CN108064007A - Know method for distinguishing and microcontroller and intelligent sound box for the enhancing voice of intelligent sound box - Google Patents
Know method for distinguishing and microcontroller and intelligent sound box for the enhancing voice of intelligent sound box Download PDFInfo
- Publication number
- CN108064007A CN108064007A CN201711084937.1A CN201711084937A CN108064007A CN 108064007 A CN108064007 A CN 108064007A CN 201711084937 A CN201711084937 A CN 201711084937A CN 108064007 A CN108064007 A CN 108064007A
- Authority
- CN
- China
- Prior art keywords
- microphone
- power amplifier
- voice
- sound
- loud speaker
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/02—Circuits for transducers, loudspeakers or microphones for preventing acoustic reaction, i.e. acoustic oscillatory feedback
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/02—Casings; Cabinets ; Supports therefor; Mountings therein
- H04R1/04—Structural association of microphone with electric circuitry therefor
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Otolaryngology (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
It discloses a kind of enhancing voice for intelligent sound box and knows method for distinguishing, including:The voice signal received using microphone opens noise cancellation;When the noise cancellation is opened, speaker volume is reduced by power amplifier control instruction;After the voice messaging corresponding information to be played is got, recover horizontal before instruction recovers speaker volume to reduction by power amplifier.This method can reduce the production cost of sound-box device.
Description
Technical field
The present invention relates to intelligent sound box technical field, more particularly, to the enhancing voice of intelligent sound box know method for distinguishing and
Microcontroller and intelligent sound box.
Background technology
Since in actual use, microphone and loud speaker need to purchase respectively, add the purchase cost of user,
And it is unfavorable for subsequent plant maintenance, therefore, many manufacturers begin attempt to the integrated microphone in intelligent sound box, so as to fulfill two
The integrated design of person.
Because speaker's distance microphone is farther out, signal-to-noise ratio is poorer, in order to improve the human voice signal that microphone receives, mesh
It is multi-microphone array scheme that preceding sound-box device in the market, which would generally use, such as common 6+1 microphone schemes.But because
More for number of microphone, each microphone channel is required to I2S inputs all the way and ADC conversions, so signal acquisition circuit is answered
Miscellaneous, computing module parts selection threshold is higher, and the production cost so as to cause sound-box device remains high.
The content of the invention
The embodiment of the present invention provide for intelligent sound box enhancing voice know method for distinguishing and sound-box device, can drop
The production cost of bass box equipment.
In order to achieve the above objectives, a kind of scheme for carrying out speaker volume and automatically controlling is provided in embodiment, by raising
Sound device Automatic control of sound volume, to eliminate noise and the echo that loud speaker is brought, so as to reduce masking by noise, reduce noise jamming,
The relative signal-to-noise ratio of microphone is enhanced, a kind of favourable environment is provided for clear pickup efficient voice, makes to reduce microphone
Condition is provided with quantity, simplifies circuit and structure.
Compared with the microphone placement scheme that number of microphone is 6~8 is commonly used in existing scheme, raise one's voice because eliminating
The influence of noise of device, so the relative signal-to-noise ratio increase of microphone, so as to reduce the quantity that microphone uses.Simultaneously as Mike
The reduction of wind quantity simplifies ADC conversion circuits, reduces A/D converter number of packages amount, microphone channel quantity is reduced, to be shipped
It calculates processing recorded audio signals to reduce, also just reduces data processing amount, reduce the type selecting threshold of MCU, finally reduce sound-box device
Production cost.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 a are a kind of schematic diagram of method flow provided in an embodiment of the present invention;
Fig. 1 b are the schematic diagram of another method flow provided in an embodiment of the present invention;
Fig. 1 c are the schematic diagram of another method flow provided in an embodiment of the present invention;
Fig. 2 is the schematic diagram of another specific example provided in an embodiment of the present invention;
Fig. 3 is the structure diagram of sound-box device provided in an embodiment of the present invention;
Fig. 4, Fig. 5 are the array structure schematic diagram of microphone provided in an embodiment of the present invention;
Drawing reference numeral therein represents:1- keypads component, 2- casing of loudspeaker box-upper casing, 3- mainboards, 4- loud speakers, 5- sound
Learn phase equalizer, 6- casing of loudspeaker box-lower casing, 7- light circuits plate, 8- light diffusion sheet and 9- pedestals.
Specific embodiment
For those skilled in the art is made to more fully understand technical scheme, below in conjunction with the accompanying drawings and specific embodiment party
Formula is described in further detail the present invention.Embodiments of the present invention are described in more detail below, the embodiment is shown
Example is shown in the drawings, wherein same or similar label represents same or similar element or with identical or class from beginning to end
Like the element of function.It is exemplary below with reference to the embodiment of attached drawing description, is only used for explaining the present invention, and cannot
It is construed to limitation of the present invention.Those skilled in the art of the present technique are appreciated that unless expressly stated, odd number shape used herein
Formula " one ", "one", " described " and "the" may also comprise plural form.It is to be further understood that the specification of the present invention
The middle wording " comprising " used refers to there are the feature, integer, step, operation, element and/or component, but it is not excluded that
Other one or more features of presence or addition, integer, step, operation, element, component and/or their group.It should be understood that
When we claim element to be " connected " or during " coupled " to another element, it can be directly connected or coupled to other elements or
There may also be intermediary elements.In addition, " connection " used herein or " coupling " can include wireless connection or coupling.Here make
Wording "and/or" includes any cell of one or more associated list items and all combines.The art
Technical staff is appreciated that unless otherwise defined all terms used herein have (including technical term and scientific terminology)
The meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.It is it should also be understood that such as general
Those terms defined in dictionary, which should be understood that, to be had a meaning that is consistent with the meaning in the context of the prior art, and
Unless being defined as here, will not be explained with the meaning of idealization or overly formal.
The embodiment of the present invention provides knows method for distinguishing for the enhancing voice of intelligent sound box, as shown in Figure 1a, including:
S1, the voice signal received using microphone open noise cancellation.
Wherein, the flow of the present embodiment can be performed by a kind of sound-box device, for running the journey of the flow of the present embodiment
Sequence module (be specifically properly termed as volume control disappear echo program), may be mounted at the ROM (Read-Only of sound-box device
Memory, read-only memory) in and pass through MCU (Microcontroller Unit, micro-control unit or microcontroller) control
Operation, MCU runs the volume control and disappears echo program, and it is determined whether to enable noise cancellations according to program.
S2, when the noise cancellation is opened, pass through power amplifier control instruction reduce speaker volume.
If being not turned on noise cancellation, the current operating status of sound-box device is maintained, does not do additional processing.
Wherein, the power amplifier control instruction reduces volume for triggering the loud speaker.In the present embodiment, power amplifier is triggered
Control instruction can specifically include 2 modes, and one is end-point detection, that is, when having external input voice signal, volume reduces
(such as -6dB);Secondly to wake up word triggering, it is common, the volume of power amplifier of loud speaker can be minimized when waking up word triggering.
Specifically, the first step, power amplifier control instruction can be used for triggering the loud speaker reduction sound when end-point detection triggers
Measure the designated value for being less than current volume to one;Second step, the loud speaker reduces volume to zero or touches when waking up word triggering
Send out loud speaker temporary close described.
S3, when getting the corresponding information to be played of the voice messaging, instruction is recovered by speaker volume by power amplifier
Recover horizontal to before reducing.
Wherein, the power amplifier recovers instruction and recovers level of the volume to before reducing for triggering the loud speaker.It is to be played
Information refers to the information that loud speaker playback is needed to play.
Specifically, information to be played can specifically be obtained by sound-box device from local storage, such as from sound-box device
Memory in obtain voice data, and according to voice data by the loud speaker play cuing voice of sound-box device, also,
By recovering to instruct, it is necessary to send power amplifier to loud speaker before the loud speaker play cuing voice of sound-box device, in order to raise one's voice
Device recovers volume, and with the volume play cuing voice after recovery.
Optionally, information to be played can also be sent to sound-box device by cloud server, such as:Sound-box device is directed to wheat
The signal of gram elegance collection carries out speech analysis and synthesis, and passes through the Internet transmission to cloud server, to perform cloud identification
Service.Cloud server carries out speech recognition, semantic analysis, and feeds back information to be played, and cloud can be included in information to be played
The behavior command that end server is sent to sound-box device, if behavior command needs speaker to carry out voice when being performed on sound-box device
It during feedback, then sends power amplifier to loud speaker and recovers instruction, in order to which loud speaker recovers volume, and carried with the volume broadcasting after recovery
Show voice.
Phonetic entry environment has environment white noise, the sound etc. of loud speaker music, for successful activation recognizer,
Speech terminals detection is an important step of speech recognition, and generally use method is:Threshold comparative law:Feature of the extraction per frame
Compared with the thresholding set or certain mechanism is taken to judge this feature;Model matching method:It is established not for noise or voice
Same model is compared with the model of training to adaptation, approximate speech identification;And the end-point detection of fusion various features and method
These methods of algorithm are to be detected calculating for microphone input channel signal to judge, are that microphone input channel is believed
Number Optimal improvements.Because current intelligent sound loudspeaker distance microphone is closer, the sound of loud speaker is for useful
Belong to noise for voice, larger impact is provided with to threshold threshold.In order to improve the human voice signal that microphone receives, mesh
Preceding market enhances the voice sound that microphone receives frequently with being multi-microphone array scheme using Beamforming technology
Pressure.
It is common to pick up currently used for the intelligent sound box of far field speech recognition in the last all kinds of speaker products in current market
Sound number of microphone is 6~8 or uses common 6+1 microphone schemes, such as:In existing product.But because Mike
Wind quantity is more, and each microphone channel is required to I all the way2S (Inter-IC Sound, integrated circuit built-in audio bus)
Input and ADC (Analog-to-Digital Converter, A/D converter or analog-digital converter) are converted, so signal
Acquisition Circuit is complicated, and computing module parts selection threshold is higher, and the production cost so as to cause sound-box device remains high.And
And ambient noise, the sound of loud speaker music and echo can shelter the generation of the signal-to-noise ratio of microphone, and microphone number
Increasing for amount can not solve the problems, such as masking by noise.
Scheme described in this patent carries out the scheme that speaker volume automatically controls after referring to a kind of end-point detection, by raising one's voice
Device Automatic control of sound volume to eliminate noise and the echo that loud speaker is brought, so as to reduce masking by noise, reduce noise jamming, increases
The strong relative signal-to-noise ratio of microphone, provides a kind of favourable environment, to reduce microphone use for clear pickup efficient voice
Quantity provides condition, simplifies circuit and structure.The final production cost for reducing sound-box device.
In the present embodiment, provide in a kind of step S1, detect whether that opening noise eliminates according to the voice signal
The concrete scheme of function, as shown in Figure 1 b, including:
S11, receive the voice signal that collects of microphone, and according to the input sensitivity of the microphone, described raise one's voice
The output sensitivity of device and the volume status of power amplifier obtain the work(of voice signal that the microphone receives and the loud speaker
Put the energy integral difference between output signal.
S12, when energy integral difference variation be more than preset range when, open noise cancellation.
In the present embodiment, because the distance of microphone to loud speaker is fixed, microphone receives speaker playback
Sound pressure machine loud speaker reduction sound pressure subtract the attenuation of distance, when no other outside sound sources interference, microphone
The acoustic pressure of receiving and the acoustic pressure of speaker playback are the proportionate relationships of a constant coefficient.Therefore microphone receives acoustic pressure and is converted into
The audio signal integral energy variation of the energy variation and aforementioned playout of electric signal is a fixed functional relation.Specifically,
Existing end-point detection algorithm software can be utilized in the present embodiment, according to signal and this fixed functional relation precomputation wheat
The electric signal of gram wind, while detect that microphone is actual to receive transformed electric signal, when the signal being an actually-received be more than it is advance
During the signal of calculating, then external sound input (or interference) is judged.
De-noising and recording are opened at this time, and acoustic model matching is carried out to recording substance and is compared (or identification);Work as identification
To model be particular keywords (such as small small biu of biu) when we be determined as wake up the machine, and perform it is subsequent recording progress
Local identification (such as some simple switching on and shutting down, increase volume down small volume), when not identifying (such as due to local library
Acoustic model is less) it is transmitted further to backstage voice recognition acoustic model storehouse identification is compared.
Such as:In sound-box device, pick up sound in real time by microphone and pass through ADC and be converted to digital signal i.e. data
(DATA), then I is passed through2S bus transfers are to locally stored unit (Flash or DDR).Then the program built in ROM passes through
The computing of MCU rows and feedback command and data are managed, described instruction includes being not limited to Intelligent volume control and disappears echo journey
Sequence and whether behavior feedback is carried out to microphone input signal by the program, specifically included:
Converted according to microphone input sensitivity and loud speaker output sensitivity and volume status, microphone receive signal and
There is relatively-stationary short-time energy integration differential Δ between power amplifier output signal.
When someone's vocal input because the superposition of acoustic energy, when microphone receives signal and can exceed this difference DELTA, MCU at this time
It sends instruction and opens automatic volume control eliminated noise function, reduce power amplifier output, while improve the gain of microphone input channel,
Accuracy and clarity so as to fulfill microphone pickup, reduce the interference of noise.Wherein, microphone reception signal breaks this
A difference DELTA, it can be understood as:After microphone receives signal, the variation of the energy integral difference DELTA influenced is more than default difference
Be worth scope (i.e. so-called preset range in the present embodiment), energy integral difference DELTA has an appropriate difference range, difference range according to
Ambient noise conditions preset (initial value is the test value under quiet environment), other have interference noise such as fan, washing machine, TV
It can be by the self-defined environmental pattern of client (corresponding energy integral difference range) when machine, outdoor automobile.Afterwards, for Mike's elegance
The signal of collection carries out voice extraction, analysis and synthesis, and is transferred to local speech recognition system and carries out voice wake-up (Mike's elegance
The signal of collection carries out acoustic model with fixed wake-up word and compares).When the sound recognized is specific human voices unit --- it is i.e. pre-
During " wake-up word " the acoustic feature model put;It wakes up successfully.Power amplifier output is closed at this time, while subsequent voice messaging is carried out
Local identification services transmitting voice signal to the identification of background network cloud, background service progress speech recognition, semantic analysis, and
Behavior command is fed back, if read statement completion needs sound equipment progress voice feedback, passes through Intelligent volume first and controls recovery work(
Output gain is put, while backstage feedback voice is given to the power amplifier output of sound equipment.
If the variation of current energy integral difference is not above preset range, extra process is not done.
S2, when the noise cancellation is opened, pass through power amplifier control instruction reduce speaker volume.
If being not turned on noise cancellation, the current operating status of sound-box device is maintained, does not do additional processing.
S3, after the voice messaging corresponding information to be played is got, instruction is recovered by speaker by power amplifier
Amount recovers horizontal to before reducing.
In above-mentioned provided step S1, detected whether to open the specific of noise cancellation according to the voice signal
Scheme converts according to microphone input sensitivity and loud speaker output sensitivity and volume status, since microphone receives signal
There is relatively-stationary short-time energy integration differential Δ between power amplifier output signal, therefore when someone's vocal input because of acoustic energy
Superposition, when microphone reception signal can break this difference DELTA, MCU sends instruction and closes power amplifier output at this time, while improves wheat
The gain of gram wind input channel, accuracy and clarity so as to fulfill microphone pickup reduce the interference of noise.
The present embodiment is compared using the difference value and preset range of microphone channel signal and power amplifier output signal
Method is as end-point detection means, in the end-point detection stage using the short-time energy integration superposition of each microphone synthesis and power amplifier passage
Short-time energy integral contrast when more than the preset range of short-time energy integration difference, controls mute speaker by I2C at this time
Power amplifier output, and microphone integrated signal is transferred to program and carries out computing and I/O management..
Optionally, the preset range of the variation in S12 for detecting energy integral difference is quiet based on usual family
(default initial values) of environment measurement can also be set by the user according to specific use environment, and mode set by user can be with
It is directly to read out preset range adjustment word to sound-box device.
When detecting in the voice signal containing preset range adjustment word, it is corresponding to inquire about the preset range adjustment
Interval, and, can be in the memory of sound-box device using the interval inquired as the preset range wherein
Memory map assignments record the mapping relations of at least two preset range adjustment word and interval in mapping table.Such as:Default model
Enclosing adjustment word can include:Fan, washing machine, television set, outdoor automobile etc., different preset ranges adjustment word correspond to phase respectively
The interval answered, the specific value of interval can be set according to ambient noise conditions.
Preset range adjustment word is read out from user to sound-box device, sound-box device then updates default model by environmental parameter table
The specific value enclosed, so as to complete the environment set of user, so that preset range value can be more used in sound-box device
Add matching current environment, improve the accuracy rate for judging whether noise cancellation is opened.
In the present embodiment, step S2 is being performed, is opening noise cancellation, and send the same of power amplifier control instruction
When, it can also further improve the gain of the input channel of microphone, i.e., as illustrated in figure 1 c, it further includes:
S4, judge need to send the power amplifier control instruction when, to the microphone send gain improve instruction.
Wherein, the gain improves instruction for triggering the gain that the microphone improves input channel.
In the present embodiment, while power amplifier control instruction is sent, the gain of the input channel of microphone is also improved, from
And the accuracy of microphone collected sound signal is further improved, further reduce the ambient noise that microphone receives.
In the present embodiment, a kind of sound-box device local detection voice messaging is also provided, and determines whether to wake up loud speaker
The flow of power amplifier function, i.e., it is in step s3, described to send work(after the voice messaging corresponding information to be played is got
Recovery instruction is put, including:
After voice messaging is determined according to the voice signal, and detect that there are goal-sellings in the information to be played
During keyword, send the power amplifier to the loud speaker and recover instruction;After level before the speaker volume recovers to reduction,
According to the information play cuing voice to be played.
Wherein, the content that goal-selling keyword can include sound-box device is needed to carry out voice feedback is (in the present embodiment
It is referred to as waking up word), MCU sends the power amplifier to the loud speaker and recovers instruction, and the power amplifier output for recovering loud speaker increases
Benefit, while backstage feedback voice is given to the power amplifier output of sound equipment.For the signal of microphone acquisition, MCU can be with local runtime language
Cent is analysed and synthesis program, and is transferred to local speech recognition system and carries out voice wake-up.When the sound recognized is special language
Sound unit --- during i.e. preset " wake-up word " acoustic feature model, send the power amplifier to the loud speaker and recover instruction.
In the present embodiment, can be by sound-box device local detection voice messaging, and determine whether to wake up loud speaker power amplifier
Function, so as to fulfill the wake-up of the loud speaker power amplifier under offline scenario, in order to the phonetic entry being used under offline scenario.
In the present embodiment, also provide one kind and speech recognition is carried out by cloud server, and returned to sound-box device and wait to broadcast
Information is put, then power amplifier is locally sent by sound-box device and recovers instruction, so as to wake up power amplifier, i.e., in step s3, when getting
After stating the corresponding information to be played of voice messaging, the power amplifier that sends recovers instruction, including:
After voice messaging is determined according to the voice signal, the voice messaging is sent to cloud server;Work as speaker
After equipment receives the prompt message of the cloud server feedback, send the power amplifier to the loud speaker and recover instruction;Root
According to the information of voice prompt, pass through the loud speaker play cuing voice.Such as:Sound-box device will be received by microphone
Transmitting voice signal to cloud server and perform identification service, cloud server carries out speech recognition, the streams such as semantic analysis
Journey, and behavior command is fed back to sound-box device, MCU sends the power amplifier to the loud speaker and recovers instruction, recovers loud speaker
Power amplifier output gain, in order to pass through the loud speaker play cuing voice.
In the present embodiment, can be by sound-box device local detection voice messaging, and determine whether to wake up loud speaker power amplifier
Function, so as to fulfill the wake-up of the loud speaker power amplifier under online scene so that sound-box device can be by the meter of cloud server
Function is calculated, the higher speech recognition algorithm of more complicated and accuracy is run, so as to increase the accuracy of speech recognition.
In the present embodiment, a kind of flow for the power amplifier function of waking up loud speaker naturally is also provided, specifically sending
After stating power amplifier control instruction, triggering timing device starts timing;When timer reaches preset duration, then send power amplifier and recover instruction.
Wherein, preset duration can just be set by user according to use habit.So as to avoid due to long-time without
Phonetic entry or the problem of be not waken up always the power amplifier function of loud speaker caused by due to failure, program error etc.,
The normal use of loud speaker is ensured.
It should be noted that the flow of the power amplifier function of loud speaker is waken up naturally, it can be with sound-box device local detection language
Message ceases, and determines whether to wake up the flow of loud speaker power amplifier function and carry out speech recognition by cloud server, and to sound
Case equipment returns to information to be played, i.e. the flow of the power amplifier function of high in the clouds wake-up loud speaker performs simultaneously.
In the preferred embodiment of the present embodiment, the number of microphone installed on sound-box device is 2 or 4, i.e. institute
It states and receives the voice signal that microphone collects, including:
Voice signal by the reception microphone for connecting microphone array sound passage, the connection microphone array
Row sound channel quantity is 2 or 4.
For example, as shown in Figure 2:
ADC modular converters, the voice signal that microphone is picked up are digitized extraction, wherein, ADC modular converters
It can be integrated on microphone module.2 or 4 microphone combinations may be employed in microphone module in sound-box device;Mike
The type of wind can be specifically digital silicon wheat MEMS (Micro-Electro-Mechanical System, MEMS),
Capacitance wheat ECM (Electret Condenser Microphone, electret capacitor) or DYN dynamic microphone.
The power amplifier end signal of signal processing module, the voice that microphone is received and loud speaker carries out comparison in difference, so
Existing voice processing technology may be employed on signal processing module afterwards, voice increasing is carried out to the voice that microphone receives
By force, the processing such as voice de-noising, echo cancellor, and extract voice signal;
Signal emission module, the extraction voice signal that will be extracted are sent to cloud server and carry out speech recognition;
Signal receiving module, for receiving the data that cloud server is sent;
Sound identification module, for carrying out speech recognition and semantic analysis, and the voice messaging obtained to analysis seals
Dress, synthesis;
MCU, for carrying out local service control, such as volume increase/reduction volume control, switching on and shutting down, to loud speaker mould
Group sends power amplifier control instruction and power amplifier recovers the instructions such as instruction control;
If desired speaker carries out voice feedback, then going out power amplifier to loud speaker module recovers instruction, in order to loud speaker module
Recover volume, and with the volume play cuing voice after recovery.
Other behavior commands feed back to intelligent terminal, such as all kinds of smart homes of smart television, air-conditioning by MCU~I2C
Equipment etc. or other behavior commands feed back to cloud server by MCU~I2C, wherein, cloud server can be used for Yun Yin
Pleasure, internet shopping, ticket booking, news, weather etc. are in line service.
Compared with the microphone placement scheme that number of microphone is 6~8 is commonly used in existing scheme, raise one's voice because eliminating
The influence of noise of device, the present embodiment is only with 2 or 4, so the relative signal-to-noise ratio increase of microphone, so as to reduce wheat
The quantity that gram wind uses.Simultaneously as the reduction of number of microphone, simplifies ADC conversion circuits, reduce A/D converter part
Quantity also just reduces data processing amount, reduces the type selecting threshold of MCU.
The embodiment of the present invention also provides a kind of microcontroller (MCU), including:
Function management unit for the voice signal received using microphone, opens noise cancellation;
First power amplifier control unit, for when the noise cancellation is opened, being raised by the reduction of power amplifier control instruction
Sound device volume;
Second power amplifier control unit, for after the voice messaging corresponding information to be played is got, passing through power amplifier
Recover horizontal before instruction recovers speaker volume to reduction.
The embodiment of the present invention also provides the sound-box device that one kind includes above-mentioned microcontroller (MCU), as shown in Fig. 3,
Including:Casing of loudspeaker box-upper casing (2), keypad component (1), mainboard (3), loud speaker (4), acoustics phase equalizer (5), light
Circuit board (7), light diffusion sheet (8), casing of loudspeaker box-lower casing (6) and pedestal (9);
Keypad component (1) is made of at least one button and the first circuit PCB, and at least one button is mounted on institute
It states on the first circuit PCB, the first circuit PCB is used to receive the electric signal after at least one button is clicked, keypad group
Part (1) is fixed on the inner surface of casing of loudspeaker box-upper casing (2);
Mainboard (3) is mounted in the inner cavity of casing of loudspeaker box-upper casing (2), and mainboard is equipped with microphone on (3);
Acoustics phase equalizer (5) and loud speaker (4) are mounted in the inner cavity of casing of loudspeaker box-lower casing (6), acoustics phase etc.
Change device (5) and loud speaker (4) at a distance of predetermined distance, make to form gap between acoustics phase equalizer (5) and loud speaker (4);
Light circuit plate (7) is mounted on the bottom inner surface of casing of loudspeaker box-lower casing (6), and light diffusion sheet (8) is covered in
The lower section of light circuit plate (7), light circuit plate (7) are made of at least one LED light and second circuit PCB;
Pedestal (9) is mounted on the bottom end of casing of loudspeaker box-lower casing (6);
Microphone of the quantity more than 1 is uniformly distributed around the central point of mainboard (3), and the microphone is arranged on master
On plate (3), microphone picks up sound and passes through ADC in real time is converted to electric signal;Electric signal is total by integrated circuit built-in audio
Line is transferred to MCU microcontrollers;Volume control built in MCU disappears echo program, and microphone input signal is carried out by the program
Handle simultaneously feedback control command signal;
Volume control built in the MCU disappears echo program, including:
Function management unit for the voice signal received using microphone, opens noise cancellation;
First power amplifier control unit, for when the noise cancellation is opened, being raised by the reduction of power amplifier control instruction
Sound device volume;
Second power amplifier control unit, for after the voice messaging corresponding information to be played is got, passing through power amplifier
Recover horizontal before instruction recovers speaker volume to reduction.
In the preferred embodiment of the present embodiment, the number of microphone installed on mainboard (3) is 2 or 4.Outside speaker
The surface of shell-upper casing (2), the position perforate of corresponding microphone.
It should be noted that in such as Fig. 3, it, will be in sound-box device in order to which all component and erection sequence is presented
The component in portion is also presented in exterior space.Except pedestal (9), (i.e. pedestal (9) is mounted on speaker outside the sound-box device
The rear surface of shell-lower casing (6)), other parts are all mounted on casing of loudspeaker box-upper casing (2) and casing of loudspeaker box-lower casing (6) is inner
Face.Optionally, casing of loudspeaker box-lower casing (6) outer surface is coated with one layer of screen cloth, does not enter to block dust in sound equipment.
Keypad component (1) is made of at least one button and the first circuit PCB, and at least one button is mounted on institute
It states on the first circuit PCB, the first circuit PCB is used to receive the electric signal after at least one button is clicked, keypad group
Part (1) is fixed on the inner surface of casing of loudspeaker box-upper casing (2).As shown in Figure 3, perforate is equipped on casing of loudspeaker box-upper casing (2),
Perforate is used for the button of placing key-press plate component (1), in order to which user touches button from the outside of casing of loudspeaker box-upper casing (2)
The button of plate component (1), such as:Button can be controlled outside housing;If mechanical touch key key part leakage in
Housing;Button is mounted in housing if using touch key-press, and upper casing is partially transparent, and button is enable to sense finger
Slip or click action.
Wherein, the button on keypad component (1), may be employed existing Key element, such as:Using currently used
Touch sensible button or touch key.
The first circuit PCB (Printed Circuit Board, printed circuit board) employed in the present embodiment and
Two circuit PCB can use current printed circuit board that is existing, and being widely used, according to the different work(to be realized
Can, printed circuit board welds corresponding electricity component and forms circuit,.Such as:On the first circuit PCB, phase is realized for button
The click function answered, such as:The function that speaker is opened, closed.It should be noted that realize corresponding click function only for button
Simple analog circuit is designed by the prior art can be realized.It may be employed before first circuit PCB and second circuit PCB often
Winding displacement connection scheme.
Mainboard (3) is mounted in the inner cavity of casing of loudspeaker box-upper casing (2), and the wheat that quantity is more than 1 is equipped on mainboard (3)
Gram wind.
Specifically, the function elements such as central processing element and power amplifier chips, wiring board, Yi Jimai are welded on mainboard (3)
Gram wind.Wherein, the function element welded on mainboard (3), can use existing speaker in acoustic processing processing chip, work(
Put chip and corresponding function element.No longer special designing is not repeating in the present embodiment.
Acoustics phase equalizer (5) and loud speaker (4) make acoustics phase equalizer (5) and raise one's voice at a distance of predetermined distance
Gap is formed between device (4), acoustics phase equalizer (5) and loud speaker (4) are mounted in the inner cavity of casing of loudspeaker box-lower casing (6).
Wherein, common electroacoustic conversion playback device can be used in loud speaker (4).
Light circuit plate (7) is mounted on the bottom inner surface of casing of loudspeaker box-lower casing (6), and light diffusion sheet (8) is covered in
The lower section of light circuit plate (7), casing of loudspeaker box-lower casing (6) have partial notch, and light diffusion sheet (8) is embedded in notch, wherein
Housing is exposed on one side, so as to which light is uniformly diffused into outside by the translucent material characteristic of light diffusion sheet.Light electricity
Road plate (7) is made of at least one LED light and second circuit PCB.
Pedestal (9) is mounted on the bottom end of casing of loudspeaker box-lower casing (6).
Wherein, casing of loudspeaker box-upper casing (2) and casing of loudspeaker box-lower casing (6) can use plastic-injection structural member.
Sound-box device provided in this embodiment, according to the order of placement on the top by the sound-box device to bottom, successively
Include:Casing of loudspeaker box-upper casing (2), keypad component (1), mainboard (3), loud speaker (4), acoustics phase equalizer (5), lamp
Optical circuit board (7), light diffusion sheet (8), casing of loudspeaker box-lower casing (6) and pedestal (9), it is big on mainboard (3) to be equipped with quantity
In the microphone of 1, acoustics phase equalizer (5) and loud speaker (4) are mounted in the inner cavity of casing of loudspeaker box-lower casing (6).
It is achieved thereby that microphone and speaker to be integrated in the purpose of a sound-box device, the use cost of user is reduced, is also beneficial to
The routine use of user and cleaning.
In the present embodiment, light circuit plate (7) is loop configuration, and light diffusion sheet (8) is annular nesting type structure,
The size of light circuit plate (7) is identical with light diffusion sheet (8) and is nested in the inner ring of light diffusion sheet (8).Pedestal (9) it is straight
Footpath is less than the annular diameters of light diffusion sheet (8).
It is welded with the LED light of at least three kinds of colors and second circuit PCB on light circuit plate (7), LED light is for receiving the
The control of two circuit PCB simultaneously indicates a variety of working conditions.
By the nesting type structure of annular, the close journey of installation of light circuit plate (7) and light diffusion sheet (8) is enhanced
Degree, simplifies loudspeaker box structure and reduces production cost.
In the present embodiment, on the second circuit PCB, the LED light of 3 kinds of colors is installed, wherein, different colours
The flicker of LED light and the working condition for corresponding to a kind of sound-box device respectively is always on, the working condition includes:It is standby, open
It opens, wake up, in speech recognition.It should be noted that it is controlled for the light on and off of LED light.
The different operating status of speaker is shown by the LED light of different colours, the design for simplifying second circuit PCB is difficult
Degree, it is only necessary to can be realized by the corresponding electric signal of simple analog circuitry processes.Special control program need not be designed, so as to
The design difficulty of speaker is simplified, is also avoided due to the LED light mistake light on and off caused by software program is unstable the problem of.
In the present embodiment, light diffusion sheet (8) is made of macromolecule trnaslucent materials, it is therefore an objective to make what LED lamps were sent
Uniform light is spread, and enhances the dispersion effect of LED light.Pedestal (9) uses plastic structure component, and it is perpendicular that purpose enables sound equipment to consolidate
It stands in the planes such as table top, ground.Wherein, macromolecule trnaslucent materials, which is made, may be employed polymethyl methacrylate
(PMMA), phenylpropyl alcohol ethylene (PS), polyester (PET), makrolon (PC), poly(4-methyl-1-pentene) (TPX), polyacrylate
(PAR) and the common materials such as transparent epoxy resin.
In the present embodiment, the surface of casing of loudspeaker box-upper casing (2), the position perforate of corresponding microphone.Enable sound wave saturating
Arrival microphone receiving plane is crossed, so as to enhance the effect that microphone receives sound.
The surface of casing of loudspeaker box-lower casing (6), the position perforate of corresponding loud speaker (4) and acoustics phase equalizer (5), and
Sound mesh is covered out in perforate, in order to which the sound that loud speaker (4) is sent can effectively appear babinet.
In a preferred approach, acoustics phase equalizer (5) is conical acoustic wave Bragg Transducer for Waveguide Devices, for making loud speaker (4) outside
Make 360 ° of 0 diffusion of presentation during radiative acoustic wave.
In a preferred approach, the number of microphone installed on mainboard (3) is for as shown in Figure 42 or as shown in Figure 5
4.Microphone on mainboard (3) is uniformly distributed around the central point of mainboard (3).
A kind of microphone arrangement scheme is also provided in the present embodiment, which is characterized in that microphone is surrounded in mainboard (3)
Heart point is uniformly distributed;
Mainboard (3) is mounted in the inner cavity of casing of loudspeaker box-upper casing (2), and the wheat that quantity is more than 1 is equipped on mainboard (3)
Gram wind;
Keypad component (1) is made of at least one button and the first circuit PCB, and at least one button is mounted on institute
It states on the first circuit PCB, the first circuit PCB is used to receive the electric signal after at least one button is clicked, keypad group
Part (1) is fixed on the inner surface of casing of loudspeaker box-upper casing (2);
Acoustics phase equalizer (5) and loud speaker (4) are mounted in the inner cavity of casing of loudspeaker box-lower casing (6), acoustics phase etc.
Change device (5) and loud speaker (4) at a distance of predetermined distance, make to form gap between acoustics phase equalizer (5) and loud speaker (4);
Light circuit plate (7) is mounted on the bottom inner surface of casing of loudspeaker box-lower casing (6), and light diffusion sheet (8) is covered in
The lower section of light circuit plate (7), light circuit plate (7) are made of at least one LED light and second circuit PCB;
Pedestal (9) is mounted on the bottom end of casing of loudspeaker box-lower casing (6).
According to the order of placement on the top by the sound-box device to bottom, include successively:Casing of loudspeaker box-upper casing (2),
Keypad component (1), mainboard (3), loud speaker (4), acoustics phase equalizer (5), light circuit plate (7), light diffusion sheet
(8), casing of loudspeaker box-lower casing (6) and pedestal (9);
As shown in Figure 4, the number of microphone installed on mainboard (3) is for 2 or as shown in Figure 5, on mainboard (3)
The number of microphone of installation is 4.
Further, bluetooth and WIFI module are also equipped in speaker, WIFI is used for Internet service, and bluetooth sets for bluetooth
Audio when using for pairing and as wireless sound box receives.The embodiment of the present invention also provides a kind of speaker microphone arrangement scheme
Array structure, including:Microphone of the quantity more than 1 is uniformly distributed around the central point of mainboard (3), and the microphone is set
It puts on mainboard (3), microphone picks up sound (analog signal) and passes through ADC in real time is converted to digital signal (i.e. audio number
According to);The voice data is initially transmitted to local storage unit by integrated circuit built-in audio bus, then the sound built in ROM
Amount controls the echo program that disappears to pass through MCU microcontrollers;To microphone input signal progress computing and I/O management, and according to
Feedback control is needed to instruct.
For example, following steps specifically may be employed in the volume control echo program that disappears:
A) converted according to microphone input sensitivity and loud speaker output sensitivity and volume status, microphone receives signal
There is relatively-stationary short-time energy integration differential Δ between power amplifier output signal.
B) when someone's vocal input because the superposition of acoustic energy, microphone, which is received when signal can break this difference DELTA, (to be allowed
Δ has appropriate difference range, and difference range is preset according to ambient noise conditions, such as fan, washing machine, television set, outdoor automobile
Noise), MCU sends instruction and closes power amplifier output (Speaker Quiet reduces noise and echo) at this time, while it is defeated to improve microphone
Enter the gain of passage, accuracy and clarity so as to fulfill microphone pickup reduce the interference of noise.
C) then, speech analysis and synthesis are carried out for the signal of microphone acquisition, and is transferred to local voice identification system
System carries out voice wake-up (and fixed wake-up acoustic model compares).When the sound recognized is specific human voices unit --- it is i.e. pre-
During " wake-up word " the acoustic feature model put;It wakes up successfully.
D) while by transmitting voice signal to local carry out speech recognition (local None- identified is transferred to background network cloud
Identification service), and voice messaging or control instruction are fed back, if read statement completion needs speaker progress sound feedback, first
It is controlled by Intelligent volume and recovers power amplifier output gain, while backstage feedback voice is given to the power amplifier output of sound equipment.
E) as above a-b-c-d, cycle operation.
User usually requires to wear headset, but long periods of wear headset is also present with the problem of damaging hearing and in inflammation
It also is difficult to use headset in the weather of heat.In this case, user is usually required for buying microphone (microphone) and sound simultaneously
Case, and install to PC.2 kinds of equipment are purchased simultaneously, add the use cost of user, and the equipment used is more,
The management of the connecting line, power cord of desktop is also more chaotic, is unfavorable for routine use and the cleaning of user.
In existing product, there is also the speaker products classes that some are integrated with microphone (microphone) and loudspeaker (loud speaker)
Although design as can realize the integrated of microphone and loud speaker, but more be realized by way of windrow it is corresponding
Function there are complicated, produce and process the problem of with high costs, has ultimately resulted in the high use cost of user or even height
In the cost for purchasing 2 kinds of equipment simultaneously, therefore, it is difficult to mass produce and popularize.
Sound-box device provided in this embodiment, according to the order of placement on the top by the sound-box device to bottom, successively
Include:Casing of loudspeaker box-upper casing (2), keypad component (1), mainboard (3), loud speaker (4), acoustics phase equalizer (5), lamp
Optical circuit board (7), light diffusion sheet (8), casing of loudspeaker box-lower casing (6) and pedestal (9), it is big on mainboard (3) to be equipped with quantity
In the microphone of 1, acoustics phase equalizer (5) and loud speaker (4) are mounted in the inner cavity of casing of loudspeaker box-lower casing (6).
It is achieved thereby that microphone and speaker to be integrated in the purpose of a sound-box device, the use cost of user is reduced, is also beneficial to
The routine use of user and cleaning.And a kind of microphone array array structure of uniqueness is provided, passes through the Mike to negligible amounts
Wind carries out reasonable Arrangement, realizes the sound collection function of sound-box device.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Point just to refer each other, and the highlights of each of the examples are difference from other examples.It is real especially for equipment
For applying example, since it is substantially similar to embodiment of the method, so describing fairly simple, related part is referring to embodiment of the method
Part explanation.The above description is merely a specific embodiment, but protection scope of the present invention is not limited to
This, any one skilled in the art in the technical scope disclosed by the present invention, the variation that can readily occur in or replaces
It changes, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claim
Subject to enclosing.
Claims (10)
1. a kind of enhancing voice for intelligent sound box knows method for distinguishing, which is characterized in that including:
The voice signal received using microphone opens noise cancellation;
When the noise cancellation is opened, speaker volume is reduced by power amplifier control instruction;
After the voice messaging corresponding information to be played is got, by power amplifier recover instruction by speaker volume recover to
It is horizontal before reduction.
2. according to the method described in claim 1, it is characterized in that, described detect whether to open noise according to the voice signal
Function is eliminated, including:
According to the volume status of the input sensitivity of the microphone, the output sensitivity of the loud speaker and power amplifier, institute is obtained
State the energy integral difference between voice signal that microphone receives and the power amplifier output signal of the loud speaker;
When the variation of energy integral difference is more than preset range, noise cancellation is opened.
3. it according to the method described in claim 1, it is characterized in that, further includes:
When detecting in the voice signal containing preset range adjustment word, inquire about the preset range and adjust corresponding value
Section, and using the interval inquired as the preset range.
4. it according to the method described in claim 1, it is characterized in that, further includes:
When judging to need to send the power amplifier control instruction, send gain to the microphone and improve instruction, the gain carries
Height instructs to trigger the gain that the microphone improves input channel.
5. according to the method described in claim 1, it is characterized in that, it is described send power amplifier recover instruction, including:
After voice messaging is determined according to the voice signal, and detect crucial there are goal-selling in the information to be played
During word, send the power amplifier to the loud speaker and recover instruction;
After level before the speaker volume recovers to reduction, according to the information play cuing voice to be played.
6. according to the method described in claim 1, it is characterized in that, it is described send power amplifier recover instruction, including:
After voice messaging is determined according to the voice signal, the voice messaging is sent to cloud server;
After the prompt message of the cloud server feedback is received, send the power amplifier to the loud speaker and recover instruction;
According to the information of voice prompt, pass through the loud speaker play cuing voice.
7. method as claimed in any of claims 1 to 6, which is characterized in that further include:
After the power amplifier control instruction is sent, triggering timing device starts timing;
When timer reaches preset duration, then send power amplifier and recover instruction.
8. according to the method described in claim 1, it is characterized in that, described receive the voice signal that collects of microphone, including:
Voice signal by the reception microphone for connecting microphone array sound passage, the connection microphone array sound
Sound number of channels is 2 or 4.
9. a kind of intelligent sound box is with microcontroller (MCU), which is characterized in that including:
Memory module, wherein being stored with computer program;
Processing module is configured as running the computer program stored in the memory module, so that:
The voice signal received using microphone opens noise cancellation;
When the noise cancellation is opened, speaker volume is reduced by power amplifier control instruction;
When getting the corresponding information to be played of the voice messaging, instruction is recovered by power amplifier and recovers speaker volume to dropping
It is horizontal before low.
10. a kind of intelligent sound box, which is characterized in that including:
Casing of loudspeaker box, mainboard, loud speaker and microphone array, mainboard are arranged in casing of loudspeaker box, and loud speaker is connected with microphone
Mainboard;
Microcontroller (MCU) is provided on mainboard, the microcontroller (MCU) further comprises:
Memory module, wherein being stored with computer program;
Processing module is configured as running the computer program stored in the memory module, so that:
The voice signal received using microphone opens noise cancellation;
When the noise cancellation is opened, speaker volume is reduced by power amplifier control instruction;
When getting the corresponding information to be played of the voice messaging, instruction is recovered by power amplifier and recovers speaker volume to dropping
It is horizontal before low.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711084937.1A CN108064007A (en) | 2017-11-07 | 2017-11-07 | Know method for distinguishing and microcontroller and intelligent sound box for the enhancing voice of intelligent sound box |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711084937.1A CN108064007A (en) | 2017-11-07 | 2017-11-07 | Know method for distinguishing and microcontroller and intelligent sound box for the enhancing voice of intelligent sound box |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108064007A true CN108064007A (en) | 2018-05-22 |
Family
ID=62135018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711084937.1A Pending CN108064007A (en) | 2017-11-07 | 2017-11-07 | Know method for distinguishing and microcontroller and intelligent sound box for the enhancing voice of intelligent sound box |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108064007A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109087650A (en) * | 2018-10-24 | 2018-12-25 | 北京小米移动软件有限公司 | voice awakening method and device |
CN110278205A (en) * | 2019-06-19 | 2019-09-24 | 百度在线网络技术(北京)有限公司 | Baffle Box of Bluetooth pedestal and its control method and system |
CN111208736A (en) * | 2019-12-17 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Intelligent sound box control method and device, electronic equipment and storage medium |
US11151987B2 (en) * | 2018-06-29 | 2021-10-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and system for interacting with third-party application |
CN113853234A (en) * | 2019-04-03 | 2021-12-28 | Jk控股股份有限公司 | Device for acting on at least part of the body |
CN114173258A (en) * | 2022-02-07 | 2022-03-11 | 深圳市朗琴音响技术有限公司 | Intelligent sound box control method and intelligent sound box |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102945672A (en) * | 2012-09-29 | 2013-02-27 | 深圳市国华识别科技开发有限公司 | Voice control system for multimedia equipment, and voice control method |
CN103971680A (en) * | 2013-01-24 | 2014-08-06 | 华为终端有限公司 | Method and device for recognizing voices |
CN104064185A (en) * | 2013-03-18 | 2014-09-24 | 联想(北京)有限公司 | Information processing method and system and electronic device |
CN105702253A (en) * | 2016-01-07 | 2016-06-22 | 北京云知声信息技术有限公司 | Voice awakening method and device |
CN105960628A (en) * | 2014-06-24 | 2016-09-21 | 谷歌公司 | Dynamic threshold for speaker verification |
CN106504760A (en) * | 2016-10-26 | 2017-03-15 | 成都启英泰伦科技有限公司 | Broadband background noise and speech Separation detecting system and method |
CN106782591A (en) * | 2016-12-26 | 2017-05-31 | 惠州Tcl移动通信有限公司 | A kind of devices and methods therefor that phonetic recognization rate is improved under background noise |
CN106936991A (en) * | 2017-03-03 | 2017-07-07 | 深圳市金立通信设备有限公司 | The method and terminal of a kind of automatic regulating volume |
-
2017
- 2017-11-07 CN CN201711084937.1A patent/CN108064007A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102945672A (en) * | 2012-09-29 | 2013-02-27 | 深圳市国华识别科技开发有限公司 | Voice control system for multimedia equipment, and voice control method |
CN103971680A (en) * | 2013-01-24 | 2014-08-06 | 华为终端有限公司 | Method and device for recognizing voices |
CN104064185A (en) * | 2013-03-18 | 2014-09-24 | 联想(北京)有限公司 | Information processing method and system and electronic device |
CN105960628A (en) * | 2014-06-24 | 2016-09-21 | 谷歌公司 | Dynamic threshold for speaker verification |
CN105702253A (en) * | 2016-01-07 | 2016-06-22 | 北京云知声信息技术有限公司 | Voice awakening method and device |
CN106504760A (en) * | 2016-10-26 | 2017-03-15 | 成都启英泰伦科技有限公司 | Broadband background noise and speech Separation detecting system and method |
CN106782591A (en) * | 2016-12-26 | 2017-05-31 | 惠州Tcl移动通信有限公司 | A kind of devices and methods therefor that phonetic recognization rate is improved under background noise |
CN106936991A (en) * | 2017-03-03 | 2017-07-07 | 深圳市金立通信设备有限公司 | The method and terminal of a kind of automatic regulating volume |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11151987B2 (en) * | 2018-06-29 | 2021-10-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and system for interacting with third-party application |
CN109087650A (en) * | 2018-10-24 | 2018-12-25 | 北京小米移动软件有限公司 | voice awakening method and device |
CN113853234A (en) * | 2019-04-03 | 2021-12-28 | Jk控股股份有限公司 | Device for acting on at least part of the body |
CN110278205A (en) * | 2019-06-19 | 2019-09-24 | 百度在线网络技术(北京)有限公司 | Baffle Box of Bluetooth pedestal and its control method and system |
US10950238B2 (en) | 2019-06-19 | 2021-03-16 | Baidu Online Network Technology (Beijing) Co., Ltd. | Bluetooth speaker base, method and system for controlling thereof |
CN111208736A (en) * | 2019-12-17 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Intelligent sound box control method and device, electronic equipment and storage medium |
CN111208736B (en) * | 2019-12-17 | 2023-10-27 | 中移(杭州)信息技术有限公司 | Intelligent sound box control method and device, electronic equipment and storage medium |
CN114173258A (en) * | 2022-02-07 | 2022-03-11 | 深圳市朗琴音响技术有限公司 | Intelligent sound box control method and intelligent sound box |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108064007A (en) | Know method for distinguishing and microcontroller and intelligent sound box for the enhancing voice of intelligent sound box | |
US8081765B2 (en) | Volume adjusting system and method | |
CN105338459A (en) | MEMS (Micro-Electro-Mechanical System) microphone and signal processing method thereof | |
CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
CN107134286A (en) | ANTENNAUDIO player method, music player and storage medium based on interactive voice | |
CN105280195A (en) | Method and device for processing speech signal | |
CN105379308A (en) | VAD detection microphone and method of operating the same | |
JP4897169B2 (en) | Voice recognition device and consumer electronic system | |
CN103024630A (en) | Volume regulating method of first electronic equipment and first electronic equipment | |
CN113630708B (en) | Method and device for detecting abnormal earphone microphone, earphone kit and storage medium | |
WO2020048431A1 (en) | Voice processing method, electronic device and display device | |
CN106782519A (en) | A kind of robot | |
CN108447483B (en) | speech recognition system | |
CN108712566A (en) | A kind of voice assistant awakening method and mobile terminal | |
CN207530995U (en) | Sound-box device and its microphone array array structure | |
CN110349582A (en) | Display device and far field speech processing circuit | |
CN206283621U (en) | A kind of intelligent remote controller | |
CN109243426A (en) | A kind of automatization judgement voice false wake-up system and its judgment method | |
CN208538474U (en) | Speech recognition system | |
CN113516975A (en) | Intelligent household voice-operated switch system and control method | |
CN106647545A (en) | Target sound obtaining device and method and intelligent assembly by using same | |
CN105718165A (en) | Startup method and device of terminal background application | |
CN106653060B (en) | Air blowing sound identification system and air blowing identification method adopting same | |
CN104766610A (en) | Voice recognition system and method based on vibration | |
CN213028445U (en) | Intelligent sound box |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180522 |
|
RJ01 | Rejection of invention patent application after publication |