CN103259908B - A kind of mobile terminal and its intelligent control method - Google Patents

A kind of mobile terminal and its intelligent control method Download PDF

Info

Publication number
CN103259908B
CN103259908B CN201210034244.2A CN201210034244A CN103259908B CN 103259908 B CN103259908 B CN 103259908B CN 201210034244 A CN201210034244 A CN 201210034244A CN 103259908 B CN103259908 B CN 103259908B
Authority
CN
China
Prior art keywords
voice
mobile terminal
unit
user
voiceprint
Prior art date
Application number
CN201210034244.2A
Other languages
Chinese (zh)
Other versions
CN103259908A (en
Inventor
阳光
Original Assignee
联想(北京)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 联想(北京)有限公司 filed Critical 联想(北京)有限公司
Priority to CN201210034244.2A priority Critical patent/CN103259908B/en
Publication of CN103259908A publication Critical patent/CN103259908A/en
Application granted granted Critical
Publication of CN103259908B publication Critical patent/CN103259908B/en

Links

Abstract

The invention discloses a kind of mobile terminal and intelligent control method, wherein mobile terminal includes:Receiving unit, voice content extraction unit, voiceprint extraction unit and voice recognition unit;Receiving unit is connected with voice content extraction unit and vocal print information extraction unit, for receiving the voice messaging of user input and sending to voice content extraction unit and vocal print information extraction unit;Voice content extraction unit, for extracting the voice content in voice messaging and sending to voice recognition unit;Voiceprint extraction unit, for extracting the voiceprint in voice messaging, and sends to voice recognition unit;Voice recognition unit, is connected with voice content extraction unit and vocal print information extraction unit, for when voice content and voiceprint meet pre-conditioned, performing corresponding operating.The present invention realizes the personalized mobile terminal control for user by extracting voiceprint and being controlled using voiceprint, improves the accuracy rate of control.

Description

A kind of mobile terminal and its intelligent control method

Technical field

The present invention relates to the communications field, more particularly, to a kind of mobile terminal and its intelligent control method.

Background technology

User sometimes and is inconvenient to use the adept machine of hand, such as user is driving or having greasy dirt, water etc. on hand.Now need There is a kind of method of rational operating handset.

This problem is solved by speech recognition technology in the prior art.Its principle is that default standard is input into mobile phone Voice content, when the voice of user input and received pronunciation content matching, mobile phone performs associative operation automatically, such as connect automatically Answer a call or hang up the telephone.But this mode has one disadvantage in that exactly any user can be controlled to same mobile phone.Than Such as when a user is not intended to receive calls, but people around him is when having said the voice for matching, the mobile phone of the user will from It is dynamic to receive calls.This has the disadvantage what is caused without specific aim by the control method, causes user to the accurate of mobile phone control Rate is relatively low.The problem is also existed in other mobile terminals.Therefore, a kind of personalization control for user is badly in need of at present Method, to improve the accuracy rate controlled mobile terminal.

The content of the invention

The invention provides a kind of mobile terminal and its intelligent control method, by extracting voiceprint and to voiceprint Judged, realized the personalized mobile terminal control for user, improve the accuracy rate of control.

The invention provides a kind of mobile terminal, the mobile terminal includes:

Receiving unit, voice content extraction unit, voiceprint extraction unit and voice recognition unit;The receiving unit Be connected with the voice content extraction unit and the voiceprint extraction unit, for receive user input voice messaging simultaneously Send to the voice content extraction unit and the voiceprint extraction unit;The voice content extraction unit, for carrying Take the voice content in the voice messaging and send to the voice recognition unit;The voiceprint extraction unit, is used for The voiceprint in the voice messaging is extracted, and sends the voiceprint to the voice recognition unit;The voice is known Other unit, is connected with the voice content extraction unit and the voiceprint extraction unit, in the voice content and When the voiceprint meets pre-conditioned, corresponding operating is performed.

Preferably, the mobile terminal also includes:

Unit, the voice messaging for analyzing user input obtains the standard vocal print feature of the user;

The voice recognition unit, when being additionally operable to the voiceprint and meeting the standard vocal print feature, performs corresponding behaviour Make.

Preferably, the mobile terminal also includes:

First microphone, the second microphone, computing unit voice intensity recognition unit and hands-free unit;

The computing unit, for the user according to communication process voice messaging reach first microphone and The status information of second microphone calculates the distance of the user and the mobile terminal;

The voice intensity recognition unit, is connected with the receiving unit, is used described in the communication process for recognizing The power of family voice messaging simultaneously generates voice intensity recognition result;

The hands-free unit, is connected with second microphone and the voice intensity recognition unit, for according to described Distance and the voice intensity recognition result control the mobile terminal to be switched between hands-free mode and non-hands-free mode.

Preferably, the mobile terminal also includes:

Background sound intensity recognition unit, is connected with the receiving unit, for the user described in the communication process Extract background sound in voice messaging, and power to the background sound is identified generating background sound intensity recognition result;

The hands-free unit, is connected with the background sound intensity recognition unit, is additionally operable to according to the distance, the voice Intensity recognition result and the background sound intensity recognition result control the mobile terminal in the hands-free mode and described non-exempt from Carrying and switch between pattern.

Preferably, the mobile terminal also includes:

Pressure sensor, is connected with the receiving unit, for producing certain shape according to the voice messaging for receiving State information;

The hands-free unit, is additionally operable to be connected with the pressure sensor, according to the distance, the voice intensity identification The status information of result and the pressure sensor controls the mobile terminal in the hands-free mode and the non-hands-free mode Between switch over.

Present invention also offers a kind of intelligent control method of mobile terminal, methods described includes:

Receive the voice messaging of user input;Extract the sound of the voice content and the voice messaging in the voice messaging Line information;When the voice content and the voiceprint meet pre-conditioned, associative operation is performed.

Preferably, methods described also includes:

The voice messaging of user input is analyzed, the standard vocal print feature of the user is obtained;

The voiceprint meet it is pre-conditioned including:The voiceprint meets the standard vocal print feature.

When the mobile terminal includes the first microphone and the second microphone, it is preferred that methods described also includes:

The voice messaging of the user according to communication process reaches the voice intensity of the first microphone and the second microphone Information, calculates the distance of the user and the mobile terminal;

Recognize the power of user speech information described in the communication process and generate voice intensity recognition result;

The mobile terminal is controlled in hands-free mode and non-hands-free according to the distance and the voice intensity recognition result Switched between pattern.

Preferably, methods described also includes:

Background sound is extracted in the voice messaging of user described in the communication process, and to the power of the background sound It is identified generating background sound intensity recognition result;

It is described that the mobile terminal is controlled in hands-free mode and non-according to the distance and the voice intensity recognition result Switching includes between hands-free mode:

According to the distance, the voice intensity recognition result and the background sound intensity recognition result control the movement Terminal switches between the hands-free mode and the non-hands-free mode.

Preferably, methods described also includes:

The voice messaging of user produces certain pressure sensor state according to the communication process for receiving;

It is described that the mobile terminal is controlled in the hands-free mode according to the distance and the voice intensity recognition result Switching and the non-hands-free mode between includes:

According to the distance, the voice intensity recognition result and the pressure sensor state control the mobile terminal Switch between the hands-free mode and the non-hands-free mode.

Compared with prior art, the present invention has the advantages that:

Voice content and voiceprint are extracted by the voice messaging for being input into mobile terminal in the present invention, and simultaneously to language Whether sound content and voiceprint meet pre-conditioned is judged so that the control to mobile terminal needs to meet vocal print simultaneously Information.Different user's voiceprints are different, therefore, with reference to the judgement of voiceprint, realize the movement for user Terminal control, it is to avoid the drawbacks of any user can be controlled to mobile terminal, improves the accuracy rate of control.

Brief description of the drawings

In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment The accompanying drawing for needing to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the invention Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also obtain according to these accompanying drawings Obtain other accompanying drawings.

Fig. 1 is the mobile terminal structure figure of the inventive method embodiment 1;

Fig. 2 is the principle schematic of the embodiment of the present invention 3;

Fig. 3 is that angle value of the present invention changes ratio corresponding relation figure with intensity of sound;

Fig. 4 is the flow chart of the inventive method embodiment 6.

Specific embodiment

Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on Embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained belongs to present invention protection Scope.

Referring to Fig. 1, the embodiment of the present invention 1 provides a kind of mobile terminal, and the mobile terminal includes:

Receiving unit 11, voice content extraction unit 12, voiceprint extraction unit 13 and voice recognition unit 14;

Receiving unit 11 is connected with voice content extraction unit 12 and vocal print information extraction unit 13, defeated for receiving user The voice messaging that enters simultaneously is sent to voice content extraction unit 12 and vocal print information extraction unit 13.

Voice content extraction unit 12, for extracting the voice content in voice messaging and sending to voice recognition unit 14。

Specifically, the voice signal that analysis is received, and convert voice signals into corresponding text message, i.e. voice Hold.

Voiceprint extraction unit 13, for extracting the voiceprint in voice messaging, and sends voiceprint to voice Recognition unit 14.

So-called vocal print, refers to the sound wave spectrum information of sound.Modern scientific research shows that vocal print has specificity, any The voiceprint map of two people is all variant.And vocal print is the characteristics of have relative stability.Especially after adult, the sound of people Can keep stablizing constant relatively for a long time.It is demonstrated experimentally that no matter talker is deliberately to imitate other people sound and the tone, or whisper in sb.'s ear is light Sound is talked, even if imitating remarkably true to life, its vocal print is but identical all the time.This shows, user can be accurately distinguished according to vocal print.

Sound wave spectrum information mainly includes pitch, loudness of a sound, the duration of a sound, four kinds of information of tone color, and these information are decomposed into nine again More than ten plant feature.These features are demonstrated by different wave length, frequency, intensity, the rhythm of alternative sounds.Sonagraph can be sound wave Change is converted into intensity, wavelength, frequency, the tempo variation of electric signal, and the change of these electric signals is depicted as wave spectrum by instrument again Figure, just into vocal print figure.

Specifically, can be analyzed to the voice signal of user input, according to existing algorithm, extract and represent vocal print The sound wave spectrum information of information.

In a particular embodiment of the present invention, the partial information such as pitch, loudness of a sound in sound wave spectrum information can only be extracted As voiceprint.Certainly, the step of be after in more accurately carry out Application on Voiceprint Recognition, highly preferred mode is to extract language All vocal print features in message number.

Voice recognition unit 14, is connected, in language with voice content extraction unit 12 and vocal print information extraction unit 13 When sound content and voiceprint meet pre-conditioned, corresponding operating is performed.

The pre-conditioned voice content and voiceprint for referring specifically to prestore in the present invention.So-called concrete operations can be Connect, hang up, the present invention is illustrated as a example by connecting and hanging up to pre-conditioned.

In a particular embodiment of the present invention, " feeding " or the " on " etc. of can prestoring are used as in the received pronunciation for connecting phone Hold, while a certain specific sound band limits that prestores is used as standard voiceprint.

So, when user is inconvenient to receive calls, it is only necessary to say the contents such as " feeding " or " on ".Now voice After recognition unit compares the voice content and voiceprint of reception with the voice content and voiceprint for prestoring respectively, sentence Break when both all sames, with regard to turn on automatically phone.And even if other users also say " feeding " or " on ", also can be because of vocal print Information does not meet pre-conditioned and cannot play control action to mobile terminal.

Likewise, in another embodiment of the invention, the conduct such as " goodbye ", " not connecing ", " extremely busy " that can prestore is hung up The received pronunciation content of phone, while a certain specific sound band limits that prestores is used as standard voiceprint.

So, when user is extremely busy, it has not been convenient to when receiving calls or needing to hang up the phone answered, corresponding language need to only be said Sound content.Now, voice recognition unit is by the voice content and voiceprint of reception and the voice content and vocal print for prestoring After information is compared respectively, when judging both all sames, phone is automatically hung up.And work as other users and say above-mentioned voice content When, can because voiceprint do not meet it is pre-conditioned cannot play control action to mobile terminal.

In specific deterministic process, to save workload, voice recognition unit first can believe voice content and vocal print One in breath is contrasted, and when this matches, then carries out the contrast of the next item down, when this mismatches, is no longer carried out another The contrast of one.Sequencing of the present invention not to two does concrete restriction.

In user input voice messaging, the environmental noise of surrounding can influence the voice messaging of input, so as to extraction Voice content and voiceprint are impacted.Therefore, in a preferred embodiment of the invention, it is more accurately to obtain voice messaging In voice content and voiceprint, mobile terminal also include pretreatment unit, one end connection receiving unit, one end connects respectively Voice content extraction unit and vocal print information extraction unit, for being pre-processed to the voice messaging that receiving unit sends, mistake Filter environmental noise.

So, voice content extraction unit and vocal print information extraction unit can just be divided the voice messaging after treatment Analyse and extract voice content and voiceprint.

Voiceprint also has variability simultaneously, i.e., for same person, with the change of age, environment or health Change, some of vocal print feature can also change.But these changes in the short period of time generally will not be particularly significant.Cause This, in an embodiment of the present invention, voice recognition unit be additionally operable to voiceprint and standard vocal print feature substantial match i.e. When matching degree is more than certain threshold value, associative operation is performed.Specifically, arrow can be set up to the multiple features for characterizing voiceprint Amount, each characteristic parameter in the voiceprint that will be extracted compares with corresponding standard vocal print feature, and provides matching degree, Then the matching degree to each feature seeks comprehensive matching degree, when the comprehensive matching degree is more than default threshold value, with reference in voice Hold and perform associative operation.

The standard voiceprint prestored in the present invention can be obtained by way of parameter is input into.But which is typically only capable to Generally characterize the vocal print of a certain user.Therefore, in embodiments of the invention 2, mobile terminal also includes unit, is used for The voice messaging of user input is analyzed, the standard vocal print feature of the user is obtained.The voice recognition unit, is additionally operable to described When voiceprint meets the standard vocal print feature, corresponding operating is performed.

User can be by the voice messaging of microphone input oneself, and then unit is divided the voice messaging Analysis, obtain to should user vocal print feature.The input behavior of user is influenceed by surrounding sometimes, to make the vocal print of acquisition Information is more accurate, can be by repeatedly input, and repeatedly analysis, carries out comprehensive mode and obtain to result.

In addition, corresponding to different voice contents, the voiceprint of user might have certain difference.Therefore, in this hair In bright, user can be input into default received pronunciation content identical voice messaging, such as when it is default connection phone voice Content is " feeding ", then user can just be obtained by repeatedly input " feeding " and characterize the vocal print feature of oneself.

Certainly, it is more highly preferred to, user can obtain first by input with phone identical received pronunciation content is connected Vocal print feature, obtains the second vocal print feature, then, by the first vocal print by input with identical received pronunciation content of hanging up the telephone Feature and the second vocal print feature are all as standard vocal print feature.Voice recognition unit first passes through the analysis to voice content, knows Voice correspondence is which standard vocal print feature, and then it is compared with corresponding standard vocal print feature, judges whether it matches.

What deserves to be explained is, heretofore described operation include it is various, can be control mobile terminal enter it is hands-free or Non- hands-free mode.Such as set when the voice content of user input is for " connecting, hands-free ", control mobile terminal is connected and automatic Into hands-free mode.

In sum, the mobile terminal in the above embodiment of the present invention, by extracting the voiceprint in voice messaging, and It is contrasted to carry out corresponding operating with default standard voiceprint, it is to avoid in the prior art only carried out according to a voice content Identification, causes other users to be also controlled to mobile terminal, so that control does not have specific aim, and precise control rate is not Problem high.

User generally inconvenience with hand take mobile terminal when using speech recognition technology is come auto-pickup or hangs up the telephone, Now, user typically apart from mobile terminal farther out, when user voice intensity is smaller, communication effect is often not so good.Therefore, In embodiments of the invention 3, mobile terminal also includes:

First microphone, the second microphone, computing unit, voice intensity recognition unit and hands-free unit.

First microphone, for receiving the voice messaging of user, and is transferred to the opposing party for conversing, that is, realize movement Call between terminal and another mobile terminal.

Usual only one of which microphone is microphone on current mobile terminal, for realizing above-mentioned functions.Second is transaudient Device, the voice messaging for receiving user.

Computing unit, the first microphone and the second microphone are reached for the voice messaging according to user in communication process Voice strength information calculates the distance of user and mobile terminal.

The present invention installs the second microphone in another region of mobile terminal, to calculate user to the distance of mobile terminal. Concrete principle is as shown in Figure 2:

User is at the A of position, and the first microphone is at the B of position, and the second microphone is at the C of position.Sound is being passed Intensity can gradually weaken during passing, and user voice just to direction it is different from the angle of microphone, intensity of sound It is different.

First, measurement user voice reaches the Strength Changes value of the first microphone and the second microphone, it is assumed that be followed successively by P1, P2.So the result of P1/P2 be exactly user voice just to direction and the first microphone angle value.

Then, the corresponding relation of ratio is changed with intensity of sound according to the angle value for prestoring, if being obtained by calculating When user this sound is just to the first microphone, the intensity of sound P3 of the first microphone is reached.Wherein, intensity of sound change ratio is The ratio of Strength Changes when Strength Changes and sound when referring to sound along a certain angular spread are just to propagating.As shown in figure 3, being The angle value for prestoring changes the corresponding relation figure of ratio with intensity of sound.Accordingly, user voice can be known with angle value For P1/P1 direction reach the first microphone Strength Changes be this sound just to reach the first microphone Strength Changes k Times.So just can obtain P3=P1/k by calculating.

Finally, the Strength Changes P0 according to known user voice in unit distance, must by formula X=P0/P3 User is arrived with a distance from the first microphone.

In the present invention, described angle value and the corresponding relation and intensity of sound of intensity of sound change are in unit distance Change intensity can be obtained by advance experiment.

Voice intensity recognition unit, is connected with receiving unit, the power for recognizing user speech information in communication process And generate voice intensity recognition result.

Hands-free unit, is connected with the second microphone and voice intensity recognition unit, for being known according to distance and voice intensity Other output control mobile terminal is switched between hands-free mode and non-hands-free mode.

Specifically, when distant and smaller voice intensity, control mobile terminal is automatically into hands-free mode.

When apart from closer, when voice intensity is larger, mobile terminal is controlled to automatically switch to non-hands-free mode.

In the present invention, user can voluntarily set switching condition, and the present invention is not limited to specific switching condition.

The voice that receiving unit is received generally all is mingled with background sound, and the intensity of background sound can produce shadow to communication process Ring.Therefore, in embodiments of the invention 4, mobile terminal also includes:

Background sound intensity recognition unit, is connected with receiving unit, for being carried in the voice messaging of the user from communication process Background sound is taken out, and the power of background sound is identified to generate background sound intensity recognition result.

Hands-free unit, is connected with background sound intensity recognition unit, is additionally operable to according to distance, voice intensity recognition result and the back of the body Scape loudness of a sound degree recognition result control mobile terminal is switched between hands-free mode and non-hands-free mode.

Specifically, when background sound intensity is big, distance is remote, voice intensity hour, controllable mobile terminal enters hands-free mode.

Same can the generation on communication effect in position between user and mobile terminal influences.Here the position having a talk about be not necessarily referring to away from From, but the angular relationship of user and mobile terminal.Such as user is just to mobile terminal or in side or back to movement Terminal.Under same distance and voice intensity, different angular relationships, communication effect is different.Therefore, in implementation of the invention In example 5, mobile terminal also includes:

Pressure sensor, is connected with receiving unit, for producing certain status information according to the voice messaging for receiving.

Angle between user and mobile terminal is different, and the angle that voice reaches pressure sensor is just different, and now pressure is passed Sensor will produce different states.

Hands-free unit, is additionally operable to be connected with pressure sensor, according to distance, voice intensity recognition result and pressure sensor Status information control mobile terminal switched between hands-free mode and non-hands-free mode.

Specifically, when distance is remote, voice intensity is small, the position between the state representation user of pressure sensor and mobile terminal Be unfavorable for call such as back to when, control mobile terminal enter hands-free mode.

Certainly, the embodiment of the present invention can be combined with the intensity of background sound and control the pattern switching of mobile terminal together. In the present invention, specific switching condition is not limited.

The embodiment of the present invention 6 additionally provides a kind of intelligent control method of mobile terminal, and referring to Fig. 3, methods described includes:

S11, the voice messaging for receiving user input.

The voiceprint of S12, the voice content and the voice messaging extracted in the voice messaging.

S13, when the voice content and the voiceprint meet pre-conditioned, perform associative operation.

The pre-conditioned received pronunciation content for referring specifically to prestore and standard voiceprint in the present invention.So-called specific behaviour Work can be to turn on, hang up.In embodiments of the invention 7, to obtain more accurately standard voiceprint, methods described is also Including:The voice messaging of user input is analyzed, the standard vocal print feature of user is obtained.Now voiceprint meet it is pre-conditioned i.e. For voiceprint meets standard vocal print feature.When determining voice content and voiceprint with default received pronunciation content and mark When quasi- vocal print feature is matched, associative operation is performed.

Specifically, then user can be analyzed by the voice messaging of microphone input oneself to the voice messaging, Obtain to should user vocal print feature.The input behavior of user is influenceed by surrounding sometimes, for the vocal print for making acquisition is believed Breath is more accurate, can be by repeatedly input, and repeatedly analysis, carries out comprehensive mode and obtain to result.

User generally inconvenience with hand take mobile terminal when using speech recognition technology is come auto-pickup or hangs up the telephone, Now, user typically apart from mobile terminal farther out, when user voice intensity is smaller, communication effect is often not so good.Therefore, In embodiments of the invention 8, mobile terminal includes the first microphone and the second microphone, and methods described also includes:

Voice messaging according to user in communication process reaches the status information of the first microphone and the second microphone, calculates User and the distance of mobile terminal.

Usual only one of which microphone is microphone on current mobile terminal, for collecting voice and sending call to Another mobile terminal, to realize the call between mobile terminal.

The present invention installs the second microphone in another region of mobile terminal, to calculate user to the distance of mobile terminal.

Recognize the power of user speech information in communication process and generate voice intensity recognition result.

Carried out between hands-free mode and non-hands-free mode according to distance and voice intensity recognition result control mobile terminal Switching.

Specifically, when distant and smaller voice intensity, control mobile terminal is automatically into hands-free mode.

When apart from closer, when voice intensity is larger, mobile terminal is controlled to automatically switch to non-hands-free mode.

In the present invention, user can voluntarily set switching condition, and the present invention is not limited to specific switching condition.

The voice that mobile terminal is received generally all is mingled with background sound, and the intensity of background sound can produce shadow to communication process Ring.Therefore, in embodiments of the invention 9, the method also includes:

Extract background sound in the voice messaging of user from communication process, and power to background sound is identified generation Background sound intensity recognition result.

It is described that the mobile terminal is controlled in hands-free mode and non-according to the distance and the voice intensity recognition result Switching includes between hands-free mode:

According to the distance, the voice intensity recognition result and the background sound intensity recognition result control the movement Terminal switches between the hands-free mode and the non-hands-free mode.

Specifically, when background sound intensity is big, distance is remote, voice intensity hour, controllable mobile terminal enters hands-free mode.

Same can the generation on communication effect in position between user and mobile terminal influences.Here the position having a talk about be not necessarily referring to away from From, but the angular relationship of user and mobile terminal.Such as user is just to mobile terminal or in side or back to movement Terminal.Under same distance and voice intensity, different angular relationships, communication effect is different.Therefore, in implementation of the invention In example 10, the method also includes:

The voice messaging of user produces certain pressure sensor state according to the communication process for receiving.

It is described that the mobile terminal is controlled in the hands-free mode according to the distance and the voice intensity recognition result Switching and the non-hands-free mode between includes:

According to the distance, the voice intensity recognition result and the pressure sensor state control the mobile terminal Switch between the hands-free mode and the non-hands-free mode.

Specifically, when distance is remote, voice intensity is small, the position between the state representation user of pressure sensor and mobile terminal Be unfavorable for call such as back to when, control mobile terminal enter hands-free mode.

Certainly, the embodiment of the present invention can be combined with the intensity of background sound and control the pattern switching of mobile terminal together. In the present invention, specific switching condition is not limited.

It is worth noting that, the method for the present invention is corresponding with mobile terminal of the invention, therefore to method part not Describe in detail again, relevant portion is referring to mobile terminal embodiment.

A kind of mobile terminal provided by the present invention and its control method are described above, tool used herein Body example is set forth to principle of the invention and implementation method, and the explanation of above example is only intended to help and understands this hair Bright method and its core concept;Simultaneously for those of ordinary skill in the art, according to thought of the invention, specific real Apply and be will change in mode and range of application.In sum, this specification content should not be construed as to limit of the invention System.

Claims (6)

1. a kind of mobile terminal, it is characterised in that the mobile terminal includes:
Receiving unit, voice content extraction unit, voiceprint extraction unit and voice recognition unit;
The receiving unit is connected with the voice content extraction unit and the voiceprint extraction unit, for receiving user The voice messaging of input is simultaneously sent to the voice content extraction unit and the voiceprint extraction unit;
The voice content extraction unit, for extracting the voice content in the voice messaging and sending to the speech recognition Unit;
The voiceprint extraction unit, for extracting the voiceprint in the voice messaging, and sends the voiceprint To the voice recognition unit;
The voice recognition unit, is connected with the voice content extraction unit and the voiceprint extraction unit, for When the voice content and the voiceprint meet pre-conditioned, corresponding operating is performed;
Also include:
First microphone, the second microphone, computing unit, voice intensity recognition unit and hands-free unit;
The computing unit, the voice messaging for the user according to communication process reaches first microphone and described The voice strength information of the second microphone calculates the distance of the user and the mobile terminal;
The voice intensity recognition unit, is connected with the receiving unit, for recognizing user's language described in the communication process The power of message breath simultaneously generates voice intensity recognition result;
Pressure sensor, is connected with the receiving unit, for producing certain state letter according to the voice messaging for receiving Breath;
The hands-free unit, is connected with second microphone, voice intensity identification and the pressure sensor unit, uses According to the status information recognition result of the distance, the voice intensity and the pressure sensor control mobile terminal Switched between hands-free mode and non-hands-free mode, the status information can characterize user and be closed with the angle of mobile terminal System.
2. mobile terminal according to claim 1, it is characterised in that the mobile terminal also includes:
Unit, the voice messaging for analyzing user input obtains the standard vocal print feature of the user;
The voice recognition unit, when being additionally operable to the voiceprint and meeting the standard vocal print feature, performs corresponding operating.
3. mobile terminal according to claim 1, it is characterised in that the mobile terminal also includes:
Background sound intensity recognition unit, is connected with the receiving unit, for the voice of the user described in the communication process Extract background sound in information, and power to the background sound is identified generating background sound intensity recognition result;
The hands-free unit, is connected with the background sound intensity recognition unit, is additionally operable to according to the distance, the voice intensity Recognition result and the background sound intensity recognition result control the mobile terminal in the hands-free mode and the non-hands-free mould Switched between formula.
4. a kind of intelligent control method of mobile terminal, it is characterised in that methods described includes:
Receive the voice messaging of user input;
Extract the voiceprint of the voice content and the voice messaging in the voice messaging;
When the voice content and the voiceprint meet pre-conditioned, associative operation is performed;
Also include:
The voice messaging of the user according to communication process reaches the voice strength information of the first microphone and the second microphone, Calculate the distance of the user and the mobile terminal;
Recognize the power of user speech information described in the communication process and generate voice intensity recognition result;
The voice messaging of user produces certain pressure sensor state according to the communication process for receiving;
According to the distance, the voice intensity recognition result and the pressure sensor state control the mobile terminal exempting from Carrying and switch between pattern and non-hands-free mode, the status information can characterize the angular relationship of user and mobile terminal.
5. method according to claim 4, it is characterised in that methods described also includes:
The voice messaging of user input is analyzed, the standard vocal print feature of the user is obtained;
The voiceprint meet it is pre-conditioned including:The voiceprint meets the standard vocal print feature.
6. method according to claim 4, it is characterised in that methods described also includes:
Extract background sound in the voice messaging of user described in the communication process, and power to the background sound is carried out Identification generation background sound intensity recognition result;
It is described that the mobile terminal is controlled in hands-free mode and non-hands-free according to the distance and the voice intensity recognition result Switching includes between pattern:
According to the distance, the voice intensity recognition result and the background sound intensity recognition result control the mobile terminal Switch between the hands-free mode and the non-hands-free mode.
CN201210034244.2A 2012-02-15 2012-02-15 A kind of mobile terminal and its intelligent control method CN103259908B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210034244.2A CN103259908B (en) 2012-02-15 2012-02-15 A kind of mobile terminal and its intelligent control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210034244.2A CN103259908B (en) 2012-02-15 2012-02-15 A kind of mobile terminal and its intelligent control method

Publications (2)

Publication Number Publication Date
CN103259908A CN103259908A (en) 2013-08-21
CN103259908B true CN103259908B (en) 2017-06-27

Family

ID=48963589

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210034244.2A CN103259908B (en) 2012-02-15 2012-02-15 A kind of mobile terminal and its intelligent control method

Country Status (1)

Country Link
CN (1) CN103259908B (en)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103051781A (en) * 2012-12-07 2013-04-17 百度在线网络技术(北京)有限公司 Method for controlling backstage through voice and mobile terminal
CN104427125A (en) * 2013-09-10 2015-03-18 中兴通讯股份有限公司 Method and mobile terminal for answering call
CN103888604A (en) * 2014-03-10 2014-06-25 深圳市金立通信设备有限公司 Method for switching application modes of terminal, and terminal
CN105321514A (en) * 2014-05-28 2016-02-10 西安中兴新软件有限责任公司 Alarm method and terminal
CN105491216A (en) * 2014-09-19 2016-04-13 中兴通讯股份有限公司 Incoming call processing method and device, and terminal
CN105516439A (en) * 2014-09-23 2016-04-20 中兴通讯股份有限公司 Telephone answering method, telephone hanging up method, and terminal
CN104320529A (en) * 2014-11-10 2015-01-28 京东方科技集团股份有限公司 Information receiving processing method and voice communication device
CN104580699B (en) * 2014-12-15 2017-06-30 广东欧珀移动通信有限公司 Acoustic control intelligent terminal method and device when a kind of standby
CN104660810A (en) * 2015-02-06 2015-05-27 中国科学院数据与通信保护研究教育中心 Telephone answering control method
CN104667530B (en) * 2015-02-10 2018-02-06 深圳分布科技有限公司 A kind of mobile social intelligence toy system and application method
CN104820798A (en) * 2015-04-24 2015-08-05 成都腾悦科技有限公司 A novel voice and face recognition system for a computer
CN104994301B (en) * 2015-07-20 2018-12-07 魅族科技(中国)有限公司 A kind of photographic method and terminal
CN105100917A (en) * 2015-08-27 2015-11-25 广东欧珀移动通信有限公司 Multimedia content playing control method and terminal device
CN105159492B (en) * 2015-08-27 2019-03-15 Oppo广东移动通信有限公司 A kind of music control method and terminal device
CN106060235A (en) * 2016-05-05 2016-10-26 广东小天才科技有限公司 Startup/shutdown control method and device applied to mobile device and mobile device
CN106057198B (en) * 2016-05-27 2019-08-16 北京云知声信息技术有限公司 A kind of method and apparatus controlling intelligent transportation tool
CN110415711A (en) * 2018-04-28 2019-11-05 中兴通讯股份有限公司 The state identification method and electronic equipment of a kind of electronic equipment
CN108922525B (en) * 2018-06-19 2020-05-12 Oppo广东移动通信有限公司 Voice processing method, device, storage medium and electronic equipment
WO2020000427A1 (en) * 2018-06-29 2020-01-02 华为技术有限公司 Voice control method, wearable apparatus, and terminal

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1852335A (en) * 2005-04-22 2006-10-25 英华达(上海)电子有限公司 Voice automatic processing method of foreign communication event for mobile phone
CN101441869A (en) * 2007-11-21 2009-05-27 联想(北京)有限公司 Method and terminal for speech recognition of terminal user identification
CN101510425A (en) * 2008-02-15 2009-08-19 株式会社东芝 Voice recognition apparatus and method for performing voice recognition
CN101668085A (en) * 2009-09-16 2010-03-10 宇龙计算机通信科技(深圳)有限公司 Method for regulating voice output of mobile terminal and mobile terminal
CN101715018A (en) * 2009-11-03 2010-05-26 沈阳晨讯希姆通科技有限公司 Voice control method of functions of mobile phone
CN101964844A (en) * 2010-09-26 2011-02-02 中兴通讯股份有限公司 Method and device for automatically regulating audio playing in handhold verbal equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1852335A (en) * 2005-04-22 2006-10-25 英华达(上海)电子有限公司 Voice automatic processing method of foreign communication event for mobile phone
CN101441869A (en) * 2007-11-21 2009-05-27 联想(北京)有限公司 Method and terminal for speech recognition of terminal user identification
CN101510425A (en) * 2008-02-15 2009-08-19 株式会社东芝 Voice recognition apparatus and method for performing voice recognition
CN101668085A (en) * 2009-09-16 2010-03-10 宇龙计算机通信科技(深圳)有限公司 Method for regulating voice output of mobile terminal and mobile terminal
CN101715018A (en) * 2009-11-03 2010-05-26 沈阳晨讯希姆通科技有限公司 Voice control method of functions of mobile phone
CN101964844A (en) * 2010-09-26 2011-02-02 中兴通讯股份有限公司 Method and device for automatically regulating audio playing in handhold verbal equipment

Also Published As

Publication number Publication date
CN103259908A (en) 2013-08-21

Similar Documents

Publication Publication Date Title
CN103730116B (en) Intelligent watch realizes the system and method that intelligent home device controls
CN105009204B (en) Speech recognition power management
JP5772448B2 (en) Speech analysis system and speech analysis apparatus
CN105653226B (en) Information display method and device
CN103971680B (en) A kind of method, apparatus of speech recognition
ES2775799T3 (en) Method and apparatus for multisensory speech enhancement on a mobile device
EP1517298B1 (en) Speaking period detection based on electromyography
US9769296B2 (en) Techniques for voice controlling bluetooth headset
JP4809454B2 (en) Circuit activation method and circuit activation apparatus by speech estimation
JP2007501444A (en) Speech recognition method using signal-to-noise ratio
CN103456305B (en) Terminal and the method for speech processing based on multiple sound collection unit
CN107895578A (en) Voice interactive method and device
CN104811552B (en) A kind of shortcut function starts method, apparatus and verbal system
TWI590228B (en) Voice control system, electronic device having the same, and voice control method
JP5529844B2 (en) Gesture multi-dimensional analysis system and method
CN103248743B (en) Vehicle-mounted hands-free calling device and method thereof
CN104184872A (en) Crank call preventing mobile phone achieving method based on conversation content
TW577043B (en) Voice recognition system using implicit speaker adaptation
US7328159B2 (en) Interactive speech recognition apparatus and method with conditioned voice prompts
WO2001033550A1 (en) Speech parameter compression
FR2794322A1 (en) Mobile telephone local noise suppression method, using voice-processing algorithm, determining suppression parameters before any voice signals are exchanged between called and calling parties
CN104104800A (en) Method for adjusting volume output of mobile terminal according to environment noises and mobile terminal
CN1391210A (en) Method for training or adapting to phonetic recognizer
CN101370195A (en) Method and device for implementing emotion regulation in mobile terminal
US20040162722A1 (en) Speech quality indication

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
GR01 Patent grant