WO2022147905A1 - 一种优化骨传导耳机工作状态的方法 - Google Patents
一种优化骨传导耳机工作状态的方法 Download PDFInfo
- Publication number
- WO2022147905A1 WO2022147905A1 PCT/CN2021/082493 CN2021082493W WO2022147905A1 WO 2022147905 A1 WO2022147905 A1 WO 2022147905A1 CN 2021082493 W CN2021082493 W CN 2021082493W WO 2022147905 A1 WO2022147905 A1 WO 2022147905A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- earphone
- bone conduction
- user
- core
- vibration
- Prior art date
Links
- 210000000988 bone and bone Anatomy 0.000 title claims abstract description 473
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000004044 response Effects 0.000 claims abstract description 290
- 230000005236 sound signal Effects 0.000 claims abstract description 60
- 238000012549 training Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 13
- 238000003066 decision tree Methods 0.000 claims description 8
- 238000012417 linear regression Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 10
- 238000010801 machine learning Methods 0.000 description 10
- 230000035790 physiological processes and functions Effects 0.000 description 10
- 238000001514 detection method Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 210000003128 head Anatomy 0.000 description 6
- 238000007637 random forest analysis Methods 0.000 description 6
- 230000001133 acceleration Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007477 logistic regression Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 210000003625 skull Anatomy 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 210000003477 cochlea Anatomy 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 210000003027 ear inner Anatomy 0.000 description 1
- 210000000959 ear middle Anatomy 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- H04R1/00—Details of transducers, loudspeakers or microphones
- H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
- H04R1/22—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired frequency characteristic only
- H04R1/28—Transducer mountings or enclosures modified by provision of mechanical or acoustic impedances, e.g. resonator, damping means
- H04R1/2869—Reduction of undesired resonances, i.e. standing waves within enclosure, or of undesired vibrations, i.e. of the enclosure itself
- H04R1/2876—Reduction of undesired resonances, i.e. standing waves within enclosure, or of undesired vibrations, i.e. of the enclosure itself by means of damping material, e.g. as cladding
- H04R1/288—Reduction of undesired resonances, i.e. standing waves within enclosure, or of undesired vibrations, i.e. of the enclosure itself by means of damping material, e.g. as cladding for loudspeaker transducers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
-
- 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
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/1058—Manufacture or assembly
- H04R1/1075—Mountings of transducers in earphones or headphones
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B6/00—Tactile signalling systems, e.g. personal calling systems
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03G—CONTROL OF AMPLIFICATION
- H03G5/00—Tone control or bandwidth control in amplifiers
- H03G5/16—Automatic control
- H03G5/165—Equalizers; Volume or gain control in limited frequency bands
-
- 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
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/1008—Earpieces of the supra-aural or circum-aural type
-
- 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
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/1041—Mechanical or electronic switches, or control elements
-
- 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
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/105—Earpiece supports, e.g. ear hooks
-
- 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
- H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
- H04R1/1091—Details not provided for in groups H04R1/1008 - H04R1/1083
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/60—Mounting or interconnection of hearing aid parts, e.g. inside tips, housings or to ossicles
- H04R25/607—Mounting or interconnection of hearing aid parts, e.g. inside tips, housings or to ossicles of earhooks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R29/00—Monitoring arrangements; Testing arrangements
- H04R29/001—Monitoring arrangements; Testing arrangements for loudspeakers
-
- 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
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/04—Circuits for transducers, loudspeakers or microphones for correcting frequency response
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R9/00—Transducers of moving-coil, moving-strip, or moving-wire type
- H04R9/02—Details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R9/00—Transducers of moving-coil, moving-strip, or moving-wire type
- H04R9/06—Loudspeakers
-
- 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
- H04R1/025—Arrangements for fixing loudspeaker transducers, e.g. in a box, furniture
-
- 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
- H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
- H04R1/22—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired frequency characteristic only
- H04R1/28—Transducer mountings or enclosures modified by provision of mechanical or acoustic impedances, e.g. resonator, damping means
- H04R1/2807—Enclosures comprising vibrating or resonating arrangements
- H04R1/2811—Enclosures comprising vibrating or resonating arrangements for loudspeaker transducers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/43—Signal processing in hearing aids to enhance the speech intelligibility
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2460/00—Details of hearing devices, i.e. of ear- or headphones covered by H04R1/10 or H04R5/033 but not provided for in any of their subgroups, or of hearing aids covered by H04R25/00 but not provided for in any of its subgroups
- H04R2460/13—Hearing devices using bone conduction transducers
Definitions
- the present application relates to the field of acoustics, and in particular, to a method for optimizing the working state of a bone conduction earphone.
- Bone conduction earphones are different from traditional air conduction earphones.
- the earphone core of the bone conduction earphone is attached to the skin of the user's head, and the vibration is directly transmitted to the ossicles of the user's middle ear through the user's bones.
- the cochlea of the inner ear that allows the user to hear sound.
- the bone conduction earphone may have a negative impact on its functionality under different working conditions.
- the poor fit of the skin may make the user unable to hear the sound through the bone conduction headphones or the sound quality heard is poor, thereby reducing the user's listening experience and wearing experience. It is of great significance to determine the working state of the bone conduction earphone and make corresponding feedback and optimization to ensure the functionality of the bone conduction earphone.
- One of the embodiments of the present application provides a method for optimizing the working state of a bone conduction earphone
- the bone conduction earphone includes an earphone core and at least one vibration sensor
- the method includes: acquiring a vibration signal through the at least one vibration sensor, and the The vibration signal is derived at least in part from the vibration of the earphone core in response to a segment of audio signal, the vibration of the earphone core is configured to be transmitted to the user wearing the bone conduction earphone in a bone conduction manner; based on the vibration signal and the audio signal to determine the vibration response characteristic of the earphone core; and based on the vibration response characteristic of the earphone core, the working state of the bone conduction earphone is fed back.
- the bone conduction earphone includes an acquisition module, a determination module, and a control module; the acquisition module acquires a vibration signal through at least one vibration sensor, and the vibration signal is at least partially derived from an earphone core In response to the vibration generated by a piece of audio signal, the vibration of the earphone core is configured to be transmitted to the user wearing the bone conduction earphone in a bone conduction manner; the determining module is based on the vibration signal and the audio signal, determining the vibration response characteristic of the earphone core; and the control module feeding back the working state of the bone conduction earphone based on the vibration response characteristic of the earphone core.
- One of the embodiments of the present application provides a training method for an identification model, the method includes: acquiring sample information; determining a sample type of each of at least two user wearing records based on the sample information, wherein the sample type includes A positive sample type or a negative sample type; determining sample characteristic information corresponding to each of the at least two user wearing records based on the sample information; and based on the sample characteristic information and each of the at least two user wearing records; A sample type determines the recognition model.
- FIG. 1 is a flowchart of a method for optimizing a working state of a bone conduction earphone provided according to some embodiments of the present application;
- FIG. 2 is a flowchart of a method for feeding back a working state of a bone conduction earphone provided according to some embodiments of the present application;
- FIG. 3 is a frequency response curve of the vibration of the earphone core when the working states of the bone conduction earphone provided according to some embodiments of the present application are the user wearing state and the user not wearing state;
- FIG. 4 is a flowchart of a method for feeding back a working state of a bone conduction earphone provided according to some embodiments of the present application;
- FIG. 5 is a frequency response curve of the vibration of the earphone core when the working states of the bone conduction earphones provided according to some embodiments of the present application are a well-wearing state by a user and a well-wearing state by the user;
- FIG. 6 is a flowchart of a method for feeding back a working state of a bone conduction earphone provided according to some embodiments of the present application;
- FIG. 7 is a frequency response curve of the vibration of the earphone core corresponding to the larger clamping force and the smaller clamping force when the user wears the bone conduction earphone in the working state of the bone conduction earphone provided according to some embodiments of the present application;
- FIG. 10 is a flowchart of a method for feeding back the working state of a bone conduction earphone provided according to some embodiments of the present application;
- FIG. 11 is a flowchart of a method for feeding back a working state of a bone conduction earphone provided according to some embodiments of the present application;
- FIG. 12 is a flowchart of a method for feeding back the working state of a bone conduction earphone provided according to some embodiments of the present application.
- FIG. 13 is a flowchart of a training method of a recognition model provided according to some embodiments of the present application.
- FIG. 14 is a block diagram of a bone conduction earphone provided according to some embodiments of the present application.
- system means for distinguishing different components, elements, parts, parts or assemblies at different levels.
- device means for converting signals into signals.
- unit means for converting signals into signals.
- module means for converting signals into signals.
- different working states of the bone conduction earphones may affect the functionality of the bone conduction earphones, resulting in poor listening experience and wearing experience for the user. For example, when a user wears a bone conduction earphone, if the bone conduction earphone is not properly worn, the user will hear poor sound quality through the bone conduction earphone. For another example, when the user wears the bone conduction headset, when the initial input voltage of the bone conduction headset is small or large, the volume of the sound heard by the user is too small or too large, so that the user has a poor listening experience or is uncomfortable to the user. Hearing damage.
- the clamping force when the user wears the bone conduction earphone is too small or too large, the transmission efficiency of the bone conduction and the listening experience or wearing experience of the user will be affected.
- the bone conduction headset will not automatically enter or exit the working state when the user wears or does not wear it, which will increase the power consumption of the bone conduction headset and affect the user's wearing experience.
- the bone conduction earphone may include an earphone core and at least one vibration sensor, wherein the earphone core may generate vibration in response to an audio signal, and the vibration may be transmitted to the user wearing the bone conduction earphone in a bone conduction manner, Since the skin loads at different positions of the human body are different, the vibration of the earphone core is related to the actual wearing position of the user.
- the vibration signal after the earphone core is coupled with the human skin can be obtained through at least one vibration sensor.
- the vibration response characteristic of the earphone core can be determined based on the audio signal and the vibration signal, and based on the vibration response characteristic of the earphone core, the working state of the bone conduction earphone can be fed back to realize the optimization of the working state of the bone conduction earphone.
- the feedback on the working state of the bone conduction headset may include: when the user is not wearing the bone conduction headset, generating an instruction to pause playback of the bone conduction headset or adaptively adjust the power consumption of the bone conduction headset to reduce the bone conduction Power consumption of the headset.
- the feedback on the working state of the bone conduction earphones may include: when the bone conduction earphones are not well worn, generating a prompt message to prompt the user to wear the bone conduction earphones again, so that the sound quality heard by the user through the bone conduction earphones is higher than that of the user. Good for a better listening experience.
- the feedback on the working state of the bone conduction earphone may include: when the input voltage of the earphone core of the bone conduction earphone is too small or too large, adaptively adjusting the amplitude of the audio signal input to the earphone core, so as to ensure The user can hear sound at a suitable volume.
- the feedback on the working state of the bone conduction earphone may include: adaptively adjusting the clamping force when the user wears the bone conduction earphone when the clamping force is too small or too large when the user wears the bone conduction earphone , while ensuring the transmission efficiency of bone conduction, the user's wearing comfort is guaranteed.
- the feedback on the working state of the bone conduction earphones may further include: when different users wear the bone conduction earphones or the same user repeatedly wears the bone conduction earphones, performing EQ compensation on the audio signal input to the earphone core, so as to Ensure that different users or users with different wearing styles hear the same sound effect through the bone conduction headphones.
- the user's physiological state can also be monitored by feedback on the working state of the bone conduction earphone, so as to monitor and feedback the user's health condition.
- FIG. 1 is a flowchart of a method for optimizing a working state of a bone conduction earphone according to some embodiments of the present application.
- bone conduction earphones may include an earphone core and at least one vibration sensor.
- the earphone core can be a transducer device, which can convert the received audio signal into mechanical vibration, and the mechanical vibration is transmitted to the human ear through bone conduction, so that the human can hear the corresponding sound.
- the earphone core may include, but is not limited to, electric (coil type), moving iron, piezoelectric, pneumatic, electrode type earphone cores, capable of generating vibrations in response to audio signals.
- the earphone core may be an electric earphone core, and its structure may include an electromagnet, a coil and a diaphragm, the coil is connected to the diaphragm, and the coil can drive the diaphragm to vibrate under the driving of a signal current.
- the vibration sensor may be a sensor that collects a frequency response curve of the vibration of the earphone core based on the vibration of the earphone core.
- at least one vibration sensor may be disposed inside or on the surface of the earphone core, the vibration sensor may acquire a vibration signal based on the vibration of the earphone core, and then a frequency response curve of the vibration of the earphone core may be acquired based on the audio signal and the vibration signal.
- the frequency response curve can determine the vibration response characteristics of the headphone core vibration.
- the vibration response characteristics of the earphone core may include one or more of a resonance frequency of the earphone core, a response peak at a specific frequency, a quality factor, and an input voltage.
- the vibration sensors may include displacement sensors, velocity sensors, acceleration sensors, etc., or combinations thereof, classified according to the parameters measured by the vibration sensors.
- Different types of sensors can be applied to the vibration acquisition of different frequency bands of the headphone core.
- the vibration sensor when the vibration sensor is a displacement sensor, it can be used to collect the low-frequency vibration of the earphone core.
- the vibration sensor when the vibration sensor is a speed sensor, it can be used to collect the mid-frequency vibration of the earphone core.
- the vibration sensor is an acceleration sensor, it can be used to collect high-frequency vibrations in the earphone core.
- the bone conduction earphone may further include at least one vibration sensor for acquiring vibration signals of various frequency bands (eg, low frequency, medium frequency, high frequency, etc.), so as to monitor the vibration signals of all frequency bands.
- vibration sensors are classified according to the presence or absence of external excitation, and vibration sensors may include active sensors (requiring external voltage or current excitation), passive sensors.
- the vibration sensors are classified according to the measured vibration direction, and the vibration sensors may include, but are not limited to, single-axis sensors, multi-axis sensors, rotational angular velocity sensors, and the like. Different types of sensors measure different vibration directions. For example, a single-axis sensor can measure the vibration direction of a single axis.
- Multi-axis sensor and rotational angular velocity sensor can realize multi-axis vibration direction measurement.
- the types of vibration sensors may include, but are not limited to, piezoelectric sensors, Integrated Circuits Piezoelectric (ICP) acceleration sensors, Microelectro Mechanical Systems (MEMS) sensors, and the like.
- the method 100 for optimizing the working state of a bone conduction earphone may include the following steps:
- Step 110 acquiring vibration signals through at least one vibration sensor.
- step 110 may be performed by an acquisition module of the bone conduction headset (eg, acquisition module 1410).
- the vibration signal is derived, at least in part, from vibration of the headphone core in response to a segment of the audio signal.
- the earphone core can convert the received audio signal into mechanical vibration, and the mechanical vibration is transmitted to the user wearing the bone conduction earphone through bone conduction, so that the user can hear the corresponding sound, and the mechanical vibration can be transmitted to the A vibration sensor inside or on the surface of the headphone core.
- the vibration sensor can obtain the corresponding vibration signal based on the mechanical vibration. Based on the audio signal and the vibration signal, the frequency response curve of the headphone core vibration can be obtained.
- audio signals may include optical signals, electrical signals, magnetic signals, mechanical signals, etc. with acoustic information.
- the earphone core can receive audio signals through wired or wireless connection, and the audio signals can come from the storage unit of the bone conduction earphone itself, or from a terminal device other than the bone conduction earphone (for example, a mobile phone, a computer, etc.) , MP3, etc.).
- the audio signal may be a preset audio calibration signal.
- the audio calibration signal may be a frequency sweep signal, a white noise signal, or a sound signal corresponding to a piece of music.
- the audio signal may be a sound signal played when the user wears a bone conduction headset.
- Step 120 Determine the vibration response characteristic of the earphone core based on the vibration signal and the audio signal.
- step 120 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the vibration sensor may acquire a vibration signal based on the vibration of the earphone core (also referred to as mechanical vibration), and then acquire a frequency response curve of the vibration of the earphone core based on the vibration signal and the audio signal. According to the frequency response curve of the earphone core, Determine the vibration response characteristics of the headphone core.
- the vibration response feature of the earphone core may be extracted from the frequency response curve of the vibration of the earphone core by a feature extraction method.
- the method for extracting vibration response features may include, but is not limited to, Principal Components Analysis (PCA), Independent Component Algorithm (ICA), Linear Discriminant Analysis (LDA), Singular Value Decomposition (SVD), etc.
- the vibration response characteristic of the earphone core may include at least one of a resonance frequency of the earphone core, a response peak value at a specific frequency, a quality factor, and an input voltage.
- the resonant frequency of the earphone core the response peak value of a specific frequency, the quality factor, or the parameter value (for example, vibration amplitude, speed, acceleration, etc.) used to characterize the input voltage of the earphone core can be determined. etc. or any combination thereof.
- Step 130 based on the vibration response characteristic of the earphone core, feedback the working state of the bone conduction earphone.
- step 130 may be performed by a control module of the bone conduction headset (eg, control module 1430).
- different working states of the bone conduction earphone can affect the vibration of the earphone core, so that the earphone core has different vibration response characteristics. Therefore, the working state of the bone conduction earphone can be determined by the vibration response characteristics of the earphone core, thereby The working state of the bone conduction earphone can be fed back to optimize the working state of the bone conduction earphone, so as to ensure the user's listening experience and wearing experience when wearing the bone conduction earphone.
- the feedback of the working state of the bone conduction earphone based on the vibration response characteristic of the earphone core may be implemented by an algorithm.
- the determination of different working states of the bone conduction earphone may be determined based on a certain time interval (eg, 1s, 2s, 3s, etc.). In some embodiments, determining the working state of the bone conduction earphone may be determined within a certain time range (eg, 3s, 4s, 5s, etc.) when the power of the bone conduction earphone is turned on.
- the working state of the bone conduction earphone may include a user wearing state and a user not wearing state.
- the feedback on the working state of the bone conduction headphones may include the vibration response characteristics of the headphone core to determine whether the working status of the bone conduction headphones is not worn by the user, and if the working status of the bone conduction headphones is When the user is not wearing it, an instruction may be generated to suspend the operation (eg, playing) of the bone conduction earphone or adjust the power consumption of the bone conduction earphone, so as to reduce the power consumption of the bone conduction earphone.
- the working state of the bone conduction headset includes a user wearing state and a user not wearing state.
- the working state of the bone conduction headset please refer to FIG. 2 and related descriptions.
- the working state of the bone conduction earphone may include a well-worn state by the user and a well-worn state by the user.
- the feedback on the working state of the bone conduction headphones may include the vibration response characteristics of the headphone core to determine whether the working state of the bone conduction headphones is a state that the user is not wearing well, and if the working state of the bone conduction headphones If the user is not wearing well, the bone conduction headset can generate prompt information to prompt the user to re-wear the bone conduction headset or adjust the wearing posture and position of the bone conduction headset, so as to ensure the user's listening experience and wearing experience.
- the bone conduction earphone continues to maintain the well-wearing working state.
- the working states of the bone conduction earphones include the well-wearing state and the non-wearing state of the user. For more details on feedback on the working state of the bone conduction earphones, refer to FIG. 4 and related descriptions.
- the working state of the bone conduction earphone may be related to the clamping force when the user wears the bone conduction earphone.
- the feedback on the working state of the bone conduction earphone may include the vibration response characteristics of the earphone core to determine whether the clamping force of the user when wearing the bone conduction earphone is within the preset range. If the force is not within the preset range, an instruction can be generated to adjust the structure corresponding to the bone conduction earphone, so as to change the clamping force when the user wears the bone conduction earphone, so that the clamping force is within the preset range to avoid excessive clamping force.
- the working state of the bone conduction earphone is related to the clamping force when the user wears the bone conduction earphone. For more detailed description of the feedback on the working state of the bone conduction earphone, refer to FIG. 6 and its related descriptions.
- the working state of the bone conduction earphone may include the input voltage of the earphone core. Based on the vibration response characteristics of the earphone core, feedback on the working state of the bone conduction earphone may include obtaining a parameter value representing the input voltage of the earphone core, and judging whether the parameter value is within the voltage threshold, and if the input voltage of the earphone core is not within the voltage threshold , then adjust the amplitude of the audio signal input to the earphone core so that the amplitude of the audio signal of the earphone core will not be too small, resulting in poor sound quality or low volume of the sound heard by the user through the bone conduction earphone, so that the amplitude of the audio signal will not be too small.
- the value will not be too large to damage the headphone core or bring discomfort to the user or even damage the user's hearing, so as to ensure the user's listening experience and wearing experience.
- the working state of the bone conduction earphone includes the input voltage, and more details about the feedback on the working state of the bone conduction earphone can be found in FIG. 11 and its related descriptions.
- the feedback on the working state of the bone conduction earphone may include identifying the difference between the vibration response feature of the earphone core and the target response feature, and EQing the audio signal input to the earphone core according to the difference adjust. More descriptions can be found in Figure 10 and its related descriptions.
- the feedback on the working state of the bone conduction earphone may include, based on the vibration response feature of the earphone core, acquiring a parameter value related to the user's physiological parameter, and based on the parameter value, turning on Or turn off the auxiliary module of the bone conduction headset.
- the working state of the bone conduction earphone may include a user wearing state and a user not wearing state.
- the wearing state of the user refers to the working state of the bone conduction earphone after being worn by the user, and it can also be understood that the earphone core of the bone conduction earphone is in contact with the skin of the user's head.
- the state of not being worn by the user refers to a state in which the bone conduction earphone is not worn by the user, and it can be understood here that the bone conduction earphone is not in contact with the skin of the user's head.
- FIG. 2 is a flowchart of a method for feeding back a working state of a bone conduction earphone according to some embodiments of the present application.
- the method 200 for feeding back the working state of the bone conduction earphone may include the following steps:
- Step 210 based on the vibration response characteristic of the earphone core, determine whether the working state is a state of not being worn by the user.
- step 210 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- a determination module of the bone conduction headset eg, determination module 1420.
- the working state of the bone conduction earphone is the user wearing state
- the earphone core is in contact with the user's skin, and the mechanical impedance of the skin will affect the vibration of the earphone core
- the working state of the bone conduction earphone is the user's skin.
- the earphone core is not in contact with the user's skin, and the vibration of the earphone core is not affected by the mechanical impedance of the skin. Therefore, the working state of the bone conduction earphone is collected by the vibration sensor when the user is wearing it and the user is not wearing it.
- the vibration signals of the received earphone core are different, so that the working state of the bone conduction earphone is the user wearing state and the user not wearing the state that the earphone core has different vibration response characteristics (for example, resonant frequency, specific frequency response peak, quality factor, etc.), Based on the vibration response characteristics of the earphone core, it is possible to judge whether the working state of the bone conduction earphone is a user wearing state or a user not wearing state. In order to further illustrate the bone conduction earphones in the user's wearing state and the user's non-wearing state, they are described below with reference to FIG. 3 .
- FIG. 3 In order to further illustrate the bone conduction earphones in the user's wearing state and the user's non-wearing state, they are described below with reference to FIG. 3 .
- FIG. 3 is a frequency response curve of the vibration of the earphone core when the working states of the bone conduction earphone provided according to some embodiments of the present application are the user wearing state and the user non-wearing state.
- the solid line in Fig. 3 is the frequency response curve of the vibration of the earphone core when the working state of the bone conduction earphone is the user wearing state
- the dotted line in Fig. 3 is the working state of the bone conduction earphone is that the earphone core vibrates when the user is not wearing the state. frequency response curve.
- the frequency response curve of the vibration of the earphone core is significantly different when the working state of the bone conduction earphone is the user wearing state and the user not wearing the state.
- the vibration response characteristics of the cores also vary. For example, when the working state of the bone conduction earphone is the user wearing state, the frequency response curve of the earphone core vibration is flatter than the frequency response curve of the earphone core vibration when the user is not wearing it. For another example, when the working state of the bone conduction earphone is the user wearing state, the frequency corresponding to the response peak value of the frequency response curve of the vibration of the earphone core is smaller than the response peak value of the frequency response curve of the earphone core vibration when the working state of the bone conduction earphone is the user not wearing the state. corresponding frequency.
- the frequency response curve of the earphone core has a corresponding response peak 310 when the frequency is about 26 Hz, and has a response peak 320 when the frequency is about 100 Hz.
- the response peak 310 is about -65dB
- the response peak 320 is about -35dB.
- the frequency response curve of the earphone core has a corresponding response peak value 330 when the frequency is about 56Hz, and has a response peak value 340 when the frequency is about 120Hz.
- the response peak 330 is about -62dB
- the response peak 340 is about -60dB.
- Step 220 if the working state is the state not being worn by the user, generate an instruction to adjust the power consumption of the bone conduction earphone.
- step 220 may be performed by a control module of the bone conduction headset (eg, control module 1430).
- a feedback circuit may be included in the bone conduction headset, and the control module (eg, the control module 1430 ) of the bone conduction headset may generate corresponding instructions to control the feedback circuit to adjust the bone in response to the working state of the user not wearing it.
- the power consumption of conduction headphones In some embodiments, adjusting the power consumption of the bone conduction earphone can be realized by pausing the playback of the bone conduction earphone.
- the instruction generated by the control module can control the feedback circuit to suspend the reception of the audio signal of the earphone core of the bone conduction earphone or stop the terminal
- the device transmits audio signals to the earphone core of the bone conduction earphone, or turns off the power supply or part of the power consumption function of the bone conduction earphone.
- whether the working state of the bone conduction earphone is not worn by the user can also be determined through the identification model.
- the vibration response feature of the earphone core can be input into the recognition model, and then a judgment result can be generated based on the output of the recognition model, wherein the judgment result can include that the working state of the bone conduction headset is the user wearing state and the working state of the bone conduction headset is the user Not worn.
- the recognition model may be a trained machine learning model.
- the machine learning model may include K-Nearest Neighbor (KNN) model, Bayesian (Bayesian) model, Decision Tree (Decision Tree) model, random forest (random forest) model, log odds Regression (logistic regression) model, neural network (Neural Network, NN) model, ensemble learning (Ensemble Learning) model, etc. or a combination thereof.
- KNN K-Nearest Neighbor
- Bayesian Bayesian
- Decision Tree Decision Tree
- random forest random forest
- log odds Regression logistic regression
- neural network Neral Network, NN
- ensemble learning Ensemble Learning
- the above-mentioned identification model can be obtained by the following training methods: the predetermined working state of the bone conduction earphone is the user wearing state and the vibration response characteristic of the corresponding earphone core as training positive samples; The working state of the headset is that the user is not wearing it and the vibration response characteristic of the corresponding headset core is the training negative sample.
- the machine learning model is used to train the training positive sample and the training negative sample respectively, so as to obtain the ability to judge whether the working state of the headset is a user Recognition model for the unworn state.
- the vibration response feature of the earphone core can also be extracted by an algorithm (for example, the method of extracting the vibration response feature in step 120) and compared with the preset vibration response feature to determine whether the working state of the bone conduction earphone is not It is the state that the user is not wearing it, wherein the preset vibration response characteristics may be the vibration response characteristics (for example, resonance frequency, response peak value of a specific frequency, quality factor, etc.) in which the working state of the bone conduction earphone is the wearing state of the user. If the earphone core If the vibration response characteristic is different from or not within a certain threshold, it can be judged that the corresponding working state is not worn by the user.
- an algorithm for example, the method of extracting the vibration response feature in step 120
- the bone conduction earphones work normally, or it can be further judged whether the working state of the bone conduction earphones is that the user is not wearing well, so as to carry out the working state of the user not wearing well. feedback and improve it.
- the working state of the bone conduction earphone may further include a well-wearing state of the user and a well-wearing state of the user.
- the well-wearing state of the user refers to a working state in which the bone conduction earphone is correctly worn by the user.
- the vibration output end of the earphone core of a bone conduction earphone is completely in contact with the user's skin.
- the earphone core of the bone conduction earphone is located in a specific area of the user's skin (eg, the earphone core is located in the area on the front side of the user's auricle).
- the user is not wearing a good state refers to a working state in which the bone conduction headset is not properly worn by the user.
- a good state refers to a working state in which the bone conduction headset is not properly worn by the user.
- only part of the earphone core of a bone conduction earphone is in contact with the skin of the user's head.
- the earphone core is located outside a specific area of the user's skin (eg, behind the user's pinna).
- FIG. 4 is a flowchart of a method for feeding back a working state of a bone conduction earphone according to some embodiments of the present application.
- the method 400 for feeding back the working state of the bone conduction earphone may include the following steps:
- Step 410 based on the vibration response characteristics of the earphone core, determine whether the working state is a state that the user does not wear well.
- step 410 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the earphone core and the skin of the user's head have different contact conditions respectively, so that the mechanical impedance of the skin will affect the impact of the earphone core on the The influence of vibration is also different. Therefore, the working state of the bone conduction earphone is that the user wears it well and the vibration signal of the earphone core collected by the vibration sensor is different when the user does not wear it well, so that the working state of the bone conduction earphone is that the user wears well.
- the headphone core has different vibration response characteristics (for example, resonant frequency, response peak at a specific frequency, quality factor, etc.) when the headphone core is in the state and the user is not wearing it well. It is judged whether it is in a well-wearing state or the user is not wearing a well-fitting state.
- vibration response characteristics for example, resonant frequency, response peak at a specific frequency, quality factor, etc.
- the solid line in Figure 5 is the frequency response curve of the vibration of the earphone core when the working state of the bone conduction earphone is when the user is wearing it well
- the dotted line in Figure 5 is the working state of the bone conduction earphone is when the user is not wearing it well when the earphone core is in a good state Vibration frequency response curve.
- the working state of the bone conduction earphone is that the user wears well and the user does not wear it well.
- the frequency response curve of the vibration of the earphone core is significantly different.
- the working state of the bone conduction earphone is that the user wears well and the user does not wear
- the vibration response characteristics of the headphone core in good condition also vary.
- the working state of the bone conduction earphone is that the frequency response curve of the vibration of the earphone core when the user wears it well is flatter than the frequency response curve of the vibration of the earphone core when the user does not wear it well.
- the working state of the bone conduction earphone is that the frequency corresponding to the peak value of the frequency response curve of the vibration of the earphone core when the user wears it well is less than the frequency corresponding to the peak value of the frequency response curve of the vibration of the earphone core when the working state of the bone conduction earphone is that the user does not wear it well.
- the frequency corresponding to the peak of the response is that the working state of the bone conduction earphone is that the frequency response curve of the earphone core has a corresponding response peak value 510 when the frequency is about 50Hz, and has a response peak value 520 when the frequency is about 80Hz when the user is not wearing it well.
- the response peak 510 is about -84dB
- the response peak 520 is about -63dB.
- the working state of the bone conduction earphone is that when the user wears it well, the frequency response curve of the earphone core has a corresponding response peak value 530 when the frequency is about 60Hz, and has a response peak value 540 when the frequency is about 160Hz.
- the response peak 530 is about -65dB
- the response peak 540 is about -45dB.
- a trough 550 will appear in the frequency curve of the bone conduction earphone.
- one or more troughs eg, trough 550
- Step 420 if the working state is that the user is not wearing well, the bone conduction earphone sends a prompt message.
- step 420 may be performed by a control module of the bone conduction headset (eg, control module 1430).
- the control module can send out prompt information, which can be received by the user to prompt the user to wear the bone conduction headset again or adjust the posture or position of wearing the bone conduction headset, and the like.
- the bone conduction earphone can prompt the user through the earphone core vibrating or the earphone core playing a voice prompt word.
- the bone conduction earphone can send prompt information to the user through a terminal device (eg, mobile phone, computer, etc.) connected to it wired or wirelessly, and the form of prompt information can include but not limited to vibration, text, picture, voice, etc. .
- the bone conduction headset can send a prompt message to the user, prompting the user to re-wear the bone conduction headset or adjust the posture or position of wearing the bone conduction headset, so as to avoid the user
- the sound quality and quality of the sound will be poor if the bone conduction headphones are not properly worn, which ensures the user's listening experience.
- the bone conduction earphone continues to work in the well-worn working state if the working state of the bone conduction earphone is a well-worn state of the user.
- the vibration response feature of the earphone core can be input into the recognition model, and then a judgment result can be generated based on the output of the recognition model, wherein the judgment result can include that the working state of the bone conduction headset is that the user is wearing well and the working state of the bone conduction headset is The user is not wearing it in good condition.
- the recognition model may be a trained machine learning model.
- the machine learning model may include K-Nearest Neighbor (KNN) model, Bayesian (Bayesian) model, Decision Tree (Decision Tree) model, random forest (random forest) model, log odds Regression (logistic regression) model, neural network (Neural Network, NN) model, ensemble learning (Ensemble Learning) model, etc. or a combination thereof.
- KNN K-Nearest Neighbor
- Bayesian Bayesian
- Decision Tree Decision Tree
- random forest random forest
- log odds Regression logistic regression
- neural network Neral Network, NN
- ensemble learning Ensemble Learning
- the above-mentioned recognition model can be obtained by the following training methods: the predetermined working state of the bone conduction earphone is the well-wearing state of the user and the vibration response characteristics of the corresponding earphone core as training positive samples; The working state of the conductive earphone is that the user does not wear it well and the vibration response characteristic of the corresponding earphone core is the training negative sample.
- the machine learning model is used to train the training positive sample and the training negative sample respectively, so as to obtain the ability to judge whether the working state of the earphone is correct. It is a recognition model for the user not wearing a good state.
- an algorithm may be used to compare the vibration response characteristic of the earphone core with a preset vibration response characteristic to determine whether the working state of the bone conduction earphone is not worn by the user, wherein the preset vibration response characteristic may be
- the working state of bone conduction earphones is the vibration response characteristics of the user wearing well (for example, resonant frequency, response peak value of a specific frequency, quality factor, etc.), if the vibration response characteristics of the headphone core are different from the preset vibration response characteristics or exist If the difference is not within a certain threshold, it can be judged that the corresponding working state is that the user is not wearing well.
- the feedback on the working state of the bone conduction earphone may include adjusting the clamping force when the user wears the bone conduction earphone.
- the working state of the bone conduction earphone may be related to the clamping force when the user wears the bone conduction earphone, and the magnitude of the clamping force may affect the sound quality or volume of the sound heard by the user through the bone conduction earphone and the amount of the user wearing the bone conduction earphone. comfortability.
- the clamping force when the user wears the bone conduction earphone may be the pressure of the earphone core on the user's skin.
- the method 600 for feeding back the working state of the bone conduction earphone may include the following steps:
- Step 610 based on the vibration response characteristics of the earphone core, determine whether the clamping force when the user wears the bone conduction earphone is within a preset range.
- step 610 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the mechanical impedance of the skin will be different due to the different clamping force of the user's bone conduction earphone, and the impact of different mechanical impedance of the skin on the vibration of the earphone core is also different.
- the preset range may be 0.2N ⁇ 0.5N. In some embodiments, the preset range may be 0.25N ⁇ 0.45N. In some embodiments, the preset range may be 0.3N ⁇ 0.4N. It should be noted that the preset range is not limited to the above-mentioned range, and the preset range can be adaptively adjusted according to the user's experience.
- FIG. 7 is a frequency response curve of the headphone core vibration corresponding to a larger clamping force and a smaller clamping force when a user wears the bone conduction headphone in the working state of the bone conduction headphone provided according to some embodiments of the present application.
- the solid line in Fig. 7 shows the frequency response curve of the vibration of the earphone core corresponding to the smaller clamping force when the user wears the bone conduction earphone
- the dashed line in Fig. 7 corresponds to the earphone with the larger clamping force when the bone conduction earphone is worn.
- Frequency response curve of core vibration As shown in Figure 7, the frequency response curves of the headphone core vibration corresponding to the larger clamping force and the smaller clamping force when the user wears the bone conduction earphone have obvious differences. The vibration response characteristics of the headphone core corresponding to the smaller tightening force are also different. For example, the frequency response curve of the vibration of the earphone core when the clamping force is large when the user wears the bone conduction earphone is flatter than the frequency response curve of the vibration of the earphone core when the clamping force when the user wears the bone conduction earphone is small.
- the frequency corresponding to the response peak value of the frequency response curve of the vibration of the earphone core is smaller than the frequency corresponding to the frequency response curve of the vibration of the earphone core when the clamping force when the user wears the bone conduction earphone is large.
- the frequency corresponding to the peak of the response when the clamping force of the user wearing the bone conduction earphone is small, the frequency response curve of the earphone core vibration has a response peak 710 at a frequency of about 45 Hz and a response peak 720 at a frequency of about 150 Hz.
- the response peak 710 is about -53dB and the response peak 720 is about -54dB.
- the frequency response curve of the earphone core vibration has a response peak value of 730 at a frequency of about 50Hz, and a response peak value of 740 at a frequency of about 200Hz.
- the response peak 730 is about -52dB
- the response peak 320 is about -60dB.
- the frequency response curve of the vibration of the headphone core is flatter when the clamping force is small or large when conducting headphones, while the frequency response peak of the frequency response curve of the vibration of the headphone core when the user is wearing a good condition is greater than that when the user is wearing bone conduction headphones.
- the frequency corresponding to the response peak in the frequency response curve of the headphone core vibration when the force is small or large.
- the frequency response curve of the vibration of the earphone core when the clamping force is small or large has a large trough (for example, the trough 750, the trough 760), and the trough can also reflect that the user is wearing bone conduction. Less or more clamping force when headphones are used.
- Step 620 if the user wears the bone conduction earphone, the clamping force generates an instruction to adjust the structure corresponding to the bone conduction earphone, so as to change the clamping force when the user wears the bone conduction earphone.
- step 620 may be performed by a control module of the bone conduction headset (eg, control module 1430).
- the bone conduction earphone may include a feedback circuit and a structure for adjusting the clamping force, and the control module may generate corresponding instructions to control in response to the clamping force when the user is wearing the bone conduction earphone is not within a preset range
- the feedback circuit is used to adjust the structure of the bone conduction earphone for adjusting the clamping force, so as to change the clamping force when the user wears the bone conduction earphone.
- control module can generate corresponding instructions to control the feedback circuit to accurately adjust the structure of the bone conduction earphone for adjusting the clamping force based on the difference between the clamping force and the preset range, so that the user can The clamping force when wearing the bone conduction headset is just within the preset range.
- the feedback circuit can be controlled by the instructions generated by the control module to adjust the length or opening angle of the back hang of the bone conduction earphone to adjust the clamping force when the user wears the bone conduction earphone, for example, when the clamping force is less than In the preset range, the clamping force can be increased by increasing the back hanging length or reducing the back hanging angle; for another example, when the clamping force is greater than the preset range, you can reduce the back hanging length or increase the back hanging angle. angle to reduce the clamping force.
- the bone conduction earphone may include a drive structure capable of changing the length and opening angle of the bone conduction earphone based on instructions generated by the feedback circuit.
- the driving structure may include a micro motor and an adjustment component (eg, a retractable rod structure) for adjusting the length or angle of the rear hanging, the output end of the micro motor is connected with the adjustment structure, and the micro motor may drive the adjustment component to increase or decrease the rear The length of the hanging and the size of the opening angle.
- an adjustment component eg, a retractable rod structure
- the vibration response feature of the earphone core can be input into the recognition model, and then based on the output of the recognition model, the parameter value used to characterize the clamping force when the user wears the bone conduction earphone is obtained, and it is determined whether the parameter value is within the preset range.
- the parameter value used to characterize the clamping force when the user wears the bone conduction earphone may be a parameter that can reflect the magnitude of the clamping force or the magnitude range of the clamping force.
- the recognition model may be a trained machine learning model.
- the machine learning model may include K-Nearest Neighbor (KNN) model, Bayesian (Bayesian) model, Decision Tree (Decision Tree) model, random forest (random forest) model, log odds Regression (logistic regression) model, neural network (Neural Network, NN) model, ensemble learning (Ensemble Learning) model, etc. or a combination thereof.
- KNN K-Nearest Neighbor
- Bayesian Bayesian
- Decision Tree Decision Tree
- random forest random forest
- log odds Regression logistic regression
- neural network Neral Network, NN
- ensemble learning Ensemble Learning
- the above-mentioned identification model can be obtained by the following training method: pre-collecting the vibration response characteristics of the earphone cores corresponding to the clamping forces of different sizes when the user wears the bone conduction earphones, to obtain the collected vibration response characteristics of the multiple earphone cores.
- the vibration response feature is used as the input data, and the specific size or size range of the corresponding clamping force is used as the output data, and the machine learning model is trained to obtain the vibration response feature based on the earphone core.
- a model for the identification of parameter values of tightness is used as the input data, and the specific size or size range of the corresponding clamping force is used as the output data.
- the preset range may be a clamping force range that ensures that the user can comfortably wear the bone conduction earphone.
- the clamping force may range from 0.25N to 0.45N.
- the preset range may be 0.3N ⁇ 0.4N.
- the algorithm can also directly compare the vibration response characteristic of the earphone core with the preset vibration response characteristic to determine whether the clamping force when the user wears the bone conduction earphone exceeds the preset range.
- the preset vibration response feature may be the vibration response feature of the earphone core (for example, resonance frequency, response peak value of a specific frequency, quality factor, etc.) when the clamping force when the user wears the bone conduction earphone is within the preset range ), if there is a difference between the vibration response feature of the earphone core and the preset vibration response feature or the difference is not within a certain threshold, it can be judged that the vibration response feature of the earphone core corresponds to the user wearing the clamping force of the bone conduction earphone. is within the preset range.
- the clamping force related to the working state of the bone conduction earphone is within the preset range, and feeding back the corresponding working state (for example, adjusting the clamping force), it is possible to prevent the clamping force from being too small and affecting the efficiency of bone conduction , so that the sound quality or volume heard by the user through the bone conduction headphones is poor, and it can also avoid excessive clamping force to cause excessive pressure on the user's skin and bring discomfort to the user, ensuring the user's listening experience and wearing experience.
- FIG. 8 is a frequency response curve of the vibration of the earphone core when different users wear the same bone conduction earphone according to some embodiments of the present application.
- the solid line in FIG. 8 is a frequency response curve of the vibration of the earphone core when different users wear the same bone conduction earphone according to some embodiments of the present application.
- the frequency response curve of the vibration of the earphone core when user A wears the bone conduction earphone is the frequency response curve of the vibration of the earphone core when user A wears the bone conduction earphone
- the dotted line in FIG. 8 is the frequency response curve of the vibration of the earphone core when user B wears the bone conduction earphone.
- the frequency response curves of the headphone core vibration are different, so that when user A and user B wear the same bone conduction headset, the headphone core has different vibration response characteristics.
- the frequency response curve of the earphone core has a corresponding response peak 810 when the frequency is about 40 Hz, and has a response peak 820 when the frequency is about 180 Hz.
- the response peak 810 is about -48dB
- the response peak 820 is about -50dB.
- the frequency response curve of the earphone core has a corresponding response peak value 830 when the frequency is about 42 Hz, and has a response peak value 840 when the frequency is about 100 Hz.
- the response peak 830 is about -52dB
- the response peak 840 is about -47dB.
- Fig. 9 is a frequency response curve of the vibration of the earphone core when the same user wears the bone conduction earphone for many times according to some embodiments of the present application.
- the solid line in FIG. 9 is a frequency response curve of the vibration of the earphone core when the same user wears the bone conduction earphone for many times according to some embodiments of the present application.
- FIG. 9 is the frequency response curve of the vibration of the earphone core when the user wears the bone conduction earphone for the first time
- the dotted line in FIG. 9 is the frequency response curve of the vibration of the earphone core when the user wears the bone conduction earphone for the second time. It can be seen from Figure 9 that the frequency response curve of the vibration of the earphone core is different when the user wears the bone conduction earphone for the first time and when the user wears the bone conduction earphone for the second time, so that when the user wears the bone conduction earphone for the first time and the second wearing
- the headphone core has different vibration response characteristics when using bone conduction headphones.
- the vibration amplitude of the earphone core is different between the frequencies of 60 Hz and 100 Hz. This difference may result in different sounds (eg, different sound effects) that the user hears when the user wears the bone conduction headset for the first time and when the user wears the bone conduction headset for the second time.
- Fig. 10 is a flowchart of a method for feeding back the working state of a bone conduction earphone provided according to some embodiments of the present application.
- the method 1000 for feeding back the working state of the bone conduction earphone may include the following steps:
- Step 1010 identifying the difference between the vibration response feature of the earphone core and the target response feature.
- step 1010 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the target response characteristic may be a preset vibration response characteristic of the earphone core of the bone conduction earphone.
- the difference between the actual vibration response characteristic of the headphone core and the target response characteristic may be calculated by an algorithm, wherein the difference between the actual vibration response characteristic of the headphone core and the target response characteristic may include, but is not limited to, the difference between the resonance frequencies , the difference of the response peak value of a specific frequency, the difference of the quality factor, etc.
- Step 1020 Perform EQ adjustment on the audio signal input to the headphone core according to the difference.
- step 1020 may be performed by a control module of the bone conduction headset (eg, control module 1430).
- EQ is an equalizer that can separately adjust the amount of amplification of electrical signals of various frequency components. EQ adjustment refers to dividing the audio signal into multiple frequency bands, and then adjusting these frequency bands (for example, amplifying or attenuating) to obtain better sound effects.
- control module can perform compensation on the EQ based on the difference between the actual vibration response characteristics of the headphone core and the target response characteristics, the compensation EQ can act on the audio signal, and the original audio signal can be EQ adjusted, and the headphone core can respond The adjusted audio signal generates vibration, so that the user can hear the ideal sound through the bone conduction earphone.
- the feedback on the working state of the bone conduction earphone may include adjusting the amplitude of the audio signal input to the earphone core.
- the amplitude of the bone conduction earphone is related to the input voltage of the earphone core. For example, the larger the input voltage of the headphone core, the larger the amplitude of the headphone core, the smaller the input voltage of the headphone core, and the smaller the input voltage of the headphone core.
- the input voltage of the headphone core will affect the vibration amplitude of the headphone core. If the vibration amplitude of the headphone core is too large, it will bring discomfort to the user and even damage the user's hearing and cause damage to the headphone core.
- FIG. 11 is a flowchart of a method for feeding back a working state of a bone conduction earphone according to some embodiments of the present application.
- the working state of the bone conduction earphone is the input voltage of the earphone core
- the method 1100 for feeding back the working state of the bone conduction earphone may include the following steps:
- Step 1110 based on the vibration response characteristic of the earphone core, obtain a parameter value representing the input voltage of the earphone core.
- step 1110 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the voltage threshold may be the maximum voltage at which the sound produced by the bone conduction earphone does not produce distortion or breakage.
- the voltage threshold is the maximum voltage at which the sound pressure level of the sound emitted by the bone conduction earphone does not exceed a certain sound pressure level.
- the specific sound pressure level may range from 60dB to 100dB. Preferably, the specific sound pressure level may range from 70dB to 90dB. Further preferably, the range of the specific sound pressure level may be 75dB-95dB.
- the parameter value characterizing the input voltage of the headphone core may be the specific input voltage or size range of the headphone core, or may be the vibration amplitude of the headphone core or the overall output sound pressure of the headphone core.
- the voltage threshold and the specific sound pressure level can be adaptively adjusted according to actual application conditions and/or user experience, which are not further limited herein.
- Step 1120 determine whether the parameter value is within the voltage threshold.
- step 1120 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the determination module may compare the parameter value to a voltage threshold to determine whether the parameter value is within the voltage threshold.
- the voltage threshold may be an input voltage value or range of the earphone core that is comfortable for the user to wear.
- the voltage threshold may be an input voltage value or range of the earphone core that ensures that the earphone core will not be damaged.
- the voltage threshold may be the input voltage value or range of the earphone core to protect the user's hearing.
- the overall output of the earphone core will not exceed a certain limited sound pressure level (for example, children's earphones) We will try our best to require the overall sound pressure level not to exceed 85dB) to protect the user's hearing.
- a certain limited sound pressure level for example, children's earphones
- Step 1130 if the parameter value is not within the voltage threshold, adjust the amplitude of the audio signal input to the earphone core.
- step 1130 may be performed by a control module of the bone conduction headset (eg, control module 1430).
- the bone conduction earphone may include a feedback circuit, and the control module may generate corresponding instructions in response to the parameter value not being within the voltage threshold to control the feedback circuit to adjust the amplitude of the audio signal input to the earphone core, for example, the feedback circuit
- the amplitude of the audio signal input to the earphone core can be limited to limit the amplitude of the vibration of the earphone core, control the playback volume of the bone conduction earphone, and avoid the excessive vibration of the earphone core which will cause discomfort to the user or even the user's hearing and cause damage to the earphone core.
- the feedback circuit can amplify the amplitude of the audio signal input to the earphone core, so as to increase the playback volume of the bone conduction earphone and improve the sound quality.
- the feedback on the working state of the bone conduction earphone may include feedback on the user's physiological state and parameters.
- the mechanical impedance of the skin can reflect the physiological state of the human body to a certain extent.
- the corresponding skin mechanical impedance is determined, and the user's physiological state can be judged according to the skin mechanical impedance. For example, it can be determined whether the user is an elderly person and whether the user is fat or thin.
- FIG. 12 is a flowchart of a method for feeding back a working state of a bone conduction earphone according to some embodiments of the present application.
- the method 1200 for feeding back the working state of the bone conduction earphone may include the following steps:
- Step 1210 Obtain parameter values related to the user's physiological parameters based on the vibration response characteristics of the earphone core.
- step 1210 may be performed by a determination module of the bone conduction headset (eg, determination module 1420).
- the user's physiological parameter refers to a mechanical impedance parameter of the skin in contact with the earphone core.
- the parameter values related to the user's physiological parameters may include the quality, elasticity, damping, etc. of the mechanical impedance of the skin in contact with the earphone core, and the parameter values may reflect the user's weight, age, and the like.
- Step 1220 based on the parameter value, enable or disable the auxiliary module of the bone conduction earphone.
- step 1220 may be performed by a control module (eg, control module 1430) of the bone conduction headset.
- the control module can judge the change of the user's physiological state according to the obvious change of the parameter value in the short term, and then activate the corresponding auxiliary module based on the change of the user's physiological state, and the auxiliary module can prompt the user to pay attention to the change of the physiological state, for example , the control module can judge that the user is getting fat or thin according to the elasticity and damping changes of the mechanical impedance of the skin, and remind the user to pay attention through the auxiliary module.
- the control module can determine whether the user is an elderly person or a young person according to the parameter value.
- the auxiliary module can be turned on so that the auxiliary module can perform some user-friendly functions.
- the user-friendly functions can include but are not limited to falling Detection, voice reminder, automatic gain control, etc.
- the fall detection of the auxiliary module can predict the fall of the elderly and issue a voice reminder to the elderly, or after detecting the fall of the elderly and proactively make a distress call or notify an emergency contact.
- the automatic gain control of the auxiliary module can automatically adjust the vibration amplitude of the earphone core for the elderly for the user, so as to avoid excessive vibration amplitude of the earphone core and cause discomfort for the elderly to wear.
- the method for optimizing the working state of the bone conduction earphone may include the above-mentioned single method of feeding back the working state of the bone conduction earphone to realize a single function, and may also include the above-mentioned multiple work on the bone conduction earphone.
- the functions implemented by the method for feeding back the working state of the bone conduction earphone can include adjusting the power consumption of the bone conduction earphone, prompting the user to re-wear the bone conduction earphone, adjusting the clamping force when the user wears the bone conduction earphone, and EQing the audio signal.
- the order of feedback on various working states of the bone conduction earphone can be adjusted adaptively according to the actual situation. For example, in some embodiments, whether the bone conduction earphone is in the wearing state can be detected and fed back first, and then one or more of whether the user is wearing well, clamping force, voltage, etc. can be detected and fed back. For another example, multiple working states of the bone conduction earphone can be determined at the same time.
- the detection and feedback of the working state of the bone conduction headset may be real-time detection, or detection at regular intervals (for example, 3s, 2min, etc.), or detection according to user input instructions.
- the method for optimizing the working state of the bone conduction earphone provided by the present application further includes performing some additional functions through the vibration sensor. Additional functions may include, but are not limited to, echo cancellation, picking up the user's voice signal, fall detection, assisting with spatial audio, and the like.
- vibration sensors may be used for echo cancellation.
- the vibration sensor can pick up the vibration of the earphone core as a microphone, and feed the vibration back to the earphone core for cancellation, so as to prevent the sound emitted by the earphone core from being transmitted to the earphone core, causing echo or howling.
- the position of the vibration sensor can be selected to be close to the headphone core, and the vibration near the headphone core can be directly picked up to eliminate.
- a vibration sensor may be used to pick up the user's voice signal.
- the vibration sensor since the earphone core fits the skin skull, when the user speaks while wearing the bone conduction earphone, the sound can also be transmitted to the earphone core through the skull in the reverse direction. At this time, the vibration of the earphone core is picked up by the vibration sensor, and the voice of the user can also be picked up.
- Using the vibration sensor to pick up the user's voice signal by vibration can resist the external air conduction noise. Compared with the traditional air conduction microphone, picking up the speaker's voice signal by vibration is basically free from external noise interference.
- vibration sensors may be used for fall detection.
- the vibration sensor may be a multi-axis sensor such as a one-axis vibration sensor, a three-axis vibration sensor, or the like.
- the vibration sensor may also be a rotational angular velocity type vibration sensor.
- the vibration sensor can sense the violent acceleration change that occurs when the user falls or has a tendency to fall, so as to predict that the user, especially the elderly, may fall. Further, the bone conduction earphone can make a corresponding warning based on the fall detection of the vibration sensor, or notify an emergency contact.
- vibration sensors may also be used to assist in implementing spatial audio. Specifically, the realization of the spatial audio first needs to determine the rotation direction of the user's head by means of a gyroscope, wherein the vibration sensor may include a gyroscope. In some embodiments, the vibration sensor may be multi-axis translational or rotational.
- the vibration sensor can also work together with other sensors.
- the vibration sensor can be combined with a physiological sensor to jointly detect the physiological state of the user when the user wears a bone conduction headset.
- FIG. 13 is a flowchart of a training method of a recognition model provided according to some embodiments of the present application. As shown in FIG. 13, the training method 1300 of the recognition model may include the following steps:
- Step 1310 obtain sample information.
- the sample information may include wearing records of at least two users, and the wearing records of the users may include the working state of the bone conduction earphone and the corresponding frequency response curve of the vibration of the earphone core, and the clamping force when the user wears the bone conduction earphone.
- Step 1320 Determine a sample type of each of the at least two user wearing records based on the sample information, where the sample type may include a positive sample type or a negative sample type.
- the working state of the bone conduction earphone may be determined as the user wearing state as a positive sample type, and the working state as the user not wearing state may be determined as a negative sample type.
- the working state of the bone conduction headset may be determined as a positive sample type when the user is wearing well, and the working state is determined as a negative sample type when the user is not wearing well.
- Step 1330 Determine the sample feature information corresponding to each of the at least two user wearing records based on the sample information.
- the sample characteristic information may include the vibration response characteristic of the earphone core and the working state of the bone conduction earphone.
- the vibration response characteristics of the earphone core may include, but are not limited to, one or more of the resonant frequency of the earphone core, the response peak value at a specific frequency, a quality factor, and an input voltage.
- the working states of the bone conduction earphones may include the user wearing state/user not wearing state, the user wearing well/user not wearing well state, the clamping force when the user wears the bone conduction earphone, the input voltage of the earphone core Wait.
- the vibration response feature may be directly extracted from sample information corresponding to the user's wearing record.
- the working state of the bone conduction earphone can be determined based on the vibration response characteristics. For details on judging the working state of the bone conduction earphone based on the vibration response feature, reference may be made to FIG. 1 to FIG. 11 and related descriptions of this specification.
- Step 1340 determining an identification model based on the sample characteristic information and the sample type of each of the at least two user wearing records.
- the sample feature information may be used as input, and each sample type of at least two user wearing records may be used as output to train an initial machine learning model to determine a recognition model.
- the recognition model may include at least one of a naive Bayes model, a linear regression model, a decision tree model, or a support vector machine model.
- FIG. 14 is a block diagram of the bone conduction earphone provided according to some embodiments of the present application.
- the bone conduction earphone 1000 may include an acquisition module 1410 , a determination module 1420 , and a control module 1430 .
- acquisition module 1410 may be used to acquire audio signals and vibration signals. Further, the acquisition module 1410 may include an earphone core and at least one vibration sensor, and the acquisition module 1410 may obtain data from the internal storage unit of the bone conduction headset or a terminal device (eg, mobile phone, computer, MP3, etc.) that is wired or wirelessly connected to the bone conduction headset. ) to acquire an audio signal, the earphone core can generate vibration in response to the audio signal, and the acquisition module 1410 can acquire a vibration signal based on the vibration of the earphone core through at least one vibration sensor.
- a terminal device eg, mobile phone, computer, MP3, etc.
- the determination module 1420 may determine the vibration response characteristic of the earphone core based on the audio signal and the vibration signal.
- the vibration response characteristic of the earphone core may include at least one of a resonance frequency of the earphone core, a response peak value at a specific frequency, a quality factor, and an input voltage.
- the determining module 1420 may determine whether the working state of the bone conduction earphone is the not wearing state based on the vibration response characteristic of the earphone core.
- the determining module 1420 may determine whether the working state of the bone conduction earphone is not well-wearing by the user based on the vibration response characteristic of the earphone core state. In some embodiments, when the working state of the bone conduction earphone is related to the clamping force when the user wears the bone conduction earphone, the determining module 1420 may be used to determine whether the clamping force when the user wears the bone conduction earphone is within a preset range . In some embodiments, the determination module 1420 may be used to identify the difference between the vibration response characteristic of the earphone core and the target response characteristic.
- the determination module 1420 may be configured to obtain a parameter value representing the input voltage of the earphone core based on the vibration response characteristic of the earphone core, and determine whether the parameter value is within the voltage threshold Inside. In some embodiments, the determining module 1420 may be configured to obtain parameter values related to the user's physiological parameters based on the vibration response characteristics of the earphone core.
- control module 1430 may be configured to provide feedback on the working state of the bone conduction earphone based on the vibration response characteristic of the earphone core. In some embodiments, when the working state of the bone conduction headset is a state that the user is not wearing the headset, the control module 1430 may be configured to generate an instruction to adjust the power consumption of the bone conduction headset. In some embodiments, when the working state of the bone conduction headset is that the user is not wearing it well, the control module 1430 may be used to control the bone conduction headset to send out prompt information.
- the control module 1430 may be used to generate an instruction to adjust the structure corresponding to the bone conduction headset, so as to change the time when the user wears the bone conduction headset the clamping force.
- the control module 1430 may be configured to perform EQ adjustment on the audio signal input to the headphone core according to the difference between the vibration response characteristic of the headphone core and the target vibration response characteristic.
- the control module 1430 may be used to adjust the amplitude of the audio signal input to the earphone core.
- the control module 1430 may be used to turn on or off the auxiliary module of the bone conduction headset.
- the bone conduction earphone 1400 may also include other modules, for example, a training module for training a recognition model, a signal processing module for processing audio signals or vibration signals, a power supply module for powering the bone conduction earphone, etc. .
- the other modules of the bone conduction earphone will not be repeated here.
- the acquisition module 1410 , the determination module 1420 , and the control module 1430 disclosed in FIG. 14 may be different modules in the bone conduction earphone, or one module may implement the functions of the above two or more modules.
- each module may share one storage module, and each module may also have its own storage module.
- aspects of this application may be illustrated and described in several patentable categories or situations, including any new and useful process, machine, product, or combination of matter, or combinations of them. of any new and useful improvements. Accordingly, various aspects of the present application may be performed entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.
- the above hardware or software may be referred to as a "data block”, “module”, “engine”, “unit”, “component” or “system”.
- aspects of the present application may be embodied as a computer product comprising computer readable program code embodied in one or more computer readable media.
- a computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on baseband or as part of a carrier wave.
- the propagating signal may take a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination.
- Computer storage media can be any computer-readable media other than computer-readable storage media that can communicate, propagate, or transmit a program for use by coupling to an instruction execution system, apparatus, or device.
- Program code on a computer storage medium may be transmitted over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.
- the computer program coding required for the operation of the various parts of this application may be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python Etc., conventional procedural programming languages such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages.
- the program code may run entirely on the user's computer, or as a stand-alone software package on the user's computer, or partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
- the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or to an external computer (eg, through the Internet), or in a cloud computing environment, or as a service Use eg software as a service (SaaS).
- LAN local area network
- WAN wide area network
- SaaS software as a service
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Otolaryngology (AREA)
- General Health & Medical Sciences (AREA)
- Neurosurgery (AREA)
- Manufacturing & Machinery (AREA)
- General Physics & Mathematics (AREA)
- Details Of Audible-Bandwidth Transducers (AREA)
- Vibration Prevention Devices (AREA)
- Apparatuses For Generation Of Mechanical Vibrations (AREA)
- Percussion Or Vibration Massage (AREA)
- Headphones And Earphones (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
Description
Claims (25)
- 一种优化骨传导耳机工作状态的方法,其特征在于,所述骨传导耳机包括耳机芯和至少一个振动传感器,所述方法包括:通过所述至少一个振动传感器获取振动信号,所述振动信号至少部分来源于所述耳机芯响应于一段音频信号而产生的振动,所述耳机芯的振动被配置为以骨传导的方式传递给佩戴所述骨传导耳机的用户;基于所述振动信号和所述音频信号,确定所述耳机芯的振动响应特征;以及基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈。
- 根据权利要求1所述的方法,其特征在于,所述振动响应特征至少包括所述耳机芯的谐振频率、特定频率的响应峰值、品质因子、输入电压中的一个。
- 根据权利要求1所述的方法,其特征在于,所述骨传导耳机的工作状态包括用户佩戴状态和用户未佩戴状态,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴状态;以及若所述工作状态为用户未佩戴状态,则生成指令来调整所述骨传导耳机的功耗。
- 根据权利要求3所述的方法,其特征在于,所述基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴状态包括:将所述耳机芯的振动响应特征输入识别模型;以及基于所述识别模型的输出,生成判断结果。
- 根据权利要求1所述的方法,其特征在于,所述骨传导耳机的工作状态包括用户佩戴良好状态和用户未佩戴良好状态,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴良好状态;以及若所述工作状态为用户未佩戴良好状态,则所述骨传导耳机发出提示信息。
- 根据权利要求5所述的方法,其特征在于,所述基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴良好状态包括:将所述耳机芯的振动响应特征输入识别模型;以及基于所述识别模型的输出,生成判断结果。
- 根据权利要求1所述的方法,其特征在于,所述骨传导耳机的工作状态与用户佩戴所述骨传导耳机时的夹紧力有关,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:基于所述耳机芯的振动响应特征,判断用户佩戴所述骨传导耳机时的夹紧力是否在预设范围内;以及若所述夹紧力未在所述预设范围内,则生成指令来调整所述骨传导耳机对应的结构,以改变用户佩戴所述骨传导耳机时的夹紧力。
- 根据权利要求7所述的方法,其特征在于,所述基于所述耳机芯的振动响应特征,判断用户佩戴所述骨传导耳机时的夹紧力是否在预设范围内包括:将所述耳机芯的振动响应特征输入识别模型;以及基于所述识别模型的输出,获取表征用户佩戴所述骨传导耳机时夹紧力的参数值;以及判断所述参数值是否在所述预设范围内。
- 根据权利要求1所述的方法,其特征在于,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:识别所述耳机芯的振动响应特征与目标振动响应特征的差异;根据所述差异,对输入所述耳机芯的音频信号进行EQ调节。
- 根据权利要求1所述的方法,其特征在于,所述骨传导耳机的工作状态包括所述耳机芯的输入电压,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:基于所述耳机芯的振动响应特征,获取表征所述耳机芯输入电压的参数值;判断所述参数值是否在电压阈值内;以及若所述参数值未在所述电压阈值内,调整输入所述耳机芯的音频信号的幅值。
- 根据权利要求1所述的方法,其特征在于,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:基于所述耳机芯的振动响应特征,获取与所述用户生理参数有关的参数值;以及基于所述参数值,开启或关闭所述骨传导耳机的辅助模块。
- 一种骨传导耳机,其特征在于,包括获取模块、确定模块以及控制 模块;所述获取模块通过至少一个振动传感器获取振动信号,所述振动信号至少部分来源于耳机芯响应于一段音频信号而产生的振动,所述耳机芯的振动被配置为以骨传导的方式传递给佩戴所述骨传导耳机的用户;所述确定模块基于所述振动信号和所述音频信号,确定所述耳机芯的振动响应特征;以及所述控制模块基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈。
- 根据权利要求12所述的骨传导耳机,其特征在于,所述振动响应特征至少包括所述耳机芯的谐振频率、特定频率的响应峰值、品质因子、输入电压中的一个。
- 根据权利要求12所述的骨传导耳机,其特征在于,所述骨传导耳机的工作状态包括用户佩戴状态和用户未佩戴状态,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:所述确定模块基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴状态;以及若所述工作状态为用户未佩戴状态,所述控制模块则生成指令来调整所述骨传导耳机的功耗。
- 根据权利要求14所述的骨传导耳机,其特征在于,所述基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴状态包括:所述获取模块将所述耳机芯的振动响应特征输入识别模型;以及所述确定模块基于所述识别模型的输出,生成判断结果。
- 根据权利要求12所述的骨传导耳机,其特征在于,所述骨传导耳机的工作状态包括用户佩戴良好状态和用户未佩戴良好状态,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:所述确定模块基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴良好状态;以及若所述工作状态为用户未佩戴良好状态,则所述控制模块控制所述骨传导耳机发出提示信息。
- 根据权利要求16所述的骨传导耳机,其特征在于,所述基于所述耳机芯的振动响应特征,判断所述工作状态是否为用户未佩戴良好状态包括:所述获取模块将所述耳机芯的振动响应特征输入识别模型;以及所述确定模块基于所述识别模型的输出,生成判断结果。
- 根据权利要求12所述的骨传导耳机,其特征在于,所述骨传导耳机的工作状态与用户佩戴所述骨传导耳机时的夹紧力有关,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:所述确定模块基于所述耳机芯的振动响应特征,判断用户佩戴所述骨传导耳机时的夹紧力是否在预设范围内;以及若所述夹紧力未在所述预设范围内,则所述控制模块生成指令来调整所述骨传导耳机对应的结构,以改变用户佩戴所述骨传导耳机时的夹紧力。
- 根据权利要求18所述的骨传导耳机,其特征在于,所述基于所述耳机芯的振动响应特征,判断用户佩戴所述骨传导耳机时的夹紧力是否在预设范围内包括:所述获取模块将所述耳机芯的振动响应特征输入识别模型;以及所述获取模块基于所述识别模型的输出,获取表征用户佩戴所述骨传导耳机时夹紧力的参数值;以及所述确定模块判断所述参数值是否在所述预设范围内。
- 根据权利要求19所述的骨传导耳机,其特征在于,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:所述确定模块识别所述耳机芯的振动响应特征与目标振动响应特征的差异;所述控制模块根据所述差异,对输入所述耳机芯的音频信号进行EQ调节。
- 根据权利要求12所述的骨传导耳机,其特征在于,所述骨传导耳机的工作状态包括所述耳机芯的输入电压,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:所述获取模块基于所述耳机芯的振动响应特征,获取表征所述耳机芯输入电压的参数值;所述确定模块判断所述参数值是否在电压阈值内;以及若所述参数值未在所述电压阈值内,所述控制模块调整输入所述耳机芯的音频信号的幅值。
- 根据权利要求12所述的骨传导耳机,其特征在于,所述基于所述耳机芯的振动响应特征,对所述骨传导耳机的工作状态进行反馈包括:所述获取模块基于所述耳机芯的振动响应特征,获取与所述用户生理参数有关的参数值;以及所述控制模块基于所述参数值,开启或关闭所述骨传导耳机的辅助模块。
- 一种识别模型的训练方法,其特征在于,包括:获取样本信息;基于所述样本信息确定至少两个用户佩戴记录中的每一个的样本类型,其中,所述样本类型包括正样本类型或负样本类型;基于所述样本信息确定与所述至少两个用户佩戴记录的每一个相对应样本特征信息;以及基于所述样本特征信息和所述至少两个用户佩戴记录的每一个的样本类型确定所述识别模型。
- 根据权利要求23所述的方法,其特征在于,包括:对于所述至少两个用户佩戴记录中的任何一个,所述样本特征信息包括耳机芯的振动响应特征和骨传导耳机的工作状态,以及基于所述样本信息,通过以下步骤获得对应于所述用户佩戴记录的所述样本特征信息:基于所述用户佩戴记录对应的所述样本信息中提取所述耳机芯的振动响应特征;以及基于所述耳机芯的振动响应特征判断所述骨传导耳机的工作状态。
- 根据权利要求23或24任一项所述的方法,其特征在于,包括:所述识别模型包括朴素贝叶斯模型、线性回归模型、决策树模型或支持向量机模型中的至少一个。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP21916956.2A EP4184941A4 (en) | 2021-01-11 | 2021-03-23 | METHOD FOR OPTIMIZING AN OPERATING STATE OF BONE CONDUCTION HEADPHONES |
KR1020237009781A KR20230056726A (ko) | 2021-01-11 | 2021-03-23 | 골전도 이어폰의 작동상태를 최적화하기 위한 방법 |
BR112023003598A BR112023003598A2 (pt) | 2021-01-11 | 2021-03-23 | Sistema e método para controle de dispositivo médico |
JP2023518841A JP2023543764A (ja) | 2021-01-11 | 2021-03-23 | 骨伝導イヤホンの動作状態の最適化方法 |
CN202180069747.0A CN116368818A (zh) | 2021-01-11 | 2021-03-23 | 一种优化骨传导耳机工作状态的方法 |
US18/164,673 US20230188886A1 (en) | 2021-01-11 | 2023-02-06 | Methods for optimizing working state of bone conduction earphones |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110033059.0 | 2021-01-11 | ||
CN202110033059 | 2021-01-11 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/164,673 Continuation US20230188886A1 (en) | 2021-01-11 | 2023-02-06 | Methods for optimizing working state of bone conduction earphones |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022147905A1 true WO2022147905A1 (zh) | 2022-07-14 |
Family
ID=82325126
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/082493 WO2022147905A1 (zh) | 2021-01-11 | 2021-03-23 | 一种优化骨传导耳机工作状态的方法 |
PCT/CN2021/141078 WO2022148249A1 (zh) | 2021-01-11 | 2021-12-24 | 一种阻抗装置及模拟头部对振动单元振动影响的系统 |
PCT/CN2022/128431 WO2023116200A1 (zh) | 2021-01-11 | 2022-10-28 | 一种阻抗装置及模拟头部对振动单元振动影响的系统 |
Family Applications After (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/141078 WO2022148249A1 (zh) | 2021-01-11 | 2021-12-24 | 一种阻抗装置及模拟头部对振动单元振动影响的系统 |
PCT/CN2022/128431 WO2023116200A1 (zh) | 2021-01-11 | 2022-10-28 | 一种阻抗装置及模拟头部对振动单元振动影响的系统 |
Country Status (9)
Country | Link |
---|---|
US (3) | US20220360885A1 (zh) |
EP (3) | EP4184941A4 (zh) |
JP (3) | JP2023543764A (zh) |
KR (3) | KR20230056726A (zh) |
CN (5) | CN114760553A (zh) |
BR (2) | BR112023003598A2 (zh) |
MX (1) | MX2023008715A (zh) |
TW (1) | TW202341761A (zh) |
WO (3) | WO2022147905A1 (zh) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106686496A (zh) * | 2016-12-27 | 2017-05-17 | 广东小天才科技有限公司 | 一种可穿戴设备的播放模式控制方法及可穿戴设备 |
WO2019198472A1 (ja) * | 2018-04-13 | 2019-10-17 | 有限会社エコ・テクノ | 骨伝導イヤホンマイクロホン |
CN110574103A (zh) * | 2018-06-29 | 2019-12-13 | 华为技术有限公司 | 一种语音控制方法、可穿戴设备及终端 |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5624377A (en) * | 1995-02-16 | 1997-04-29 | Larson-Davis, Inc. | Apparatus and method for simulating a human mastoid |
JP2005036821A (ja) * | 2003-07-15 | 2005-02-10 | Mitsubishi Heavy Ind Ltd | 除振装置およびその調整方法 |
KR101390502B1 (ko) * | 2012-02-03 | 2014-04-30 | 단국대학교 산학협력단 | 복합형 진동 제어장치 |
CN104322078B (zh) * | 2012-04-27 | 2018-06-05 | 布鲁尔及凯尔声音及振动测量公司 | 类人耳模拟器 |
US20140363002A1 (en) * | 2013-06-09 | 2014-12-11 | DSP Group | Indication of quality for placement of bone conduction transducers |
US9596534B2 (en) * | 2013-06-11 | 2017-03-14 | Dsp Group Ltd. | Equalization and power control of bone conduction elements |
JP6559064B2 (ja) * | 2013-06-19 | 2019-08-14 | Thk株式会社 | 音低減又は振動減衰装置及び構造部材 |
CN103644243B (zh) * | 2013-12-12 | 2015-10-07 | 西南交通大学 | 虚拟弹性可控阻尼器 |
JP6243223B2 (ja) * | 2013-12-26 | 2017-12-06 | 京セラ株式会社 | 測定システム及び測定方法 |
JP2016046600A (ja) * | 2014-08-20 | 2016-04-04 | 公立大学法人奈良県立医科大学 | 耳軟骨の伝導音の予測装置及びその方法 |
CN106954155B (zh) * | 2015-08-13 | 2019-08-16 | 深圳市韶音科技有限公司 | 骨传导扬声器 |
CN207039903U (zh) * | 2017-08-21 | 2018-02-23 | 深圳市韶音科技有限公司 | 一种音频振动测试装置 |
JP6724078B2 (ja) * | 2018-08-02 | 2020-07-15 | シェンヂェン ボクステック カンパニー リミテッドShenzhen Voxtech Co., Ltd | 骨伝導スピーカーのためのシステム |
DE102019000949A1 (de) * | 2019-02-08 | 2020-08-13 | Süddeutsche Gelenkscheibenfabrik GmbH & Co. KG | Tilgervorrichtung zur Reduzierung von auf einen Gebrauchsgegenstand übertragenen Tremorschwingungen |
CN110083911B (zh) * | 2019-04-19 | 2020-10-27 | 西安交通大学 | 一种电磁振动能量回收系统的建模优化方法 |
-
2021
- 2021-03-23 CN CN202110309633.0A patent/CN114760553A/zh active Pending
- 2021-03-23 KR KR1020237009781A patent/KR20230056726A/ko not_active Application Discontinuation
- 2021-03-23 WO PCT/CN2021/082493 patent/WO2022147905A1/zh active Application Filing
- 2021-03-23 BR BR112023003598A patent/BR112023003598A2/pt unknown
- 2021-03-23 CN CN202180069747.0A patent/CN116368818A/zh active Pending
- 2021-03-23 EP EP21916956.2A patent/EP4184941A4/en active Pending
- 2021-03-23 JP JP2023518841A patent/JP2023543764A/ja active Pending
- 2021-12-24 CN CN202180019704.1A patent/CN115244951A/zh active Pending
- 2021-12-24 WO PCT/CN2021/141078 patent/WO2022148249A1/zh unknown
- 2021-12-24 EP EP21917289.7A patent/EP4080909A4/en active Pending
- 2021-12-24 JP JP2022554896A patent/JP2023518002A/ja active Pending
- 2021-12-24 KR KR1020227030167A patent/KR20220134005A/ko active Search and Examination
- 2021-12-24 CN CN202111598684.6A patent/CN114760564A/zh active Pending
- 2021-12-24 BR BR112022015117A patent/BR112022015117A2/pt unknown
-
2022
- 2022-07-14 US US17/812,720 patent/US20220360885A1/en active Pending
- 2022-10-28 KR KR1020237024683A patent/KR20230124651A/ko active Search and Examination
- 2022-10-28 WO PCT/CN2022/128431 patent/WO2023116200A1/zh active Application Filing
- 2022-10-28 EP EP22899614.6A patent/EP4243451A1/en active Pending
- 2022-10-28 CN CN202211336995.XA patent/CN116347312A/zh active Pending
- 2022-10-28 JP JP2023543180A patent/JP2024503876A/ja active Pending
- 2022-10-28 MX MX2023008715A patent/MX2023008715A/es unknown
- 2022-12-16 TW TW111148434A patent/TW202341761A/zh unknown
-
2023
- 2023-02-06 US US18/164,673 patent/US20230188886A1/en active Pending
- 2023-06-04 US US18/328,761 patent/US20230351870A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106686496A (zh) * | 2016-12-27 | 2017-05-17 | 广东小天才科技有限公司 | 一种可穿戴设备的播放模式控制方法及可穿戴设备 |
WO2019198472A1 (ja) * | 2018-04-13 | 2019-10-17 | 有限会社エコ・テクノ | 骨伝導イヤホンマイクロホン |
CN110574103A (zh) * | 2018-06-29 | 2019-12-13 | 华为技术有限公司 | 一种语音控制方法、可穿戴设备及终端 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4184941A4 * |
Also Published As
Publication number | Publication date |
---|---|
JP2024503876A (ja) | 2024-01-29 |
JP2023518002A (ja) | 2023-04-27 |
EP4080909A4 (en) | 2023-08-16 |
EP4184941A1 (en) | 2023-05-24 |
BR112022015117A2 (pt) | 2022-09-27 |
CN115244951A (zh) | 2022-10-25 |
JP2023543764A (ja) | 2023-10-18 |
EP4243451A1 (en) | 2023-09-13 |
EP4184941A4 (en) | 2024-03-06 |
EP4080909A1 (en) | 2022-10-26 |
TW202341761A (zh) | 2023-10-16 |
US20230188886A1 (en) | 2023-06-15 |
CN116347312A (zh) | 2023-06-27 |
CN114760564A (zh) | 2022-07-15 |
US20220360885A1 (en) | 2022-11-10 |
CN116368818A (zh) | 2023-06-30 |
KR20230124651A (ko) | 2023-08-25 |
KR20220134005A (ko) | 2022-10-05 |
WO2023116200A1 (zh) | 2023-06-29 |
WO2022148249A1 (zh) | 2022-07-14 |
US20230351870A1 (en) | 2023-11-02 |
KR20230056726A (ko) | 2023-04-27 |
CN114760553A (zh) | 2022-07-15 |
BR112023003598A2 (pt) | 2023-10-17 |
MX2023008715A (es) | 2023-08-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9294849B2 (en) | Method and apparatus for detecting user activities from within a hearing assistance device using a vibration sensor | |
WO2022227514A1 (zh) | 一种耳机 | |
JP6100730B2 (ja) | イヤホン | |
EP2597891B1 (en) | Method and apparatus for hearing assistance device using MEMS sensors | |
US20080205679A1 (en) | In-Ear Auditory Device and Methods of Using Same | |
EP2882203A1 (en) | Hearing aid device for hands free communication | |
CN106888414A (zh) | 具有闭塞耳朵的说话者的自身语音体验的控制 | |
US10602274B2 (en) | Audio input/output device | |
EP3873110A1 (en) | Hearing aid determining turn-taking | |
US10582291B2 (en) | Wireless hearing device | |
TWI577193B (zh) | 耳膜助聽器 | |
US20210306726A1 (en) | Hearing device for identifying a sequence of movement features, and method of its operation | |
EP3021599A1 (en) | Hearing device having several modes | |
CN115250395A (zh) | 声学输入输出设备 | |
WO2022147905A1 (zh) | 一种优化骨传导耳机工作状态的方法 | |
WO2023087572A1 (zh) | 声学装置及其传递函数确定方法 | |
WO2023164954A1 (zh) | 一种听力辅助设备 | |
TW202322640A (zh) | 開放式聲學裝置 | |
WO2022227056A1 (zh) | 声学装置 | |
WO2022041166A1 (zh) | 一种听力辅助装置 | |
WO2022041168A1 (zh) | 一种检测骨导听力设备状态的方法和系统 | |
CN116762364A (zh) | 声学输入输出设备 | |
RU2801826C1 (ru) | Способы оптимизации рабочего состояния наушников с костной проводимостью | |
JP5781194B2 (ja) | マイクロホン | |
US9538295B2 (en) | Hearing aid specialized as a supplement to lip reading |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21916956 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202317011311 Country of ref document: IN |
|
ENP | Entry into the national phase |
Ref document number: 2021916956 Country of ref document: EP Effective date: 20230215 |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112023003598 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 20237009781 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2023518841 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 112023003598 Country of ref document: BR Kind code of ref document: A2 Effective date: 20230227 |