限公司 | Intelligent television regulating system and television regulating method thereof |
| CN103945062A (en) * | 2014-04-16 | 2014-07-23 | 华为技术有限公司 | User terminal volume adjusting method, device and terminal |
| CN105406828A (en) * | 2014-08-22 | 2016-03-16 | 小米科技有限责任公司 | Sound equipment adjustment method and device |
| CN105607507A (en) * | 2016-03-21 | 2016-05-25 | 美的集团股份有限公司 | Smart sofa, smart home system and smart home control method |
| CN106921912A (en) * | 2017-04-26 | 2017-07-04 | 北京中鼎思宏科技有限公司 | Vehicle audio method for controlling volume, device and car audio system |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110225396A (en) * | 2018-03-01 | 2019-09-10 | 深圳Tcl数字技术有限公司 | A kind of method, system and the storage medium of volume adjustment |
| CN110753288B (en) * | 2018-07-23 | 2021-08-17 | 中国电信股份有限公司 | Method and system for automatically adjusting sound volume of sound box |
| CN110753288A (en) * | 2018-07-23 | 2020-02-04 | 中国电信股份有限公司 | Method and system for automatically adjusting sound volume of sound box |
| CN109040660A (en) * | 2018-10-15 | 2018-12-18 | 四川省有线广播电视网络股份有限公司 | The system of adjust automatically video conferencing system sub-venue terminal volume |
| CN109348059A (en) * | 2018-10-31 | 2019-02-15 | 努比亚技术有限公司 | Volume adjusting method, mobile terminal and computer readable storage medium |
| CN109614069A (en) * | 2018-11-30 | 2019-04-12 | 河南职业技术学院 | Computer based volume control method and volume adjusting apparatus |
| CN110347367A (en) * | 2019-07-15 | 2019-10-18 | 百度在线网络技术（北京）有限公司 | Volume adjusting method, terminal device, storage medium and electronic equipment |
| CN110347367B (en) * | 2019-07-15 | 2023-06-20 | 百度在线网络技术（北京）有限公司 | Volume adjusting method, terminal device, storage medium and electronic device |
| CN111491251A (en) * | 2019-12-26 | 2020-08-04 | 马艺 | Sound box array operation control platform |
| CN111522285A (en) * | 2020-06-26 | 2020-08-11 | 深圳全景空间工业有限公司 | Environment data sharing method for smart home |
| CN111930336A (en) * | 2020-07-29 | 2020-11-13 | 歌尔科技有限公司 | Volume adjusting method and device of audio device and storage medium |
| CN114339387A (en) * | 2020-09-27 | 2022-04-12 | 深圳Tcl新技术有限公司 | Parameter adjusting method, intelligent terminal and storage medium |
| CN114708872A (en) * | 2022-03-22 | 2022-07-05 | 青岛海尔科技有限公司 | Voice instruction response method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107562403A (en) | A kind of volume adjusting method, smart machine and storage medium | |
| CN103456305B (en) | Terminal and the method for speech processing based on multiple sound collection unit | |
| CN106375590A (en) | Volume adjustment method and device for smart terminal | |
| CN111081257A (en) | Voice acquisition method, device, equipment and storage medium | |
| CN107708007A (en) | A kind of wireless headset control method, device and wireless headset | |
| CN108924370A (en) | Call center's outgoing call speech waveform analysis method, system, equipment and storage medium | |
| CN107343077A (en) | Identify malicious call and establish the method, apparatus of identification model, equipment | |
| CN104575503B (en) | Audio recognition method and device | |
| CN104078045B (en) | Identifying method and electronic device | |
| CN107734126A (en) | voice adjusting method, device, terminal and storage medium | |
| CN110070857A (en) | The model parameter method of adjustment and device, speech ciphering equipment of voice wake-up model | |
| CN109284080A (en) | Audio method of adjustment, device, electronic equipment and storage medium | |
| CN106486127A (en) | A kind of method of speech recognition parameter adjust automatically, device and mobile terminal | |
| CN107979790A (en) | One kind call noise-reduction method, device, equipment and medium | |
| CN104781862A (en) | Real-time traffic detection | |
| CN109448705A (en) | A kind of phonetic segmentation method and device, computer installation and readable storage medium storing program for executing | |
| CN104410973A (en) | Recognition method and system for tape played phone fraud | |
| CN109271129A (en) | Audio method of adjustment, device, electronic equipment and storage medium | |
| CN109256151A (en) | Call voice regulates and controls method, apparatus, mobile terminal and readable storage medium storing program for executing | |
| CN105872205A (en) | Information processing method and device | |
| CN110389697A (en) | Data interactive method and device, storage medium and electronic device | |
| CN101211615A (en) | Method, system and apparatus for automatic recording for specific human voice | |
| CN108052985A (en) | Information collecting method, information acquisition terminal and computer readable storage medium | |
| CN108733341A (en) | A kind of voice interactive method and device | |
| KR20070008210A (en) | Method and apparatus for blocking the objectionable multimedia information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |