CN113727242A - Online pickup main power unit and method and wearable device - Google Patents
Online pickup main power unit and method and wearable device Download PDFInfo
- Publication number
- CN113727242A CN113727242A CN202111006604.3A CN202111006604A CN113727242A CN 113727242 A CN113727242 A CN 113727242A CN 202111006604 A CN202111006604 A CN 202111006604A CN 113727242 A CN113727242 A CN 113727242A
- Authority
- CN
- China
- Prior art keywords
- microphone
- resistor
- unit
- signal
- voice
- 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.)
- Granted
Links
Images
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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/87—Detection of discrete points within a voice signal
-
- 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
- H04R1/08—Mouthpieces; Microphones; Attachments therefor
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The application discloses an online pickup main power unit, a method and wearable equipment, wherein the circuit is applied to the wearable equipment and comprises a bone voiceprint sensor, a microphone and a microphone power supply control circuit; the microphone power supply control circuit is connected between the output end of the bone voiceprint sensor and the power supply end of the microphone and used for starting the microphone to pick up voice signals after the bone voiceprint sensor picks up vibration signals of bones when a wearable device wearer speaks. This application awakens up the microphone pickup according to the output of bone vocal print sensor, so both avoided the microphone of high-power consumption to increase the energy consumption because of lasting work, can in time start the microphone again when the user speaks, prevent that voice signal from missing to examine, realized being online at any time of pickup function, greatly improved user experience.
Description
Technical Field
The application relates to the technical field of voice recognition, in particular to an online pickup main electrical unit, an online pickup method and wearable equipment.
Background
With the development of the technology, a man-machine interaction mode has been developed from initial card-band interaction, keyboard interaction to touch screen interaction, or even more intelligent voice interaction at present, and many smart wearable devices are equipped with a voice interaction function and can execute corresponding operations according to a voice instruction sent by a user.
A Microphone (MIC) is a common pickup device. After the microphone picks up sound, the voice signal is sent to the voice module for voice recognition, and the power consumption of the process is relatively large. Therefore, in order to avoid excessive power consumption, an active button is generally required to turn on the sound collecting function of the microphone in the related art, so that always-on sound collection of the sound collecting function, namely always on sound collection, cannot be realized. Moreover, after the sound pickup function is turned on, environmental noise, sounds made by other people and the like can also interfere with voice recognition in the prior art, so that the voice recognition rate is not high, voice instructions made by a user cannot be timely and correctly responded, and the user experience is reduced.
In view of the above, it is an important need for those skilled in the art to provide a solution to the above technical problems.
Disclosure of Invention
The application aims to provide an online sound pickup main unit, an online sound pickup method and wearable equipment, so that the function of picking up sound at any time can be provided under the condition that power consumption is not influenced.
In order to solve the technical problem, in one aspect, the application discloses an online pickup main electrical unit applied to wearable equipment, wherein the online pickup main electrical unit comprises a bone voiceprint sensor, a microphone and a microphone power supply control circuit;
the microphone power supply control circuit is connected between the output end of the bone voiceprint sensor and the power supply end of the microphone and used for starting the microphone to pick up voice signals after the bone voiceprint sensor picks up vibration signals of bones when a wearable device wearer speaks.
Optionally, the microphone power supply control circuit comprises:
the signal amplification unit is used for carrying out power amplification on the vibration signal;
the bootstrap unit is connected with the signal amplification unit and is used for outputting a driving signal based on the vibration signal after power amplification;
the switch unit is connected with the bootstrap unit and used for closing a power switch of the microphone based on the driving signal;
and the time delay unit is connected with the bootstrap unit and used for absorbing energy from the driving signal so as to delay the switch closing action of the switch unit.
Optionally, the signal amplification unit includes a first capacitor, a second capacitor, a first resistor, a second resistor, and an operational amplifier;
the positive input end of the operational amplifier is connected with a reference voltage, and the negative input end of the operational amplifier is connected with the output end of the bone voiceprint sensor through the first capacitor and the first resistor which are connected in series; the second capacitor and the second resistor are connected in parallel between the negative input end and the output end of the operational amplifier.
Optionally, the bootstrap unit includes a third capacitor, a third resistor, a fourth resistor, and a first switching tube, and the first switching tube is turned on at a high level;
the control end of the first switch tube is connected with the output end of the operational amplifier through the third capacitor and the third resistor which are connected in series, and the input end of the first switch tube is connected to a power supply through the fourth resistor.
Optionally, the switch unit includes a fifth resistor, a sixth resistor, a seventh resistor, an eighth resistor, a second switch tube, and a third switch tube; the high level of the second switching tube is switched on, and the low level of the third switching tube is switched on;
the control end of the second switching tube is connected to the output end of the first switching tube through the fifth resistor and is grounded through the sixth resistor; the output end of the second switching tube is grounded;
the input end of the second switching tube is connected to the control end of the third switching tube through the seventh resistor; the input end of the third switching tube is connected to a power supply; the output end of the third switching tube is connected to the power supply end of the microphone; and the eighth resistor is connected between the input end and the control end of the third switching tube.
Optionally, the delay unit includes a fourth capacitor and a ninth resistor, and the fourth capacitor and the ninth resistor are both connected in parallel between the output end of the second switch tube and the ground line.
Optionally, the method further comprises:
and the voice chip is respectively connected with the bone voiceprint sensor and the microphone, and is used for performing signal fusion processing on the received vibration signal and the voice signal and performing voice recognition based on the fused processing signal.
Optionally, the voice chip includes a voice activity detection unit and a microprocessor; and the voice activity detection unit is used for awakening the microprocessor to perform signal fusion processing according to the voice activity detection result of the vibration signal.
In another aspect, the application also discloses an online pickup method, which is applied to wearable equipment, wherein a bone voiceprint sensor, a microphone and a microphone power supply control circuit are arranged in the wearable equipment; the method comprises the following steps:
monitoring vibration signals of bones when a wearable device wearer speaks in real time based on the bone voiceprint sensor;
after the vibration signal is picked up, the microphone is started to pick up a voice signal through the microphone power supply control circuit.
In yet another aspect, the present application further discloses a wearable device comprising any one of the online pickup master units described above.
The online pickup main electrical unit, the online pickup method and the wearable device have the advantages that: this application can awaken up the microphone pickup according to the output of bone voiceprint sensor automatically based on relevant circuit, so both avoided the microphone of high-power consumption to increase the energy consumption because of lasting work, can in time start the microphone again when the user speaks, prevent that speech signal from missing and examine, realized being online at any time of pickup function, greatly improved user experience.
Drawings
In order to more clearly illustrate the technical solutions in the prior art and the embodiments of the present application, the drawings that are needed to be used in the description of the prior art and the embodiments of the present application will be briefly described below. Of course, the following description of the drawings related to the embodiments of the present application is only a part of the embodiments of the present application, and it will be obvious to those skilled in the art that other drawings can be obtained from the provided drawings without any creative effort, and the obtained other drawings also belong to the protection scope of the present application.
Fig. 1 is a block diagram illustrating an on-line pickup main power unit according to the prior art;
fig. 2 is a block diagram of a main online pickup unit according to an embodiment of the present disclosure;
fig. 3 is a block diagram of a structure of another online pickup master unit disclosed in the embodiment of the present application;
fig. 4 is a circuit diagram of a microphone power control circuit according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a speech recognition process disclosed in an embodiment of the present application;
fig. 6 is a flowchart of an online sound pickup method according to an embodiment of the present application.
Detailed Description
The core of the application is to provide an online sound pickup main power unit, a method and wearable equipment so as to provide a function of picking up sound at any time under the condition of not influencing power consumption.
In order to more clearly and completely describe the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Currently, many smart wearable devices are equipped with a voice interaction function, and can perform corresponding operations according to voice instructions issued by a user. Referring to fig. 1, fig. 1 is a block diagram of a microphone pickup scheme disclosed in the prior art.
As shown in fig. 1, the microphone picks up human voice and environmental sound, outputs a corresponding voice signal to wake up the voice chip, and the voice chip performs voice recognition on the voice signal. The power consumption of the voice chip is relatively large, and is about several to several hundred mA. The main power consumption in the whole framework is a voice chip, and the MIC is the second power consumption; therefore, it is necessary to reduce the malfunction of the voice chip even after the sound pickup function is turned on, and the power consumption increases geometrically once the voice chip is run.
At present, in order to avoid excessive power consumption, an active key is generally needed to turn on the sound pickup function of a microphone in the related art, so that always-on sound pickup, namely always on sound pickup, of the sound pickup function cannot be realized. Moreover, after the sound pickup function is turned on, environmental noise, sounds made by other people and the like can also interfere with voice recognition in the prior art, so that the voice recognition rate is not high, voice instructions made by a user cannot be timely and correctly responded, and the user experience is reduced.
In view of this, the present application provides an online sound pickup scheme, which can effectively solve the above problems.
Referring to fig. 2, the embodiment of the present application discloses an online sound pickup main unit, which is applied to a wearable device, and includes a bone voiceprint sensor (VPU) 100, a Microphone (MIC) 200, and a microphone power control circuit 300;
the microphone power control circuit 300 is connected between the output end of the bone voiceprint sensor 100 and the power end of the microphone 200, and is used for starting the microphone 200 to pick up a voice signal after the bone voiceprint sensor 100 picks up a vibration signal of a bone when the wearable device wearer speaks.
In particular, the online sound pickup main unit disclosed in the present application may be specifically applied to wearable devices with sound pickup function requirements, including but not limited to earphones, AR (Augmented Reality) products, VR (Virtual Reality) products, and the like. It should be noted that the present application makes particular use of the bone voiceprint sensor to participate in controlling the pick-up of the microphone. The bone voiceprint sensor is arranged in the online pickup main electrical unit of the wearable device, so that the bone voiceprint information of a wearer of the wearable device during speaking can be accurately acquired. The bone conduction technology converts sound into mechanical vibration with different frequencies, and transmits sound waves through skull, bone labyrinth, inner ear lymph fluid transmission, spiral organ, auditory nerve and auditory center of human beings.
There are several advantages to assisting speech recognition based on a bone voiceprint sensor. First, it is easy to understand that the speed of sound transmitted through a solid is much higher than the speed of sound transmitted through air, and the attenuation is much less, so that the information retention based on the vibration signal obtained by the bone voiceprint sensor is considerable.
Secondly, the bone voiceprint sensor only senses the vibration conducted by the head bone and the like of the wearable device wearer, so that the false triggering caused by environmental noise or the voice of other people can be effectively avoided, and the voice recognition rate of the user can be effectively improved.
In addition, the bone voiceprint sensor has low power consumption, and can respond to the voice command of a wearer in real time on line at any time. Therefore, the application enables the bone voiceprint sensor to monitor in real time, and the microphone is awakened to work through the output of the bone voiceprint sensor. So, this application can realize the always on of pickup function on the one hand, and on the other hand can effectively reduce the great mistake of connecing the components and parts (like microphone, pronunciation chip) and trigger behind the consumption to reduce the overall consumption of system.
The microphone power supply control circuit is used for controlling the microphone to be turned on according to the output signal of the bone voiceprint sensor. As the name implies, the microphone power supply control circuit is a circuit which is composed of circuit components and used for controlling the microphone to be powered on. It will be readily understood by those skilled in the art that the relevant component parameters in the circuit may determine how long after the bone voiceprint sensor has an output the microphone is powered on. Therefore, a person skilled in the art can increase or decrease the action delay time of the microphone power supply control circuit by adjusting parameters of related components so as to meet the requirement on the on-line sound pickup function of the microphone.
It is easy to understand that because the microphone is automatically powered on by a pure hardware circuit, compared with a software method for starting the microphone, the method can effectively save the processing power consumption and time delay for power on confirmation by using a software algorithm; in addition, the delay time can be further adjusted by adjusting circuit parameters, and the requirements of various practical application conditions are met.
Therefore, the on-line pickup main power unit disclosed by the embodiment of the application can automatically wake up the microphone for pickup according to the output of the bone voiceprint sensor based on the related circuit, so that the energy consumption of the microphone with high power consumption is prevented from being increased due to continuous work, the microphone can be started in time when a user speaks, the voice signal is prevented from being missed for detection, the pickup function is realized to be on line at any time, and the user experience is greatly improved.
Referring to fig. 3, fig. 3 is a block diagram of a structure of another online sound pickup main unit disclosed in the embodiment of the present application.
As shown in fig. 3, as a specific embodiment, the on-line sound pickup master unit disclosed in the embodiment of the present application, on the basis of the above contents, the microphone power supply control circuit 300 includes:
a signal amplification unit 301 for performing power amplification on the vibration signal;
the bootstrap unit 302 is connected to the signal amplification unit 301, and is configured to output a driving signal based on the power-amplified vibration signal;
a switch unit 303 connected to the bootstrap unit 302, for closing a power switch of the microphone based on the driving signal;
and a delay unit 304 connected to the bootstrap unit 302 for absorbing energy from the driving signal to delay the switch closing action of the switch unit.
Specifically, the signal amplification unit 301 amplifies a signal output by the VPU based on the operational amplifier a, and then outputs the amplified signal to the bootstrap unit 302. The signal amplification unit 301 may specifically select a low power consumption operational amplifier a, and the power consumption is generally in the range of several hundred nA to several tens uA. The bootstrap unit 302 is mainly used to output a driving signal (generally raising level) with a corresponding level so as to drive the switch tube in the back-end switch unit 303 to turn on or off the power supply of the MIC. The power consumption of the bootstrap unit 302 and the switch unit 303 is relatively low, and is set according to the resistance value and the capacitance value, which is generally several uA. The delay unit 304 is capable of adjusting the delay time for the switch unit 303 to turn on the MIC power supply, i.e. the delay time is adjustable with the circuit parameters of the delay unit. When the circuit parameters of the circuit components of the delay unit 304 change, the delay time of the power-on of the microphone also changes.
Referring to fig. 4, fig. 4 is a circuit structure diagram of a microphone power control circuit according to an embodiment of the present disclosure. As a specific embodiment, based on the above, as shown in fig. 4, the on-line sound pickup main unit disclosed in the embodiments of the present application includes a signal amplifying unit 301, which includes a first capacitor C1, a second capacitor C2, a first resistor R1, a second resistor R2, and an operational amplifier a;
the positive input end of the operational amplifier A is connected with a reference voltage Vref, and the negative input end of the operational amplifier A is connected with the output end of the bone voiceprint sensor through a first capacitor C1 and a first resistor R1 which are connected in series; the second capacitor C2 and the second resistor R2 are connected in parallel between the negative input end and the output end of the operational amplifier A.
Specifically, the magnitude of the reference voltage Vref determines the potential of the positive input terminal of the operational amplifier a, so the difference between the reference voltage and the output voltage of the bone-vocal print sensor and the amplification factor of the signal amplification unit further affect the magnitude of the output voltage of the operational amplifier a. Generally, the reference voltage may be 3.3V, which is commonly used. In addition, the value of R2/R1 is the amplification factor of the signal amplification unit, and the amplification factor of the signal can be adjusted by adjusting the resistance values of R2 and R1; the larger the multiple, the less signal energy is required to open the back-end circuit switch tube.
As a specific embodiment, based on the above contents, the main online sound pickup unit disclosed in the embodiments of the present application includes that the bootstrap unit 302 includes a third capacitor C3, a third resistor R3, a fourth resistor R4, and a first switch tube, and the first switch tube is turned on at a high level;
the control end of the first switch tube is connected with the output end of the operational amplifier A through a third capacitor C3 and a third resistor R3 which are connected in series, and the input end of the first switch tube is connected to the power supply through a fourth resistor R4.
In fig. 4, Q1 is embodied as an NPN-type transistor, with a base as a control terminal, a collector as an input terminal, and an emitter as an output terminal. When the VPU output vibration signal is amplified by the signal amplification unit 301, Q1 is turned on, and the emitter thereof outputs a high-level driving signal.
Further, the bootstrap unit 302 may further include a voltage regulator tube D, a cathode of the voltage regulator tube D is connected to the control end of the first switch tube, and an anode of the voltage regulator tube D is connected to the output end of the first switch tube, so as to perform voltage regulation protection on the first switch tube. Of course, one skilled in the art can also use NMOS transistors as Q1; alternatively, a person skilled in the art may select and use the first switch tube turned on by a low level in cooperation with the high-low level conversion circuit, which is not limited in the present application.
As a specific embodiment, the on-line sound pickup main unit disclosed in the embodiments of the present application is based on the above, and the switch unit 303 includes a fifth resistor R5, a sixth resistor R6, a seventh resistor R7, an eighth resistor R8, a second switch tube, and a third switch tube; the high level of the second switching tube is switched on, and the low level of the third switching tube is switched on;
the control end of the second switch tube is connected to the output end of the first switch tube through a fifth resistor R5 and is grounded through a sixth resistor R6; the output end of the second switching tube is grounded;
the input end of the second switching tube is connected to the control end of the third switching tube through a seventh resistor R7; the input end of the third switching tube is connected to a power supply; the output end of the third switching tube is connected to the power supply end of the microphone; the eighth resistor R8 is connected between the input terminal and the control terminal of the third switching tube.
Specifically, in fig. 4, Q2 is an NPN transistor, and has a base as a control terminal, a collector as an input terminal, and an emitter as an output terminal. When the base voltage of Q2 is greater than the threshold voltage of Q3578, Q2 is turned on to ground after the emitter of Q1 outputs a high-level driving signal. Setting the resistance of R8 to be much larger than R7, R7 connected to Q2 is also pulled down to low level. For example, R8 may be specifically set to 1000K Ω and R7 may be set to 100K Ω.
The Q3 is used as a switching tube for low level turn-on, and may specifically be a PMOS tube, with a gate as a control end, a source as an input end, and a drain as an output end. When Q2 is turned on, the gate voltage of Q3 is pulled low, so that Q3 is turned on, and the MIC is powered on to pick up sound.
As a specific embodiment, in the on-line sound pickup main unit disclosed in the embodiments of the present application, on the basis of the above, the delay unit 304 includes a fourth capacitor C4 and a ninth resistor R9, and both the fourth capacitor C4 and the ninth resistor R9 are connected in parallel between the output end of the second switch tube and the ground.
Specifically, the capacitor has the functions of storing energy and stabilizing voltage, and the voltage is raised when the electric quantity is enough. Therefore, the larger the capacitance of C4 and the smaller the resistance of R9, the longer the delay time, and thus more waveforms of driving signals are required to turn on Q2 and thus turn on MIC. That is, the circuit parameters affecting the delay period include the capacitance of C4 and the resistance of R9. For example, by adjusting the magnitudes of C4 and R9, Q2 is turned on after Q1 outputs a waveform of 5 cycles; alternatively, the Q2 can be turned on after the Q1 outputs a waveform of 2 cycles by adjusting the magnitudes of C4 and R9.
As a specific embodiment, the online sound pickup main unit disclosed in the embodiment of the present application further includes, on the basis of the foregoing content:
and the voice chip 400 is respectively connected with the bone voiceprint sensor 100 and the microphone 200, and is used for performing signal fusion processing on the received vibration signal and the received voice signal and performing voice recognition based on the fused processing signal.
In particular, the human voice pickup may then be further used for speech recognition. In the embodiment, a voice chip is further arranged, and after the bone voiceprint sensor detects that the wearer speaks and outputs a vibration signal, on one hand, the microphone is controlled to be powered on, and on the other hand, the voice chip is awakened to process. It should be pointed out that, the speech chip in this application will use the vibration signal of bone voiceprint sensor output and the speech signal of microphone pickup output simultaneously as the basis, carries out speech recognition after signal fusion with two signals again. And further, the information fusion can be carried out after the vibration signal and the voice signal are subjected to the adaptive filtering. Specifically, referring to fig. 5, fig. 5 is a schematic diagram illustrating a speech recognition process according to an embodiment of the present disclosure.
Although the bone voiceprint sensor can accurately pick up the speaking vibration signal of the wearer, the bone voiceprint sensor has narrower bandwidth and less voice information compared with a microphone; the microphone, although susceptible to ambient noise and other persons' voices, can receive a wide signal band. Therefore, the method and the device combine the two signals to perform voice recognition, can effectively remove noise, can also completely restore the voice signals as much as possible, and can effectively improve the accuracy of voice recognition.
As a specific embodiment, the online sound pickup master unit disclosed in the embodiment of the present application is based on the above, and the Voice chip 400 includes a Voice Activity Detection (VAD) unit and a microprocessor; the voice activity detection unit is used for awakening the microprocessor to perform signal fusion processing according to the voice activity detection result of the vibration signal.
Voice activity detection, VAD also known as voice endpoint detection, voice boundary detection, aims to identify and eliminate long periods of silence from the voice signal stream to achieve the effect of saving voice channel resources without reducing the quality of service. When the detection value of the VAD unit for the voice activity reaches a certain threshold value, the microprocessor of the voice chip can be awakened. Generally, the microprocessor may be embodied as a DSP (Digital Signal Processing).
Referring to fig. 6, an embodiment of the present application discloses an online sound pickup method, which is applied to a wearable device, where the wearable device includes a bone and vocal print sensor, a microphone power control circuit, and a voice chip; the method comprises the following steps:
s101: the method comprises the steps of detecting vibration signals of bones when a wearable device wearer speaks in real time based on a bone voiceprint sensor.
S102: after the vibration signal is picked up, the microphone is started to pick up a voice signal through the microphone power supply control circuit.
Therefore, the online pickup method can automatically awaken the microphone for pickup according to the output of the bone voiceprint sensor based on the related circuit, so that the problem that the microphone with high power consumption is increased in energy consumption due to continuous work is avoided, the microphone can be started in time when a user speaks, voice signals are prevented from being missed for detection, the pickup function is online at any time, and the user experience is greatly improved.
As a specific embodiment, the wearable device further comprises a voice chip connected to the bone voiceprint sensor and the microphone respectively; on the basis of the above contents, the online sound pickup method provided by the embodiment of the application further includes:
the vibration signal and the voice signal are processed by signal fusion based on the voice chip,
and performing voice recognition based on the signal fusion processing result based on the voice chip.
As a specific embodiment, the voice chip includes a voice activity detection unit and a microprocessor; on the basis of the above contents, the online pickup method provided by the embodiment of the application performs signal fusion processing on the vibration signal and the voice signal based on the voice chip, and includes:
performing voice activity detection on the vibration signal based on the voice activity detection unit;
and awakening the microprocessor to perform signal fusion processing according to the voice activity detection result.
For the details of the voice recognition method, reference may be made to the above detailed description of the on-line pickup master unit, which is not repeated herein.
Further, the embodiment of the application also discloses a wearable device, which comprises any one of the online pickup main power units.
For details of the wearable device, reference may be made to the above detailed description of the on-line pickup main unit, which is not repeated here.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the equipment disclosed by the embodiment, the description is relatively simple because the equipment corresponds to the method disclosed by the embodiment, and the relevant parts can be referred to the method part for description.
It is further noted that, throughout this document, relational terms such as "first" and "second" are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The technical solutions provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall into the protection scope of the present application.
Claims (10)
1. The on-line pickup main power unit is applied to wearable equipment and comprises a bone voiceprint sensor, a microphone and a microphone power supply control circuit;
the microphone power supply control circuit is connected between the output end of the bone voiceprint sensor and the power supply end of the microphone and used for starting the microphone to pick up voice signals after the bone voiceprint sensor picks up vibration signals of bones when a wearable device wearer speaks.
2. The on-line pickup master electrical unit of claim 1, wherein the microphone power control circuit comprises:
the signal amplification unit is used for carrying out power amplification on the vibration signal;
the bootstrap unit is connected with the signal amplification unit and is used for outputting a driving signal based on the vibration signal after power amplification;
the switch unit is connected with the bootstrap unit and used for closing a power switch of the microphone based on the driving signal;
and the time delay unit is connected with the bootstrap unit and used for absorbing energy from the driving signal so as to delay the switch closing action of the switch unit.
3. The on-line pickup master unit according to claim 2, wherein the signal amplification unit comprises a first capacitor, a second capacitor, a first resistor, a second resistor and an operational amplifier;
the positive input end of the operational amplifier is connected with a reference voltage, and the negative input end of the operational amplifier is connected with the output end of the bone voiceprint sensor through the first capacitor and the first resistor which are connected in series; the second capacitor and the second resistor are connected in parallel between the negative input end and the output end of the operational amplifier.
4. The on-line pickup master unit according to claim 3, wherein the bootstrap unit includes a third capacitor, a third resistor, a fourth resistor and a first switch tube, and the first switch tube is turned on at a high level;
the control end of the first switch tube is connected with the output end of the operational amplifier through the third capacitor and the third resistor which are connected in series, and the input end of the first switch tube is connected to a power supply through the fourth resistor.
5. The on-line pickup master unit according to claim 4, wherein the switch unit comprises a fifth resistor, a sixth resistor, a seventh resistor, an eighth resistor, a second switch tube and a third switch tube; the high level of the second switching tube is switched on, and the low level of the third switching tube is switched on;
the control end of the second switching tube is connected to the output end of the first switching tube through the fifth resistor and is grounded through the sixth resistor; the output end of the second switching tube is grounded;
the input end of the second switching tube is connected to the control end of the third switching tube through the seventh resistor; the input end of the third switching tube is connected to a power supply; the output end of the third switching tube is connected to the power supply end of the microphone; and the eighth resistor is connected between the input end and the control end of the third switching tube.
6. The on-line pickup master unit according to claim 5, wherein the delay unit comprises a fourth capacitor and a ninth resistor, and the fourth capacitor and the ninth resistor are both connected in parallel between the output end of the second switching tube and the ground line.
7. The on-line pickup master unit according to any one of claims 1 to 6, further comprising:
and the voice chip is respectively connected with the bone voiceprint sensor and the microphone, and is used for performing signal fusion processing on the received vibration signal and the voice signal and performing voice recognition based on the fused processing signal.
8. The online pickup master unit according to claim 7, wherein the voice chip comprises a voice activity detection unit and a microprocessor; and the voice activity detection unit is used for awakening the microprocessor to perform signal fusion processing according to the voice activity detection result of the vibration signal.
9. The online pickup method is characterized by being applied to wearable equipment, wherein a bone voiceprint sensor, a microphone and a microphone power supply control circuit are arranged in the wearable equipment; the method comprises the following steps:
monitoring vibration signals of bones when a wearable device wearer speaks in real time based on the bone voiceprint sensor;
after the vibration signal is picked up, the microphone is started to pick up a voice signal through the microphone power supply control circuit.
10. A wearable device comprising the online pickup master unit of any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111006604.3A CN113727242B (en) | 2021-08-30 | 2021-08-30 | Online pickup main power unit and method and wearable device |
| PCT/CN2021/138586 WO2023029296A1 (en) | 2021-08-30 | 2021-12-16 | Online voice pickup main electrical unit, method and wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111006604.3A CN113727242B (en) | 2021-08-30 | 2021-08-30 | Online pickup main power unit and method and wearable device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113727242A true CN113727242A (en) | 2021-11-30 |
| CN113727242B CN113727242B (en) | 2022-11-04 |
Family
ID=78679293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111006604.3A Active CN113727242B (en) | 2021-08-30 | 2021-08-30 | Online pickup main power unit and method and wearable device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113727242B (en) |
| WO (1) | WO2023029296A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023029296A1 (en) * | 2021-08-30 | 2023-03-09 | 歌尔股份有限公司 | Online voice pickup main electrical unit, method and wearable device |
| WO2024066962A1 (en) * | 2022-09-28 | 2024-04-04 | 华为技术有限公司 | Respiratory health detection method and wearable electronic device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104144377A (en) * | 2013-05-09 | 2014-11-12 | Dsp集团有限公司 | Low power activation of voice activated device |
| CN106686494A (en) * | 2016-12-27 | 2017-05-17 | 广东小天才科技有限公司 | Voice input control method of wearable equipment and the wearable equipment |
| CN108882087A (en) * | 2018-06-12 | 2018-11-23 | 歌尔科技有限公司 | A kind of intelligent sound detection method, wireless headset, TWS earphone and terminal |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006025079A (en) * | 2004-07-07 | 2006-01-26 | Nec Tokin Corp | Head set and wireless communication system |
| CN112767963B (en) * | 2021-01-28 | 2022-11-25 | 歌尔科技有限公司 | Voice enhancement method, device and system and computer readable storage medium |
| CN112929777B (en) * | 2021-02-05 | 2023-03-28 | 英华达（上海）科技有限公司 | Audio signal processing method and device and electronic equipment |
| CN113727242B (en) * | 2021-08-30 | 2022-11-04 | 歌尔科技有限公司 | Online pickup main power unit and method and wearable device |
-
2021
- 2021-08-30 CN CN202111006604.3A patent/CN113727242B/en active Active
- 2021-12-16 WO PCT/CN2021/138586 patent/WO2023029296A1/en unknown
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104144377A (en) * | 2013-05-09 | 2014-11-12 | Dsp集团有限公司 | Low power activation of voice activated device |
| CN106686494A (en) * | 2016-12-27 | 2017-05-17 | 广东小天才科技有限公司 | Voice input control method of wearable equipment and the wearable equipment |
| CN108882087A (en) * | 2018-06-12 | 2018-11-23 | 歌尔科技有限公司 | A kind of intelligent sound detection method, wireless headset, TWS earphone and terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023029296A1 (en) * | 2021-08-30 | 2023-03-09 | 歌尔股份有限公司 | Online voice pickup main electrical unit, method and wearable device |
| WO2024066962A1 (en) * | 2022-09-28 | 2024-04-04 | 华为技术有限公司 | Respiratory health detection method and wearable electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023029296A1 (en) | 2023-03-09 |
| CN113727242B (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113727242B (en) | Online pickup main power unit and method and wearable device | |
| CN106782591B (en) | Device and method for improving speech recognition rate under background noise | |
| US9326063B2 (en) | Microphone with voice wake-up function | |
| CN107403621B (en) | Voice wake-up device and method | |
| CN204390737U (en) | A kind of home voice disposal system | |
| CN111161714B (en) | Voice information processing method, electronic equipment and storage medium | |
| CN103901782B (en) | A kind of acoustic-controlled method, electronic equipment and sound-controlled apparatus | |
| CN110473544A (en) | A kind of low-power consumption voice awakening method and device | |
| CN106782519A (en) | A kind of robot | |
| CN109040905A (en) | A kind of low-power consumption speaker and its working method | |
| CN111837179A (en) | System and method for capturing noise for pattern recognition processing | |
| CN108447483A (en) | Speech recognition system | |
| CN110322880A (en) | Vehicle-mounted terminal equipment and the method for waking up its multiple interactive voice program | |
| CN205160755U (en) | Headphone structure device, earphone and wearable equipment | |
| CN104780483A (en) | Microphone with voice activity detection function | |
| US10488831B2 (en) | Biopotential wakeup word | |
| CN104615252A (en) | Control method, control device, wearable electronic device and electronic equipment | |
| CN102693721A (en) | Simple and easy voice and gender detection device and method | |
| CN205408096U (en) | Digital microphone wind and electronic equipment | |
| JP2798620B2 (en) | Training method for speech recognition system | |
| CN208538474U (en) | Speech recognition system | |
| CN201118956Y (en) | An earphone with noise reduction function | |
| CN105232038A (en) | Brain wave analysis method and apparatus based on intelligent headset | |
| CN112995833B (en) | Earphone voice collecting method, earphone and readable storage medium | |
| CN210265228U (en) | Fan controller based on AI pronunciation chip |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |