CN207217112U - A kind of intelligent sound equipment - Google Patents
A kind of intelligent sound equipment Download PDFInfo
- Publication number
- CN207217112U CN207217112U CN201721146325.6U CN201721146325U CN207217112U CN 207217112 U CN207217112 U CN 207217112U CN 201721146325 U CN201721146325 U CN 201721146325U CN 207217112 U CN207217112 U CN 207217112U
- Authority
- CN
- China
- Prior art keywords
- signal
- head
- sound
- movable
- sound equipment
- 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
- Circuit For Audible Band Transducer (AREA)
Abstract
The utility model embodiment discloses a kind of intelligent sound equipment in fact, including for picking up the stationary tone head of voice signal and loudspeaker for playing audio signal, it is at least one can be with the intelligent sound equipment in the movable sound head for physically being combined or being departed from, connect the audio treatment unit of the stationary tone head and the movable sound head, connect the voice recognition unit of the audio treatment unit, with the main control unit for connecting the voice recognition unit, the first communication unit being arranged between the movable sound head and the audio treatment unit, and, the state detection circuit for being used to detect the movable sound head and whether being in instruction input state being arranged between first communication unit and the main control unit.The utility model embodiment can carry out closely pickup by movable sound head, can effectively ensure that the accuracy of speech recognition, and the equipment operation is simple, using being also convenient for.
Description
Technical field
The utility model embodiment is related to voice control technology field, more particularly to a kind of intelligent sound equipment.
Background technology
Intelligent sound equipment is a kind of equipment that can carry out man machine language's interaction, including the production of smart mobile phone, smart home
Product, intelligent vehicle-carried equipment, Intelligent worn device etc..For example, the intelligent sound equipment in smart home product, can be by pickup
Voice signal resolves to control instruction, to realize the control to smart machines such as television set, air-conditionings.
Chinese patent CN206353839U, a kind of TV speech control system is disclosed, include the battle array of pickup voice signal
Row microphone, the audio processing chip in localization of sound source direction and the master controller for voice signal to be resolved to control instruction.
Using matrix microphone intelligent sound equipment as shown in Figure 1a, matrix microphone includes multiple sounds first 2, wherein the sound first 2
The surrounding of intelligent sound equipment, the first 2 connection audio processing chip 3 of sound are uniformly distributed in, audio processing chip 3 passes through sound first 2
The sound in environment sound field is picked up, so as to parse phonetic order therein.In daily life, where intelligent sound equipment
Space can inevitably have many audio signals, as shown in Figure 1 b, due to the sound of various varying strengths in sound field be present,
The phonetic order quality degradation of pickup, or even None- identified can be caused to go out specific phonetic order.If moreover, intelligent language
The sound source that sound equipment distance sends phonetic order farther out, also results in and is difficult to the carrying that spins off in the sound of first 2 pickup of sound
The voice of instruction, it can not more parse specific instruction.
In addition, for intelligent sound equipment as shown in Figure 1, the difference on technical parameter between each sound head be present
It is different, cause its characteristic, such as sensitivity, can also produce difference.So, the environmental sound signal enhanced processing process to picking up
It equally can also amplify existing difference between each sound head, it is uncertain thus to aggravate auditory localization, is further influenceed from ring
The accuracy of instruction is obtained in the voice of border.
Utility model content
The utility model embodiment provides a kind of intelligent sound equipment, to solve in existing voice control program, voice
Identify that accuracy is poor, can not be controlled effectively the problem of instructing.
The utility model embodiment provides a kind of intelligent sound equipment, including for picking up the stationary tone head of voice signal
It is at least one physically to be combined or taken off with the intelligent sound equipment with the loudspeaker for playing audio signal
From movable sound head, connect the audio treatment unit of the stationary tone head and the movable sound head, connect the audio frequency process list
The voice recognition unit of member, and the main control unit of the connection voice recognition unit, are arranged on the movable sound head and the sound
The first communication unit between frequency processing unit, and, it is arranged between first communication unit and the main control unit
The state detection circuit of instruction input state whether is in for detecting the movable sound head.
Further, the state detection circuit is including being used to detect the movable sound head and the intelligent sound equipment
The no connection status detection circuit in the state departed from, or for detecting the voice signal of the movable sound head current pickup
The signal strength detection circuit of intensity.
Further, the movable sound head includes being used for detecting in the preset range of the movable sound head whether have source of sound mesh
Mark the range sensor of thing.
Further, in addition to the first switch circuit that is arranged between the stationary tone head and the audio treatment unit
And the ON-OFF control circuit being connected between the first switch circuit and the main control unit.
Further, first communication unit includes being used to detect whether the movable sound head departs from the intelligent sound
The detection switch of equipment.
Further, in addition to the main control unit be connected for the second communication unit for being communicated with controlled plant,
Be arranged between the loudspeaker and the main control unit, for converting digital signals at the sound of analog signal
Manage circuit.
Further, in addition to the second switch circuit that is arranged between the loudspeaker and the sound treatment circuit,
The second switch circuit connects the output end of the ON-OFF control circuit.
Further, in addition to the Microspeaker that is arranged on the movable sound head load bearing component, it is described miniature to raise one's voice
Device connects first communication unit.
The utility model embodiment provides a kind of intelligent sound equipment, and the equipment includes existing with the intelligent sound equipment
Movable the sound head and stationary tone head for physically combining or departing from, the square that can be both made up of movable sound head and stationary tone head
Battle array microphone is oriented pickup, can carry out closely pickup by movable sound head again；Closely picked up by movable sound head
Voice signal, the accuracy of speech recognition is can effectively ensure that, to improve the reliability of Voice command, and the equipment operation
Simply, using being also convenient for.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
, below will be to required use in embodiment in order to illustrate more clearly of the technical scheme of the utility model embodiment
Accompanying drawing be briefly described, it should be apparent that, for those of ordinary skills, do not paying creative labor
On the premise of, other accompanying drawings can also be obtained according to these accompanying drawings.
1a in Fig. 1 is a kind of structural representation of intelligent sound equipment using matrix microphone；
The structural representation of sound fields of the 1b where intelligent sound equipment in Fig. 1；
Fig. 2 is a kind of structured flowchart for intelligent sound equipment that the utility model embodiment provides；
Fig. 3 is the movable sound head and the annexation figure of intelligent sound equipment that the utility model embodiment provides；
Fig. 4 is the frequency domain figure of the voice signal for the movable sound head pickup that the utility model embodiment provides；
The frequency domain figure of voice signal after the noise reduction process that Fig. 5 provides for the utility model embodiment；
Fig. 6 is the frequency domain figure of the signal for the stationary tone head pickup that the utility model embodiment provides；
Fig. 7 be the utility model embodiment provide using the signal that stationary tone head picks up be used as noise signal, to voice letter
Number carry out noise reduction process after frequency domain figure；
Fig. 8 is a kind of flow chart of the control method for intelligent sound equipment that the utility model embodiment provides；
Fig. 9 is the flow chart of the control method for another intelligent sound equipment that the utility model embodiment provides；
Figure 10 is the flow chart of the control method for another the intelligent sound equipment that the utility model embodiment provides；
Figure 11 is the flow chart of the control method for another the intelligent sound equipment that the utility model embodiment provides；
Figure 12 is the flow chart of the control method for another the intelligent sound equipment that the utility model embodiment provides；
Figure 13 is the flow chart of the control method for another the intelligent sound equipment that the utility model embodiment provides.
Embodiment
To enable above-mentioned purpose of the present utility model, feature and advantage more obvious understandable, below in conjunction with the accompanying drawings and tool
Body embodiment is described in further detail to the utility model.
Referring to Fig. 1, a kind of intelligent sound equipment 1 is provided for the utility model embodiment, including for picking up voice letter
Number stationary tone first 10 and loudspeaker 21 for playing audio signal, connect the audio treatment unit of the stationary tone first 10
11, connect the voice recognition unit 12 of the audio treatment unit 11, and the main control unit of the connection voice recognition unit 12
13, the intelligent sound equipment 1 can also physically combined or departed from the intelligent sound equipment 1 including at least one
Movable sound first 14, the first communication unit 15 being arranged between the movable sound first 14 and the audio treatment unit 11, with
And be arranged between first communication unit 15 and the main control unit 13, for detecting whether the movable sound head is located
In the state detection circuit 16 of instruction input state.
Whether the main control unit 13 judges the movable sound first 14 by the detection signal of the state detection circuit 16
In instruction input state, if it is, being sent to the audio treatment unit 11 believes the voice of first 14 pickup of the movable sound
Number signal to noise ratio be more than or equal to the first command signal of first threshold, and, the audio treatment unit 11, according to described the
One command signal, judges whether the signal to noise ratio of the voice signal of first 14 pickup of the movable sound is more than or equal to first threshold, such as
Fruit is that the voice signal that the movable sound first 14 picks up is sent into voice recognition unit 12；If not, to the movable sound head
The voice signal of 14 pickups carries out noise reduction process, the signal to noise ratio is more than or equal to first threshold.
In the specific implementation, voice recognition unit 12 can connect cloud server 2 by third communication unit 24.Voice
The voice signal for meeting signal to noise ratio requirement can be sent to cloud server 2 and carry out speech recognition by recognition unit 12, and be parsed
Obtain control instruction signal.If the control instruction signal is search instruction, such as searches for song, cloud server 2 then performs
The search instruction, and search result is sent to intelligent sound equipment 1.
The main control unit 13 judges whether activity sound first 14 is in by the detection signal of the state detection circuit 16
The method of instruction input state includes following three methods.
Method one, the state detection circuit (16) include being used to detect the movable sound head (14) and the intelligent sound
Whether the connection status in the state departed from detects circuit to equipment.The main control unit 13 passes through the state detection circuit 16
Detection signal, whether the movable sound first 14 and the intelligent sound equipment 1 are judged in the state departed from, if it is, really
The fixed movable sound first 14 is in instruction input state.
Intelligent sound equipment 1 can include six stationary tones first 10 and two movable sounds first 14, when movable sound first 14 and intelligence
Can speech ciphering equipment 1 without departing from when, six stationary tones first 10 and two movable sounds first 14 can make up matrix microphone, for fixed
To pickup.
User can by movable sound first 14 physically separating from intelligent sound equipment 1, and can arbitrarily walk
It is dynamic, Voice command is carried out, when having broken away from Voice command, the limitation in voice signal place is sent to user.And to movable sound head
14 closely send voice signal, can strengthen the signal to noise ratio of voice signal, can be successfully even without noise reduction process is carried out
Speech recognition is carried out, and then obtains control instruction signal.And under more noisy environment, or loudspeaker 21 is in
Broadcast state can need not stop the broadcasting of loudspeaker 21, but directly carry out Voice command, avoid the numerous of Voice command
Trivial property.
Physically, movable sound first 14 can connect intelligent sound equipment 1 with jack by plug.So can be with
By judging whether the plug and jack are connected with each other, it is knot to determine the movable sound first 14 and the intelligent sound equipment 1
Conjunction state or disengaged position.
In the specific implementation, being provided with the first communication unit 15 in jack, the first communication unit 15 can include being used to pass
The interface of defeated voice signal or the detection switch for whether departing from the intelligent sound equipment 1 for detecting the movable sound first 14.
The interface and detection switch are connected with connection status detection circuit, are with detection activity sound first 14 and the intelligent sound equipment 1
The no state in disengaging.
The detection switch can be with the power control switch linkage of the first communication unit 15 or directly as the first communication unit
The power control switch of member 15.When movable sound first 14 departs from, the power on of the first communication unit 15, for be wirelessly transferred
Power supply is provided, otherwise the power supply of the first communication unit 15 is disconnected, and wire transmission is carried out by interface.
After plug inserts interface, communication connection can be carried out, main control unit 13 can recognize that interface has after successful connection
Plug inserts
Interface for transmission of speech signals includes the standard interfaces such as USB and type-c.Such as during using USB interface, when
When having the plug to be inserted according to usb protocol, communication certification can be carried out, after completing communication certification, can recognize that interface has plug to insert
Enter.The interface set in the jack can also use self defined interface.
In the utility model embodiment, except passing through interface and detection switch judgement activity sound first 14 and intelligent sound equipment
Whether 1 depart from, and can also be judged by the change in signal strength of its pickup.
In the specific implementation, can also be by the range sensor and pressure sensor that are arranged in intelligent sound equipment 1
To detect movable sound first 14 and the connection status of intelligent sound equipment physically, the range sensor and pressure sensor are set
Put on the position that intelligent sound equipment 1 is in contact with movable sound first 14.
It should be noted that the utility model embodiment is not to judging whether activity sound first 14 and intelligent sound equipment 1 take off
From method be defined.
When movable sound first 14 and intelligent sound equipment 1 depart from, first communication unit 15 can be radio communication list
Member, or, no matter movable sound first 14 physically is being in combining with intelligent sound equipment 1 in disengaging, can
Connected by radio communication.The utility model embodiment does not do concrete restriction to the communication mode of the first communication unit 15.
Method two, as shown in figure 3, the movable sound first 14 includes range sensor 141, if the main control unit 13 is sentenced
Break and the state that the movable sound first 14 is in disengaging with the intelligent sound equipment 1, connect by first communication unit 15
The output signal for the range sensor 141 received, judges whether there is source of sound target in the preset range of the movable sound first 14
Thing, if so, determining that the movable sound first 14 is in instruction input state.
When movable sound first 14 and the intelligent sound equipment 1 depart from, if user closely first to movable sound 14 sends
Voice signal, it is able to detect that in the preset range of movable sound first 14 there is source of sound object, then judges that movable sound first 14 is in
Instruction input state.The source of sound object can be the mouth of user.When movable sound first 14 and intelligent sound equipment 1 depart from, if
User closely first to movable sound 14 does not send voice signal, is able to detect that in the preset range of movable sound first 14 do not have mesh
Thing is marked, then judges that movable sound first 14 is not on instruction input state.So as to ensure in movable sound first 14 and intelligent language
After sound equipment 1 departs from, both the matrix Mike that multiple sound heads form can be passed through by the closely pickup of movable sound first 14 again
Wind realizes that square orients pickup, and use is more convenient.
Method three, the signal strength detection of the intensity of the voice signal for detecting movable sound head (14) current pickup
Circuit.The main control unit 13 judges that the movable sound first 14 currently picks up by the detection signal of the state detection circuit 16
For the voice signal got compared with the average speech intensity of previous periodic environment, whether the voice intensity of enhancing is more than the second threshold
Value, if it is, determining that the movable sound first 14 is in instruction input state.
When carrying out Voice command, user can not also separate movable sound first 14 from intelligent sound equipment 1, and
It is to send voice signal to movable sound first 14 in appropriately distance, now, the first communication unit 15 can receive and the last week
The average speech intensity of phase environment, can be true when the voice intensity of enhancing is more than Second Threshold compared to the voice intensity of enhancing
The fixed movable sound first 14 is in instruction input state.
In the specific implementation, whether the intensity for the voice signal that can also be arrived by judging first 14 current pickup of activity sound is big
In default threshold value, and whether the movable sound of determination first 14 is in instruction input state.
Further, the intelligent sound equipment 1 also includes being arranged on the stationary tone first 10 and the audio treatment unit
First switch circuit 17 between 11 and the switch control being connected between the first switch circuit 17 and the main control unit 13
Circuit 18 processed；Wherein：
If the main control unit 13 judges that the movable sound first 14 is in instruction input state, controlled to the switch
Circuit 18 sends the second command signal for disconnecting the first switch circuit 17.
First switch circuit 17 is used for the break-make for controlling the signal output channels of stationary tone first 10.When movable sound first 14 is in
Instruction input state, it can be determined that go out intelligent sound equipment 1 and control instruction signal is included by first 14 pickup of movable sound
Voice signal, then the signal of first 10 pickup of stationary tone is that may be defined as noise, prevents the signal output of first 10 pickup of stationary tone from arriving
Audio treatment unit 11, reduce the complexity of the process signal of audio treatment unit 11.
Under normal conditions, due to the closely pickup of movable sound first 14, the voice letter for meeting signal to noise ratio requirement can be obtained
Number.Fig. 4 is the frequency domain figure of the voice signal of first 14 pickup of movable sound.As shown in figure 4, the intensity of voice signal is significantly stronger than noise
Signal, it is possible to the voice signal without noise reduction process that movable sound first 14 picks up is sent to voice recognition unit 12,
Carry out speech recognition.
When the signal to noise ratio of the voice signal of first 14 pickup of movable sound is less than first threshold, it is necessary to be carried out to it at noise reduction
Reason, to obtain satisfactory signal, i.e., can smoothly identify the signal of phonetic control command.Fig. 5 is after noise reduction process
The frequency domain figure of voice signal.From Fig. 4 and Fig. 5, voice signal further increases and noise signal after noise reduction process
Intensity difference, so as to realize the accuracy of speech recognition.
In the specific implementation, the signal output channels of stationary tone first 10 can also be connected, so that the energy of audio treatment unit 11
The voice signal of enough first 14 pickups of reception activity sound simultaneously and the signal of first 10 pickup of stationary tone.In that case, can incite somebody to action
The signal of first 10 pickup of stationary tone is carried out at noise reduction as noise signal to the voice signal of movable first 14 pickup of sound
Reason, so that the signal to noise ratio is more than or equal to first threshold.Fig. 6 is the frequency domain figure of the signal of first 10 pickup of stationary tone, and Fig. 7 is
Using the signal that the stationary tone first 10 picks up as noise signal, the frequency domain figure after noise reduction process is carried out to voice signal.By scheming
4th, Fig. 6 and Fig. 7 understand, using the signal that the stationary tone first 10 picks up be used as noise signal, to voice signal progress noise reduction after, greatly
The big intensity difference improved between voice signal and noise signal, so as to realize the accuracy of speech recognition.
In embodiments of the present invention, intelligent sound equipment 1 also include be connected with the main control unit 13 for it is controlled
Second communication unit 20 of equipment communication, and, it is arranged between the loudspeaker 21 and the main control unit 13, for by number
Word signal is converted to the sound treatment circuit 22 of analog signal.
Further, main control unit 13 is by instructing output unit 19 to connect the second communication unit 20 and sound treatment circuit
22, wherein：
The main control unit 13 judges whether include control instruction in the speech recognition signal of the voice recognition unit 12
Signal, if comprising, send the control instruction signal to the instruction output unit 19, and to the ON-OFF control circuit 18
Send the 3rd command signal for connecting the first switch circuit 17.Instruct output unit 19 again will by the second communication unit 20
Control instruction signal is sent to controlled plant.
When control instruction signal is sent into instruction output unit 19, and movable sound first 14 and intelligent sound equipment 1 are not
During disengaging, the 3rd command signal for connecting the first switch circuit 17 is sent to the ON-OFF control circuit 18, connects and fixes
The signal output channels of sound first 10.After realizing that Voice command terminates, original state, user's Voice command next time are returned
When, it can reselect and pickup is oriented by matrix microphone, or pass through the closely pickup of movable sound first 14.
After sending the control instruction signal to the instruction output unit 19, if the main control unit 13 judges institute
The state that movable sound first 14 is not in disengaging with the intelligent sound equipment 1 is stated, sends and connects to the ON-OFF control circuit 18
3rd command signal of the first switch circuit 17.
Further, intelligent sound equipment 1 also include be arranged on the loudspeaker 21 and the sound treatment circuit 22 it
Between second switch circuit 23, the second switch circuit 23 connects the output end of the ON-OFF control circuit 18, for basis
Need to control the break-make of the input audio signal of loudspeaker 21.
When the matrix microphone by first 14 composition of stationary tone first 10 and movable sound carries out pickup, audio treatment unit 11
The voice signal of signal to noise ratio requirement can not be met, or when voice recognition unit 12 can not parse control instruction signal,
Main control unit 13 disconnects the input of the audio signal of loudspeaker 21, stops the playing audio signal of loudspeaker 21, is arrived so as to reduce pickup
Interference signal.
Dropped when using the signal that stationary tone first 10 picks up as noise signal, the voice signal of 14 pickup first to movable sound
After making an uproar, the voice signal of signal to noise ratio requirement can not be still met, or voice recognition unit 12 can not parse control and refer to
When making signal, stop the playing audio signal of loudspeaker 21, so as to reduce the interference signal picked up.
Further, as shown in figure 3, intelligent sound equipment 1 also includes being arranged on first 14 load bearing component of the movable sound
Microspeaker 142, the Microspeaker 142 connects first communication unit 15；Wherein：
If the main control unit 13 judges that the movable sound first 14 is in the shape departed from the intelligent sound equipment 1
State, audio signal is sent to the Microspeaker 142 by first communication unit 15.
When audio signal is sent to Microspeaker 142, ear only is pressed close into Microspeaker 142 can just hear
Sound, so as to avoid the audio signal put outside from influenceing other people.
The utility model embodiment provides a kind of intelligent sound and set, and the equipment is included with the intelligent sound equipment in thing
Movable the sound head and stationary tone head for combining or departing from reason structure, the matrix that can be both made up of movable sound head and stationary tone head
Microphone is oriented pickup, can carry out closely pickup by movable sound head again；Closely picked up by movable sound head
Voice signal, the accuracy of speech recognition is can effectively ensure that, to improve the reliability of Voice command, and equipment operation letter
It is single, using being also convenient for.
Reference picture 8, the utility model embodiment provide a kind of control method of intelligent sound equipment, the intelligent sound
Equipment includes stationary tone head, loudspeaker and at least one can physically combined or departed from the intelligent sound equipment
Movable sound head, methods described comprises the following steps.
Step 1, if the movable sound head is in instruction input state, generation makes the voice letter of the movable sound head pickup
Number signal to noise ratio be more than or equal to first threshold the first command signal.
In the utility model embodiment, step 1 can specifically include：
Step 1a, if whether the movable sound head is in the state departed from the intelligent sound equipment, it is determined that described
Movable sound head is in instruction input state.
Step 1b, if the movable sound head is in the state departed from, and the movable sound with the intelligent sound equipment
There is source of sound object in the preset range of head, determine that the movable sound head is in instruction input state.
Step 1c, if the average speech for the voice signal and previous periodic environment that the movable sound head current pickup arrives is strong
Degree is compared, and the voice intensity of enhancing is more than Second Threshold, determines that the movable sound head is in instruction input state.
Step 2, according to first command signal judge the voice signal that the movable sound head picks up signal to noise ratio whether
More than or equal to first threshold, if it is, going to step 4；Otherwise turn in next step.
Step 3, noise reduction process is carried out to the voice signal of the movable sound head pickup, is more than or equal to the signal to noise ratio
First threshold.
In the utility model embodiment, can the sound of reception activity simultaneously head pickup voice signal and stationary tone head pickup
Signal, then using movable sound head pickup signal as the noise signal of voice signal, noise reduction process is carried out to it, so as to carry
The signal to noise ratio of high voice signal.
If to that after audio signal noise reduction signal to noise ratio still can not be made to be more than or equal to first threshold, it can disconnect and raise one's voice
The input of the audio signal of device.
Step 4, the voice signal for the signal to noise ratio being more than or equal to first threshold carries out speech recognition, and obtains voice
Identification signal.
Step 5, if including control instruction signal in the speech recognition signal, send the control to controlled plant and refer to
Signal is made, and voice signal of the signal to noise ratio more than or equal to first threshold is sent to the loudspeaker；
Step 6, the signal output channels of the stationary tone head are connected.
Before step 2, in addition to：
If described movable sound head is in instruction input state, the signal output channels of the stationary tone head are disconnected, with
Make the audio treatment unit voice signal that only reception activity sound head picks up.
Reference picture 9, the utility model embodiment provide the control method of another intelligent sound equipment, the intelligent language
Sound equipment include stationary tone head, loudspeaker and it is at least one can with the intelligent sound equipment physically combined or take off
From movable sound head, this method comprises the following steps.
Step 11, if the movable sound head is in the state departed from the intelligent sound equipment, the activity is determined
Sound head is in instruction input state.
Step 12, instruction input state is in response to the movable sound head, disconnects the signal output of the stationary tone head
Passage, and the signal to noise ratio for generating the voice signal for making the movable sound head pickup is more than or equal to the first instruction letter of first threshold
Number.
In the specific implementation, be in instruction input state in response to the movable sound head, the loudspeaker can also be disconnected
Audio signal input, so as to stop loudspeaker playing audio signal, the interference signal of reduction activity sound head pickup (believe by noise
Number).
Step 13, according to first command signal judge the voice signal that the movable sound head picks up signal to noise ratio whether
More than or equal to first threshold；If it is, go to step 15；Otherwise turn in next step.
Step 14, noise reduction process is carried out to the voice signal of the movable sound head pickup, the signal to noise ratio is more than or is waited
In first threshold.
Step 15, the voice signal for the signal to noise ratio being more than or equal to first threshold carries out speech recognition, and obtains language
Sound identification signal.
Step 16, if including control instruction signal in the speech recognition signal, the control is sent to controlled plant
Command signal, and send voice signal of the signal to noise ratio more than or equal to first threshold to the loudspeaker.
Step 17, the state be combineding with each other is in response to the movable sound head and the intelligent sound equipment, connects institute
State the signal output channels of stationary tone head.
Reference picture 10, the utility model embodiment provide the control method of another intelligent sound equipment, the intelligence
Speech ciphering equipment include stationary tone head, loudspeaker and it is at least one can with the intelligent sound equipment physically being combined or
The movable sound head of disengaging, this method comprise the following steps.
Step 21, if the movable sound head is in the state departed from, and the movable sound with the intelligent sound equipment
There is source of sound object in the preset range of head, determine that the movable sound head is in instruction input state.
Step 22, instruction input state is in response to the movable sound head, disconnects the signal output of the stationary tone head
Passage, and the signal to noise ratio for generating the voice signal for making the movable sound head pickup is more than or equal to the first instruction letter of first threshold
Number.
In the specific implementation, be in instruction input state in response to the movable sound head, the loudspeaker can also be disconnected
Audio signal input, so as to stop loudspeaker playing audio signal, the interference signal of reduction activity sound head pickup (believe by noise
Number).
Step 23, according to first command signal judge the voice signal that the movable sound head picks up signal to noise ratio whether
More than or equal to first threshold；If it is, go to step 25；Otherwise turn in next step.
Step 24, noise reduction process is carried out to the voice signal of the movable sound head pickup, the signal to noise ratio is more than or is waited
In first threshold.
Step 25, the voice signal for the signal to noise ratio being more than or equal to first threshold carries out speech recognition, and obtains language
Sound identification signal.
Step 26, if including control instruction signal in the speech recognition signal, the control is sent to controlled plant
Command signal, and send voice signal of the signal to noise ratio more than or equal to first threshold to the loudspeaker.
Step 27, in response to not having source of sound object in the preset range of the movable sound head, the stationary tone head is connected
Signal output channels.
When user has sent voice signal, the signal output channels of stationary tone head can be connected, recover intelligent sound equipment
Original state.
Reference picture 11, the utility model embodiment provide the control method of another intelligent sound equipment, the intelligence
Speech ciphering equipment include stationary tone head, loudspeaker and it is at least one can with the intelligent sound equipment physically being combined or
The movable sound head of disengaging, this method comprise the following steps.
Step 31, if the movable sound head is in the state departed from the intelligent sound equipment, the activity is determined
Sound head is in instruction input state.
Step 32, instruction input state is in response to the movable sound head, generation makes the language of the movable sound head pickup
The signal to noise ratio of sound signal is more than or equal to the first command signal of first threshold.
Step 33, according to first command signal judge the voice signal that the movable sound head picks up signal to noise ratio whether
More than or equal to first threshold；If it is, go to step 35；Otherwise turn in next step.
Step 34, the noise signal using the signal of movable sound head pickup as voice signal, is picked up to the movable sound head
Voice signal carry out noise reduction process, the signal to noise ratio is more than or equal to first threshold.
Step 35, the voice signal for the signal to noise ratio being more than or equal to first threshold carries out speech recognition, and obtains language
Sound identification signal.
Step 36, if including control instruction signal in the speech recognition signal, the control is sent to controlled plant
Command signal, and send voice signal of the signal to noise ratio more than or equal to first threshold to the loudspeaker.
Step 37, in response to not having source of sound object in the preset range of the movable sound head, the stationary tone head is connected
Signal output channels.
Reference picture 12, the utility model embodiment provide the control method of another intelligent sound equipment, the intelligence
Speech ciphering equipment include stationary tone head, loudspeaker and it is at least one can with the intelligent sound equipment physically being combined or
The movable sound head of disengaging, this method comprise the following steps.
Step 41, if the average speech for the voice signal and previous periodic environment that the movable sound head current pickup arrives is strong
Degree is compared, and the voice intensity of enhancing is more than Second Threshold, determines that the movable sound head is in instruction input state.
When movable sound head and intelligent sound equipment are in the state be combineding with each other, user can close in intelligent sound equipment
Voice signal is sent to intelligent sound equipment in suitable scope, so as to determine that the movable sound head is in by the method for step 41
Instruction input state.
Step 42, instruction input state is in response to the movable sound head, generation makes the language of the movable sound head pickup
The signal to noise ratio of sound signal is more than or equal to the first command signal of first threshold.
Step 43, according to first command signal judge the voice signal that the movable sound head picks up signal to noise ratio whether
More than or equal to first threshold；If it is, go to step 45；Otherwise turn in next step.
Step 44, noise reduction process is carried out to the voice signal of the movable sound head pickup, the signal to noise ratio is more than or is waited
In first threshold.
Step 45, the voice signal for the signal to noise ratio being more than or equal to first threshold carries out speech recognition, and obtains language
Sound identification signal.
Step 46, if including control instruction signal in the speech recognition signal, the control is sent to controlled plant
Command signal, and send voice signal of the signal to noise ratio more than or equal to first threshold to the loudspeaker.
Step 47, the signal output channels of the stationary tone head are connected.
It should be noted that when movable sound head and intelligent sound equipment are in the state departed from, step can also be passed through
41 method determines that the movable sound head is in instruction input state.
Reference picture 13, the utility model embodiment provide the control method of another intelligent sound equipment, the intelligence
Speech ciphering equipment include stationary tone head, loudspeaker and it is at least one can with the intelligent sound equipment physically being combined or
The movable sound head of disengaging, Microspeaker is provided with the load bearing component of the movable sound head, this method comprises the following steps.
Step 51, audio signal is obtained.
The audio signal can be the audio signal locally generated or the audio signal received from the external world.
Step 52, if movable sound head is in disengaged position with intelligent sound equipment, the audio signal is sent to institute
Microspeaker is stated, the audio signal is otherwise sent to the loudspeaker.
The utility model embodiment provides a kind of control method of intelligent sound equipment, and the equipment includes and the intelligence
Speech ciphering equipment physically combine or depart from movable sound head and stationary tone head, can both pass through movable sound head and stationary tone
The matrix microphone of head composition is oriented pickup, can carry out closely pickup by movable sound head again；Pass through movable sound head
The voice signal closely picked up, the accuracy of speech recognition is can effectively ensure that, to improve the reliability of Voice command, and
The equipment operation is simple, using being also convenient for.
For embodiment of the method, because it is substantially similar to device embodiment, so description is fairly simple, it is related
Part illustrates referring to the part of device embodiment.
Each embodiment in this specification is described by the way of progressive, what each embodiment stressed be with
The difference of other embodiment, between each embodiment identical similar part mutually referring to.
It should be understood by those skilled in the art that, the embodiment of the utility model embodiment can be provided as method, apparatus or
Computer program product.Therefore, the utility model embodiment can use complete hardware embodiment, complete software embodiment or knot
The form of embodiment in terms of conjunction software and hardware.Wherein wrapped in one or more moreover, the utility model embodiment can use
Computer-usable storage medium containing computer usable program code (includes but is not limited to magnetic disk storage, CD-ROM, optics
Memory etc.) on the form of computer program product implemented.
The utility model embodiment is with reference to according to the method for the utility model embodiment, terminal device (system) and meter
The flow chart and/or block diagram of calculation machine program product describes.It should be understood that can by computer program instructions implementation process figure and/
Or each flow in block diagram and/or square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.Can
These computer program instructions are provided at all-purpose computer, special-purpose computer, Embedded Processor or other programmable datas
The processor of terminal device is managed to generate a machine so that pass through computer or other programmable data processing terminal equipments
The instruction of computing device is generated for realizing in one flow of flow chart or multiple flows and/or one square frame or more of block diagram
The device for the function of being specified in individual square frame.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing terminal equipments
In the computer-readable memory to work in a specific way so that the instruction generation bag being stored in the computer-readable memory
The manufacture of command device is included, the command device is realized in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps is performed on computer or other programmable terminal equipments to generate computer implemented processing, so that
The instruction performed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or specified in one square frame of block diagram or multiple square frames function the step of.
Although having been described for the preferred embodiment of the utility model embodiment, those skilled in the art once learn
Basic creative concept, then can make other change and modification to these embodiments.So appended claims are intended to solve
It is interpreted as including preferred embodiment and falls into having altered and changing for the utility model embodiment scope.
Finally, it is to be noted that, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between any this actual relation or order be present.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or terminal device including a series of elements are not only wrapped
Those key elements, but also the other element including being not expressly set out are included, or is also included for this process, method, article
Or the key element that terminal device is intrinsic.In the absence of more restrictions, wanted by what sentence "including a ..." limited
Element, it is not excluded that other identical element in the process including the key element, method, article or terminal device also be present.
A kind of intelligent sound equipment provided by the utility model and its control method are described in detail above, this
Apply specific case in text to be set forth principle of the present utility model and embodiment, the explanation of above example is
It is used to help understand method and its core concept of the present utility model；Meanwhile for those of ordinary skill in the art, according to this
The thought of utility model, there will be changes in specific embodiments and applications, in summary, this specification content
It should not be construed as to limitation of the present utility model.
Claims (9)
1. a kind of intelligent sound equipment (1), it is characterised in that including for picking up the stationary tone head (10) of voice signal and being used for
The loudspeaker (21) of playing audio signal, it is at least one can with the intelligent sound equipment (1) physically being combined or
The movable sound head (14) of disengaging, the audio treatment unit (11) of the stationary tone head (10) and the movable sound head (14) is connected,
Connect the voice recognition unit (12) of the audio treatment unit (11), and the master control list of the connection voice recognition unit (12)
First (13), the first communication unit (15) being arranged between the movable sound head (14) and the audio treatment unit (11), with
And it is arranged between first communication unit (15) and the main control unit (13) be used for whether detecting the movable sound head
State detection circuit (16) in instruction input state.
2. intelligent sound equipment as claimed in claim 1, it is characterised in that the state detection circuit (16) includes being used to examine
Surveying the movable sound head (14), whether the connection status in the state departed from detects circuit with the intelligent sound equipment (1),
Or the signal strength detection circuit of the intensity of the voice signal for detecting movable sound head (14) current pickup.
3. intelligent sound equipment as claimed in claim 2, it is characterised in that the movable sound head (14) includes being used to detect institute
Whether state has the range sensor (141) of source of sound object in the preset range of movable sound head (14).
4. the intelligent sound equipment as described in claim 1,2 or 3, it is characterised in that also include being arranged on the stationary tone head
(10) the first switch circuit (17) between the audio treatment unit (11) and it is connected to the first switch circuit (17)
ON-OFF control circuit (18) between the main control unit (13).
5. intelligent sound equipment as claimed in claim 4, it is characterised in that first communication unit (15) includes being used to examine
Survey the detection switch whether movable sound head (14) departs from the intelligent sound equipment (1).
6. intelligent sound equipment as claimed in claim 5, it is characterised in that also include what is be connected with the main control unit (13)
For the second communication unit (20) to be communicated with controlled plant, and, it is arranged on the loudspeaker (21) and the main control unit
(13) between, for converting digital signals into the sound treatment circuit (22) of analog signal.
7. intelligent sound equipment as claimed in claim 6, it is characterised in that also include being arranged on the loudspeaker (21) and institute
State the second switch circuit (23) between sound treatment circuit (22), second switch circuit (23) the connection switch control
The output end of circuit (18).
8. intelligent sound equipment as claimed in claim 7, it is characterised in that also held including being arranged on the movable sound head (14)
The Microspeaker (21) on part is carried, the Microspeaker (142) connects first communication unit (15).
9. intelligent sound equipment as claimed in claim 1, it is characterised in that the voice recognition unit (12) passes through threeway
Believe unit (24) connection cloud server (2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721146325.6U CN207217112U (en) | 2017-09-08 | 2017-09-08 | A kind of intelligent sound equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721146325.6U CN207217112U (en) | 2017-09-08 | 2017-09-08 | A kind of intelligent sound equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN207217112U true CN207217112U (en) | 2018-04-10 |
Family
ID=61823571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201721146325.6U Active CN207217112U (en) | 2017-09-08 | 2017-09-08 | A kind of intelligent sound equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN207217112U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111934957A (en) * | 2020-07-16 | 2020-11-13 | 宁波方太厨具有限公司 | Application system and method supporting WiFi and offline voice |
-
2017
- 2017-09-08 CN CN201721146325.6U patent/CN207217112U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111934957A (en) * | 2020-07-16 | 2020-11-13 | 宁波方太厨具有限公司 | Application system and method supporting WiFi and offline voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11282520B2 (en) | Method, apparatus and device for interaction of intelligent voice devices, and storage medium | |
| US10957319B2 (en) | Speech processing method, device and computer readable storage medium | |
| CN109473095B (en) | Intelligent household control system and control method | |
| CN106303836B (en) | Method and device for adjusting stereo playing | |
| CN106601272B (en) | Earphone and its audio recognition method | |
| CN106792341A (en) | Audio output method and device and terminal equipment | |
| CN108886653A (en) | A kind of earphone sound channel control method, relevant device and system | |
| CN109473097B (en) | Intelligent voice equipment and control method thereof | |
| CN102857807A (en) | Communication terminal voice control method and digital television terminal | |
| CN103974163A (en) | Earphone compatible method, earphone compatible device and mobile terminal | |
| CN106169039A (en) | A kind of mobile terminal and operational approach thereof | |
| CN105679350B (en) | A kind of method and device that audio plays | |
| CN110972023B (en) | Earphone charging box and voice playing system thereof | |
| EP3223537A1 (en) | Content playback device, content playback method, and content playback program | |
| CN105719672A (en) | Recording scene mode switching method and recording scene mode switching mode device | |
| CN109121059A (en) | Loudspeaker plug-hole detection method and Related product | |
| CN207217112U (en) | A kind of intelligent sound equipment | |
| CN110996308A (en) | Sound playing device and control method, control device and readable storage medium thereof | |
| CN109473096B (en) | Intelligent voice equipment and control method thereof | |
| CN108370486A (en) | Audio output device and method for controlling audio output device | |
| CN103945063A (en) | Earphone mode switching device and method and mobile terminal | |
| CN116193413B (en) | Bluetooth connection method, system, storage medium and device | |
| CN103297896A (en) | Audio output method and electronic equipment | |
| US8755743B2 (en) | Earpiece messaging | |
| CN110035346A (en) | Communication means, device, bluetooth headset and the storage medium of bluetooth headset |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 100101 Room 101, 1st floor, block C, building 21, 2 Wanhong West Street, xibajianfang, dongzhimenwai, Chaoyang District, Beijing Patentee after: Beijing Junlin Technology Co.,Ltd. Address before: 100107 commercial building 03, floor 3, block C, tianlangyuan, Chaoyang District, Beijing (No. 1336, Fengshou incubator) Patentee before: BEIJING JUNLIN TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210305 Address after: 215163 Room 201, building 17, No.158, Jinfeng Road, science and Technology City, Suzhou, Jiangsu Province Patentee after: Suzhou Junlin Intelligent Technology Co.,Ltd. Address before: 100101 Room 101, 1st floor, block C, building 21, 2 Wanhong West Street, xibajianfang, dongzhimenwai, Chaoyang District, Beijing Patentee before: Beijing Junlin Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |