CN103886861B - A kind of method of control electronics and electronic equipment - Google Patents
A kind of method of control electronics and electronic equipment Download PDFInfo
- Publication number
- CN103886861B CN103886861B CN201210557125.5A CN201210557125A CN103886861B CN 103886861 B CN103886861 B CN 103886861B CN 201210557125 A CN201210557125 A CN 201210557125A CN 103886861 B CN103886861 B CN 103886861B
- Authority
- CN
- China
- Prior art keywords
- electronic equipment
- speech recognition
- voice
- flow
- sound
- 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.)
- Active
Links
Landscapes
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a kind of method of control electronics and electronic equipment.The method is applied to an electronic equipment, and described electronic equipment includes a speech recognition engine, and methods described includes:When described speech recognition engine is closed, detect whether described electronic equipment receives the first voice air-flow, wherein, described first voice air-flow sends produced air-flow during the first sound for user;When described electronic equipment receives described first voice air-flow, generate a control instruction;Execute described control instruction, control the state of described speech recognition engine to be adjusted to opening so that described electronic equipment can carry out speech recognition from described closed mode.
Description
Technical field
The present invention relates to electronic technology field, more particularly, to a kind of method of control electronics and electronic equipment.
Background technology
With the development of computer technology, electronic equipment more come intelligent, user can by electronic equipment, such as, intelligence
Mobile phone, panel computer, intelligent television, notebook computer, regard an intelligent robot as, can be by carrying out voice friendship with it
Mutually, some information are obtained.Such as, user " inquires " the nearest restaurant of electronic equipment at which;For another example, user " inquires " electronics
From place A to place B how to get to equipment.
At present, when user needs interactive voice, interactive voice software can be opened, then speak against electronic equipment, electricity
Sub- equipment passes through the speech recognition engine being disposed thereon(Local client)By the phonetic entry of user, such as " nearest chaffy dish
Shop is at which?", be converted to text message, and send that information to cloud server, cloud server can be according to above-mentioned text envelope
Breath, is calculated by a series of search, finds the result mated the most with text message, such as " XX chafing dish restaurant, 500 meters of front ",
And this result is sent back to local client in the form of text, in local client, the text message of the above results is changed Chinese idiom
Sound information output is to user so that user can mention " answer " of electronic equipment.
During present inventor's technical scheme in realizing the embodiment of the present application, find at least to deposit in prior art
In following technical problem:
Because when carrying out interactive voice or with voice, electronic equipment being controlled, speech recognition engine is constantly in out
Open state, so, no matter mike receives any sound, all can be identified mating by speech recognition engine, so, lead
Cause the input of some invalid voice to be also processed, and then there is the big technical problem of speech recognition engine power consumption.
Content of the invention
The present invention provides a kind of method of control electronics and electronic equipment, in order to solve language present in prior art
Sound identifies the big technical problem of engine power consumption.
On the one hand, the present invention passes through an embodiment of the application, provides a kind of method of control electronics, is applied to
One electronic equipment, described electronic equipment includes a speech recognition engine, and methods described includes:When described speech recognition engine is in
During closed mode, detect whether described electronic equipment receives the first voice air-flow, wherein, described first voice air-flow is user
Send produced air-flow during the first sound;When described electronic equipment receives described first voice air-flow, generate a control
Instruction;Execute described control instruction, control the state of described speech recognition engine to be adjusted to opening from described closed mode,
Described electronic equipment is enable to carry out speech recognition.
Optionally, described electronic equipment comprises a vibrating sensor;Whether the described electronic equipment of described detection receives the
One voice air-flow is specially:By described vibrating sensor, detect whether there is the vibration being caused by described first voice air-flow.
Optionally, described generation one control instruction specifically includes:Described first sound is converted to the first acoustical signal;Sentence
It is pre-conditioned whether described first acoustical signal that breaks meets first;When described first acoustical signal, to meet described first pre-conditioned
When, generate described control instruction.
Optionally, described control described speech recognition engine state from described closed mode be adjusted to opening it
Afterwards, methods described also includes:By described electronic equipment access network;Speech recognition is carried out to described first acoustical signal.
Optionally, described speech recognition is carried out to described first acoustical signal, specifically include:By described first acoustical signal
Be converted to the first text message, and described first text message is sent to cloud server;Receive by described cloud server
The second text message sending, wherein, described second text message is that described cloud server is based on described first text message
The recognition result being obtained;Described second text message is converted to second sound signal, and is exported by voice output
Described second sound signal.
On the other hand, the present invention passes through another embodiment offer a kind of electronic equipment of the application, including:Circuit board;Language
Sound identifies engine, is arranged on described circuit board;Detection module, for when described speech recognition engine is closed,
Detect whether described electronic equipment receives the first voice air-flow, wherein, described first voice air-flow sends the first sound for user
Produced air-flow during sound;Control module, is arranged on described circuit board, is connected with described speech recognition engine, for working as
When stating electronic equipment and receiving described first voice air-flow, generate a control instruction;Execute described control instruction, control institute's predicate
Sound identifies that the state of engine is adjusted to opening so that described electronic equipment can carry out voice knowledge from described closed mode
Not.
Optionally, described control module specifically includes:Signal generating unit, for receiving described first when described electronic equipment
During voice air-flow, generate a control instruction;Control unit, for executing described control instruction, controls described speech recognition engine
State be adjusted to opening so that described electronic equipment can carry out speech recognition from described closed mode.
Optionally, described detection module is specially a vibrating sensor, for by described vibrating sensor, detecting whether
There is the vibration being caused by described first voice air-flow.
Optionally, described electronic equipment also includes a voice collection device, for gathering described first sound;Described vibration
Sensor is specifically located in described voice collection device.
Optionally, described electronic equipment also includes:One spray guard, gathers described first sound for voice collection device
When, filter described first voice air-flow;Described vibrating sensor is specifically located on described spray guard.
Optionally, described signal generating unit specifically includes:First converting unit, for being converted to first by described first sound
Acoustical signal;Judging unit, pre-conditioned for judging whether described first acoustical signal meets first;Generate subelement, use
In when described first acoustical signal meet described first pre-conditioned when, generate described control instruction.
Optionally, described electronic equipment also includes:Networking unit, for by described electronic equipment access network;Identification is single
Unit, for carrying out speech recognition to described first acoustical signal.
Optionally, described recognition unit specifically includes:Second converting unit, for being converted to described first acoustical signal
First text message;Transmitting element, for being sent to cloud server by described first text message;Receiving unit, is used for connecing
Receive the second text message being sent by described cloud server, wherein, described second text message is described cloud server base
The recognition result being obtained in described second text message;3rd converting unit, for being converted to described second text message
Second sound signal;Output unit, for exporting described second sound signal by voice output.
The one or more technical schemes providing in the embodiment of the present application, at least have the following technical effect that or advantage:
1st, because when speech recognition engine is closed, whether detection electronic equipment receives the first voice gas
Stream, when electronic equipment receives the first voice air-flow, control voice identifies that the state of engine is adjusted to open from closed mode
State is so that electronic equipment can carry out speech recognition, then, speech recognition engine can produce according to the phonetic entry of user
The first voice air-flow open, without power consumption is produced due to the always on of speech recognition engine, also will not be to receiving
All sound all be identified mate, so, efficiently solve speech recognition engine power consumption present in prior art big
Technical problem, and then reduce the power consumption of speech recognition engine, extend the use time of electronic equipment.
2nd, because electronic equipment also includes a spray guard, when user speaks against voice collection device, can filter out
The first voice air-flow that the first sound that user sends is taken out of is so that the first voice air-flow will not directly collide sound collection dress
Put and produce noise, and then make speech recognition engine more accurate to the identification of the first sound, and, because the first sound is miscellaneous
Sound is few so that speech recognition engine amount of calculation when processing to the first sound reduces, and reduces speech recognition engine further
Power consumption.
Brief description
Fig. 1 is the structural representation of electronic equipment in one embodiment of the invention;
Fig. 2 is the method flow diagram of control electronics in one embodiment of the invention;
Fig. 3 is the position relationship schematic diagram of spray guard and voice collection device in one embodiment of the invention.
Specific embodiment
The embodiment of the present application is passed through to provide a kind of method of control electronics and electronic equipment, solves in prior art
The big technical problem of speech recognition engine power consumption existing.
Technical scheme in the embodiment of the present application is to solve the problems, such as that above-mentioned speech recognition engine power consumption is big, totally
Thinking is as follows:
When speech recognition engine is closed, whether detection electronic equipment receives the first voice air-flow, wherein,
First voice air-flow sends produced air-flow during the first sound for user;When electronic equipment receives the first voice air-flow,
Control voice identifies that the state of engine is adjusted to opening so that electronic equipment can carry out speech recognition from closed mode,
Thus without as interactive voice software or speech recognition software once unlatching in prior art, speech recognition engine is also simultaneously
Open, and all sound receiving all are carried out speech recognition match, so, reduce the power consumption of speech recognition engine, prolong
Grow the use time of electronic equipment.
Below by accompanying drawing and technical solution of the present invention is described in detail specific embodiment it should be understood that the present invention
Specific features in embodiment and embodiment are the detailed description to technical solution of the present invention, rather than to the technology of the present invention
The restriction of scheme, in the case of not conflicting, the technical characteristic in the embodiment of the present invention and embodiment can be mutually combined.
On the one hand, the present invention passes through an embodiment of the application, provides a kind of method of control electronics.The method
It is applied to an electronic equipment, such as, smart mobile phone, panel computer, intelligent television, notebook computer;As shown in figure 1, this electronics
Equipment includes circuit board 10, speech recognition engine 20, detection module 30, control module 40, wherein, speech recognition engine 20 and control
Molding block 40 is arranged on circuit boards.
In specific implementation process, detection module 30 is specifically as follows vibrating sensor or baroceptor, also
Can be pneumatic sensor, the application is not specifically limited.
As shown in Fig. 2 the method includes:
S101:When speech recognition engine is closed, whether detection electronic equipment receives the first voice air-flow,
Wherein, the first voice air-flow sends produced air-flow during the first sound for user;
S102:When electronic equipment receives the first voice air-flow, generate a control instruction;
S103:Execution control instruction, control voice identify the state of engine be adjusted to opening from closed mode so that
Electronic equipment can carry out speech recognition.
Below, such scheme is described in detail taking interactive voice as a example.
Incorporated by reference to Fig. 1 and Fig. 2, for example, user wants and electronic equipment, such as smart mobile phone, carries out interactive voice, now,
Speech recognition engine 20 is closed, and then, user speaks against electronic equipment, that is, send the first sound, such as, user
Want to know that Mountain Everest is how high by interactive voice software, then, against electronic equipment, user says that " Mountain Everest has
How high ", now, execute S101, whether detection electronic equipment have received the first voice air-flow, the first voice gas mentioned here
Stream be exactly user when sending the first sound, the air-flow that breathed out by lung, such as, people, during speaking, handss is placed on mouth
Front is it becomes possible to feel the air-flow being formed from the internal gas spraying, that is, voice air-flow mentioned here.
In specific implementation process, when detection module 30 is vibrating sensor, detection module 30 can be arranged on sound
On harvester, then, when user speaks against voice collection device, detection module 30 is just able to detect that user speaks band
The the first voice air-flow coming;Further, as shown in figure 3, a spray guard can also be arranged before voice collection device 301
302, so, user speak the first voice air-flow bringing can be filtered by spray guard 302 so that first sound produce noise relatively
Few, now, detection module 30 is arranged on spray guard 302, and so, the first voice air-flow and the first sound first pass through blowout prevention
Cover 302, then, the first sound passes through and continues to propagate to voice collection device 301, and certainly, detection module 30 can also be arranged
In other positions, as long as being able to detect that the first voice air-flow, the application is not specifically limited.In the present embodiment, examine
Survey module 30 to be arranged on spray guard 302.
So, when detection module 30 is vibrating sensor, S101 can be:By vibrating sensor, detect whether to deposit
In the vibration being caused by the first voice air-flow.That is, detect whether the first voice air-flow by detection module 30
Exist, that is, whether detection user speaks against voice collection device 301.
Then, execute S102, that is,:When electronic equipment receives the first voice air-flow, generate a control instruction.
In specific implementation process, when detection module 30 detects electronic equipment and receives the first voice air-flow, S102 can
Think:First sound is converted to the first acoustical signal;Judge whether the first acoustical signal meets first pre-conditioned;When first
Acoustical signal meet first pre-conditioned when, generate control instruction.
Specifically, when detection module 30 detects electronic equipment and receives the first voice air-flow, voice collection device
301 will receive the first sound, then convert sound into acoustical signal, i.e. the first acoustical signal;Next, electronic equipment
Judge whether the first acoustical signal meets first pre-conditioned, for example, judge whether the first acoustical signal is human voice signal, than
As the first acoustical signal producing when user speaks against voice collection device 301 is exactly human voice signal, that is, meet first pre-
If condition;When user blows against voice collection device 301 although detection module 30 shaking of also can detecting that air-flow causes
Dynamic, but now the first acoustical signal is not just human voice signal, that is, be unsatisfactory for first pre-conditioned.It is, of course, also possible to judge
Whether one acoustical signal carries voice messaging, the first acoustical signal producing when user speaks against voice collection device 301
Exactly carry the signal of voice messaging, that is, meet first pre-conditioned;When user blows against voice collection device 301, though
So detection module 30 also can detect the vibration that air-flow causes, but to be the first acoustical signal just do not have any voice letter for this
Breath, that is, be unsatisfactory for first pre-conditioned.
In actual applications, voice activity detection can be passed through(VAD, Voice activity detection)Algorithm or
Person's voice activity detection algorithm is judging whether the first acoustical signal carries voice messaging, it is, of course, also possible to pass through other algorithms
To judge whether the first acoustical signal carries voice messaging, the application is not specifically limited.
Finally, when judge first acoustical signal meet first pre-conditioned when, generate control instruction, this control instruction be use
Identify the instruction that engine 20 is opened in control voice.
Next, after above-mentioned control instruction is generated by S102, entering S103, that is,:Execution control instruction, control voice
The state of identification engine is adjusted to opening so that electronic equipment can carry out speech recognition from closed mode.
Further, by S103 control voice identify engine 20 state from closed mode be adjusted to opening it
Afterwards, the method also includes:By electronic equipment access network;Speech recognition is carried out to the first acoustical signal.
In specific implementation process, the process that the first acoustical signal is carried out with speech recognition can include:By the first sound
Signal is converted to the first text message, and the first text message is sent to cloud server;Receive and sent by cloud server
The second text message, wherein, the recognition result that the second text message is obtained based on the first text message by cloud server;
Second text message is converted to second sound signal, and second sound signal is exported by voice output.
Specifically, first after speech recognition engine 20 unlatching, first, voice collection device 301 being collected
Acoustical signal changes the first text message, will become textual form by the Content Transformation that comprises of the first acoustical signal;Then, voice is known
This first text message can be sent to cloud server by other engine 20, allow it to be obtained by searching algorithm according to the first text message
Obtain the recognition result mating the most with the first text message.Such as, the first text message is " Mountain Everest is how high ", connects down
Come, cloud server can search for the recognition result mating the most with the first text message, i.e. pearl Mu Lang in the data base of itself
8844.43 meters of agate peak height.Next, this result is converted to the second text message by cloud server, i.e. " Qomolangma peak height
8844.43 meters ", then the second text message is sent to electronic equipment, speech recognition engine 20 is receiving this second text
After information, convert thereof into voice signal, i.e. second sound signal, and exported by voice output that is to say, that allowing electricity
Sub- equipment " reading " " 8844.43 meters of Qomolangma peak height ".
So far, user and the interactive voice process of electronic equipment just finish.
Further, after the second text message is converted into second sound information by speech recognition engine 20, when one section
Interior, such as 1 minute, 3 minutes, 5 minutes, detection module 30 can't detect spray guard 302 and vibrates or can't detect voice gas
Stream input, then, speech recognition engine 20 is automatically switched off.
Certainly, in actual applications, such scheme can be also used for Voice command electronic equipment, and specific implementation process will
It is described in detail in the following embodiments, this is no longer going to repeat them.
The method to introduce the control electronics in the present invention below by way of several specific embodiments, following enforcement
Example mainly describes the several possible application scenarios of the method for described control electronics.It should be noted that in the present invention
Embodiment be served only for explain the present invention, and cannot be used for limit the present invention.The embodiment that all meet inventive concept all exists
Within protection scope of the present invention, those skilled in the art know how to be deformed according to the thought of the present invention naturally.
Embodiment one:
Electronic equipment is smart mobile phone.When user wants place B in place A, but how to get to do not know, then user
Open mike, now, user says " place B is how to get to " against electronic equipment, i.e. the first sound, the first sound bring first
Voice air-flow collides spray guard 302, causes the vibration of spray guard 302, now, is arranged on the detection module 30 on spray guard 302,
I.e. vibrating sensor, detects above-mentioned vibration, and afterwards, the first sound is carried out being converted to the first acoustical signal by mike, then,
Judge whether the first acoustical signal carries voice messaging, when the first acoustical signal carries voice messaging, generate a control instruction,
Control voice identification engine 20 is switched to opening from closed mode.Then, speech recognition engine 20 is to the first acoustical signal
Carry out speech recognition, be converted into the first text message, meanwhile, the position controlling GPS current to electronic equipment positions,
Obtain primary importance information, then, speech recognition engine 20 is connected to networking, by the first text message and primary importance information one
It is sent to cloud server together;When cloud server receives the first text message that speech recognition engine 20 sends and first
After confidence breath, by series of algorithms, calculate from place A to the route of place B, and convert this information into the second text envelope
Breath, next, the second text message is sent to speech recognition engine 20 by cloud server;When speech recognition engine 20 receives
After two text messages, then it is converted into second sound signal, and exported by speaker so that user can hear electronics
Equipment " saying " is from place A to the route of place B.Further, when the second text is converted to the rising tone by speech recognition engine 20
Afterwards, within 1 minute, or 2 minutes, detection module 30 can't detect spray guard 302 and vibrates message number, then, voice is known
Other engine 20 is automatically switched off.
Embodiment two:
Electronic equipment is notebook computer.When user wants to control notebook computer to play music by voice, first,
During user uses notebook computer, detection module 30, such as baroceptor is constantly in detection state.When user is to pen
Remember that the mike on this computer says " broadcasting music ", that is, during the first sound, be arranged on baroceptor on mike with regard to energy
Now mike front region internal gas pressure is enough detected to raise, now, the first sound is converted to the first acoustical signal by mike,
Then, judge whether the first acoustical signal is human voice signal, when the first acoustical signal is human voice signal, generate control instruction,
Control voice identification engine 20 is adjusted to opening from closed mode;Next, speech recognition engine 20 is believed to the first sound
Number carry out speech recognition, that is, obtain the voice messaging of " the broadcasting music " entrained by the first acoustical signal, then, be stored in pen
Remember in the preset instructions list in this computer and make a look up, see in this list whether include the preset instructions of " broadcasting music ", when
After finding this preset instructions, electronic equipment just responds this instruction, opens music player, commences play out music.
From the above description, it can be seen that because when speech recognition engine 20 is closed, whether detection electronic equipment
Receive the first voice air-flow, when electronic equipment receives the first voice air-flow, control voice identify engine 20 state from
Closed mode is adjusted to opening so that electronic equipment can carry out speech recognition, then, user is carrying out interactive voice
When, speech recognition engine 20 can be opened according to the first voice air-flow that the phonetic entry of user produces, without due to voice
Interactive software always on and persistently open networking, another kind of situation, when user is when carrying out Voice command electronic equipment, language
Sound identification engine 20 can be opened according to the first voice air-flow, without being always maintained at opening, any sound all would not be entered
Row identification, so, reduce the power consumption of speech recognition engine 20, extend the use time of electronic equipment;Further, due to electricity
Sub- equipment also includes a spray guard 302, when user speaks against voice collection device 301, can filter out what user sent
The first voice air-flow that first sound is taken out of is so that the first voice air-flow will not directly collide voice collection device 301 and produce
Raw noise, and then make speech recognition engine 20 more accurate to the identification of the first sound, and, due to the first sound noise
Less so that speech recognition engine amount of calculation when processing to the first sound reduces, reduce speech recognition engine further
Power consumption.
On the other hand, based on same inventive concept, the present invention provides a kind of electronics to set by another embodiment of the application
Standby, as shown in figure 1, including:Circuit board 10;Speech recognition engine 20, setting is on the circuit board 10;Detection module 30, for working as
When speech recognition engine 20 is closed, whether detection electronic equipment receives the first voice air-flow, wherein, the first voice
Air-flow sends produced air-flow during the first sound for user;Control module 40, setting on the circuit board 10, is drawn with speech recognition
Hold up 20 connections, for when electronic equipment receives the first voice air-flow, generating a control instruction;Execution control instruction, controls
The state of speech recognition engine 20 is adjusted to opening so that electronic equipment can carry out speech recognition from closed mode.
Further, control module 40 specifically includes:Signal generating unit, for receiving the first voice air-flow when electronic equipment
When, generate a control instruction;Control unit, for executing control instruction, control voice identifies the state of engine 20 from closing shape
State is adjusted to opening so that electronic equipment can carry out speech recognition.
Further, detection module 30 be specially a vibrating sensor, for by vibrating sensor, detect whether exist by
The vibration that first voice air-flow causes.
In specific implementation process, detection module 30 can also be specifically baroceptor, pneumatic sensor, and the application is not
It is specifically limited.
Further, electronic equipment also includes a voice collection device 301, for gathering the first sound;Vibrating sensing utensil
Body is arranged in voice collection device 301.
Further, as shown in figure 3, electronic equipment also includes:One spray guard 302, for voice collection device 301 collection the
During one sound, filter the first voice air-flow;Vibrating sensor is specifically located on spray guard 302.
Further, signal generating unit specifically includes:First converting unit, for being converted to the first sound letter by the first sound
Number;Judging unit, pre-conditioned for judging whether the first acoustical signal meets first;Generate subelement, for when the first sound
Message number meet first pre-conditioned when, generate control instruction.
Further, electronic equipment also includes:Networking unit, for by electronic equipment access network;Recognition unit, for right
First acoustical signal carries out speech recognition.
Further, recognition unit specifically includes:Second converting unit, for being converted to the first text by the first acoustical signal
Information;Transmitting element, for being sent to cloud server by the first text message;Receiving unit, for receiving by cloud service
The second text message that device sends, wherein, the knowledge that the second text message is obtained based on the second text message by cloud server
Other result;3rd converting unit, for being converted to second sound signal by the second text message;Output unit, for by sound
Sound output device exports second sound signal.
As described above, above-mentioned electronic equipment is used for the method realizing above-mentioned control electronics, so, this electronics
The work process of equipment is consistent with one or more embodiments of said method, and here does not just repeat one by one.
Technical scheme in above-mentioned the embodiment of the present application, at least has the following technical effect that or advantage:
1st, because when speech recognition engine is closed, whether detection electronic equipment receives the first voice gas
Stream, when electronic equipment receives the first voice air-flow, control voice identifies that the state of engine is adjusted to open from closed mode
State is so that electronic equipment can carry out speech recognition, then, speech recognition engine can produce according to the phonetic entry of user
The first voice air-flow open, without power consumption is produced due to the always on of speech recognition engine, also will not be to receiving
All sound all be identified mate, so, efficiently solve speech recognition engine power consumption present in prior art big
Technical problem, and then reduce the power consumption of speech recognition engine, extend the use time of electronic equipment.
2nd, because electronic equipment also includes a spray guard, when user speaks against voice collection device, can filter out
The first voice air-flow that the first sound that user sends is taken out of is so that the first voice air-flow will not directly collide sound collection dress
Put and produce noise, and then make speech recognition engine more accurate to the identification of the first sound, and, because the first sound is miscellaneous
Sound is few so that speech recognition engine amount of calculation when processing to the first sound reduces, and reduces speech recognition engine further
Power consumption.Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or the reality combining software and hardware aspect
Apply the form of example.And, the present invention can be using in one or more computers wherein including computer usable program code
Usable storage medium(Including but not limited to disk memory, CD-ROM, optical memory etc.)The computer program of upper enforcement produces
The form of product.
The present invention is with reference to method according to embodiments of the present invention, equipment(System), and computer program flow process
Figure and/or block diagram are describing.It should be understood that can be by each stream in computer program instructions flowchart and/or block diagram
Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor instructing general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device is to produce
A raw machine is so that produced for reality by the instruction of computer or the computing device of other programmable data processing device
The device of the function of specifying in present one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing device with spy
Determine in the computer-readable memory that mode works so that the instruction generation inclusion being stored in this computer-readable memory refers to
Make the manufacture of device, this command device realize in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The function of specifying in multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing device so that counting
On calculation machine or other programmable devices, execution series of operation steps to be to produce computer implemented process, thus in computer or
On other programmable devices, the instruction of execution is provided for realizing in one flow process of flow chart or multiple flow process and/or block diagram one
The step of the function of specifying in individual square frame or multiple square frame.
Obviously, those skilled in the art can carry out the various changes and modification essence without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprise these changes and modification.
Claims (13)
1. a kind of method of control electronics, is applied to an electronic equipment it is characterised in that described electronic equipment includes a language
Sound identifies engine, and methods described includes:
When described speech recognition engine is closed, detect whether described electronic equipment receives the first voice air-flow,
Wherein, described first voice air-flow sends produced air-flow during the first sound for user;
When described electronic equipment receives described first voice air-flow, generate a control instruction;
Execute described control instruction, control the state of described speech recognition engine to be adjusted to opening from described closed mode,
Described electronic equipment is enable to carry out speech recognition.
2. the method for claim 1 is it is characterised in that described electronic equipment comprises a vibrating sensor;
Whether the described electronic equipment of described detection receives the first voice air-flow is specially:By described vibrating sensor, detect
With the presence or absence of the vibration being caused by described first voice air-flow.
3. method as claimed in claim 2 is it is characterised in that described generation one control instruction specifically includes:
Described first sound is converted to the first acoustical signal;
Judge whether described first acoustical signal meets first pre-conditioned;
When described first acoustical signal meet described first pre-conditioned when, generate described control instruction.
4. method as claimed in claim 3 it is characterised in that described control described speech recognition engine state from described
After closed mode is adjusted to opening, methods described also includes:
By described electronic equipment access network;
Speech recognition is carried out to described first acoustical signal.
5. method as claimed in claim 4, it is characterised in that described carry out speech recognition to described first acoustical signal, has
Body includes:
Described first acoustical signal is converted to the first text message, and described first text message is sent to cloud service
Device;
Receive the second text message being sent by described cloud server, wherein, described second text message is described high in the clouds clothes
The recognition result that business device is obtained based on described first text message;
Described second text message is converted to second sound signal, and described rising tone message is exported by voice output
Number.
6. a kind of electronic equipment is it is characterised in that include:
Circuit board;
Speech recognition engine, is arranged on described circuit board;
Detection module, for when described speech recognition engine is closed, detecting whether described electronic equipment receives
First voice air-flow, wherein, described first voice air-flow sends produced air-flow during the first sound for user;
Control module, is arranged on described circuit board, is connected with described speech recognition engine, for receiving when described electronic equipment
During to described first voice air-flow, generate a control instruction;Execute described control instruction, control the shape of described speech recognition engine
State is adjusted to opening so that described electronic equipment can carry out speech recognition from described closed mode.
7. electronic equipment as claimed in claim 6 is it is characterised in that described control module specifically includes:
Signal generating unit, for when described electronic equipment receives described first voice air-flow, generating a control instruction;
Control unit, for executing described control instruction, controls the state of described speech recognition engine to adjust from described closed mode
Whole to opening so that described electronic equipment can carry out speech recognition.
8. electronic equipment as claimed in claim 7, it is characterised in that described detection module is specially a vibrating sensor, is used
In by described vibrating sensor, detect whether there is the vibration being caused by described first voice air-flow.
9. electronic equipment as claimed in claim 8 is it is characterised in that described electronic equipment also includes a voice collection device,
For gathering described first sound;
Described vibrating sensor is specifically located in described voice collection device.
10. electronic equipment as claimed in claim 8 is it is characterised in that described electronic equipment also includes:One spray guard, is used for
When voice collection device gathers described first sound, filter described first voice air-flow;Described vibrating sensor is specifically located at
On described spray guard.
11. electronic equipments as claimed in claim 8 are it is characterised in that described signal generating unit specifically includes:
First converting unit, for being converted to the first acoustical signal by described first sound;
Judging unit, pre-conditioned for judging whether described first acoustical signal meets first;
Generate subelement, for when described first acoustical signal meet described first pre-conditioned when, generate described control instruction.
12. electronic equipments as claimed in claim 11 are it is characterised in that described electronic equipment also includes:
Networking unit, for by described electronic equipment access network;
Recognition unit, for carrying out speech recognition to described first acoustical signal.
13. electronic equipments as claimed in claim 12 are it is characterised in that described recognition unit specifically includes:
Second converting unit, for being converted to the first text message by described first acoustical signal;
Transmitting element, for being sent to cloud server by described first text message;
Receiving unit, for receiving the second text message being sent by described cloud server, wherein, described second text message
The recognition result being obtained based on described second text message by described cloud server;
3rd converting unit, for being converted to second sound signal by described second text message;
Output unit, for exporting described second sound signal by voice output.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210557125.5A CN103886861B (en) | 2012-12-20 | 2012-12-20 | A kind of method of control electronics and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210557125.5A CN103886861B (en) | 2012-12-20 | 2012-12-20 | A kind of method of control electronics and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103886861A CN103886861A (en) | 2014-06-25 |
CN103886861B true CN103886861B (en) | 2017-03-01 |
Family
ID=50955719
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210557125.5A Active CN103886861B (en) | 2012-12-20 | 2012-12-20 | A kind of method of control electronics and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103886861B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102015222956A1 (en) * | 2015-11-20 | 2017-05-24 | Robert Bosch Gmbh | A method for operating a server system and for operating a recording device for recording a voice command, server system, recording device and voice dialogue system |
CN105609118B (en) * | 2015-12-30 | 2020-02-07 | 生迪智慧科技有限公司 | Voice detection method and device |
CN107533415B (en) * | 2015-12-31 | 2020-09-11 | 华为技术有限公司 | Voiceprint detection method and device |
CN105549983A (en) * | 2016-01-20 | 2016-05-04 | 上海斐讯数据通信技术有限公司 | Intelligent terminal and cleansing method and device of background application of intelligent terminal |
CN107293298B (en) * | 2016-04-05 | 2021-02-19 | 富泰华工业(深圳)有限公司 | Voice control system and method |
CN107280122A (en) * | 2016-04-05 | 2017-10-24 | 富泰华工业(深圳)有限公司 | Smart cap |
JP6531776B2 (en) * | 2017-04-25 | 2019-06-19 | トヨタ自動車株式会社 | Speech dialogue system and speech dialogue method |
CN107249116B (en) * | 2017-08-09 | 2020-05-05 | 成都全云科技有限公司 | Noise echo eliminating device based on video conference |
CN107371144B (en) * | 2017-08-11 | 2021-02-02 | 深圳传音通讯有限公司 | Method and device for intelligently sending information |
CN107993650A (en) * | 2017-11-30 | 2018-05-04 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
KR102638946B1 (en) * | 2018-06-25 | 2024-02-22 | 소니그룹주식회사 | Information processing device and information processing method, and information processing system |
CN109686158A (en) * | 2019-01-07 | 2019-04-26 | 九江学院 | A kind of method of accountant management system ability culture simulation and training |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101529363A (en) * | 2006-10-18 | 2009-09-09 | 皇家飞利浦电子股份有限公司 | Electronic system control using surface interaction |
CN102324241A (en) * | 2011-05-04 | 2012-01-18 | 鸿富锦精密工业(深圳)有限公司 | Electronic device with voice-controlling function and voice-controlling method |
CN102710867A (en) * | 2012-06-20 | 2012-10-03 | 北京三星通信技术研究有限公司 | Control device and method of mobile terminal |
CN102750087A (en) * | 2012-05-31 | 2012-10-24 | 华为终端有限公司 | Method, device and terminal device for controlling speech recognition function |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4779000B2 (en) * | 2008-09-26 | 2011-09-21 | 株式会社日立製作所 | Device control device by voice recognition |
-
2012
- 2012-12-20 CN CN201210557125.5A patent/CN103886861B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101529363A (en) * | 2006-10-18 | 2009-09-09 | 皇家飞利浦电子股份有限公司 | Electronic system control using surface interaction |
CN102324241A (en) * | 2011-05-04 | 2012-01-18 | 鸿富锦精密工业(深圳)有限公司 | Electronic device with voice-controlling function and voice-controlling method |
CN102750087A (en) * | 2012-05-31 | 2012-10-24 | 华为终端有限公司 | Method, device and terminal device for controlling speech recognition function |
CN102710867A (en) * | 2012-06-20 | 2012-10-03 | 北京三星通信技术研究有限公司 | Control device and method of mobile terminal |
Also Published As
Publication number | Publication date |
---|---|
CN103886861A (en) | 2014-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103886861B (en) | A kind of method of control electronics and electronic equipment | |
CN108962255B (en) | Emotion recognition method, emotion recognition device, server and storage medium for voice conversation | |
US11289087B2 (en) | Context-based device arbitration | |
CN109087669B (en) | Audio similarity detection method and device, storage medium and computer equipment | |
CN105009204B (en) | Speech recognition power management | |
CN109346076A (en) | Interactive voice, method of speech processing, device and system | |
CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
CN108665895A (en) | Methods, devices and systems for handling information | |
CN106782504A (en) | Audio recognition method and device | |
CN107799126A (en) | Sound end detecting method and device based on Supervised machine learning | |
CN110503969A (en) | A kind of audio data processing method, device and storage medium | |
CN107767869A (en) | Method and apparatus for providing voice service | |
CN107004424A (en) | Noise reduces the method, apparatus and system with speech enhan-cement | |
WO2020253128A1 (en) | Voice recognition-based communication service method, apparatus, computer device, and storage medium | |
US10565862B2 (en) | Methods and systems for ambient system control | |
US20230386461A1 (en) | Voice user interface using non-linguistic input | |
CN110097890A (en) | A kind of method of speech processing, device and the device for speech processes | |
CN109935226A (en) | A kind of far field speech recognition enhancing system and method based on deep neural network | |
CN110097875A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
CN111883135A (en) | Voice transcription method and device and electronic equipment | |
CN107277276A (en) | One kind possesses voice control function smart mobile phone | |
CN110111776A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
KR101995443B1 (en) | Method for verifying speaker and system for recognizing speech | |
CN104952446A (en) | Digital building presentation system based on voice interaction | |
CN110176242A (en) | A kind of recognition methods of tone color, device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |