CN113660597A - In-ear detection method and device for wireless earphone and storage medium - Google Patents
In-ear detection method and device for wireless earphone and storage medium Download PDFInfo
- Publication number
- CN113660597A CN113660597A CN202111109240.1A CN202111109240A CN113660597A CN 113660597 A CN113660597 A CN 113660597A CN 202111109240 A CN202111109240 A CN 202111109240A CN 113660597 A CN113660597 A CN 113660597A
- Authority
- CN
- China
- Prior art keywords
- ear
- transfer function
- acoustic transfer
- earphone
- wireless earphone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 74
- 230000006870 function Effects 0.000 claims description 135
- 238000012546 transfer Methods 0.000 claims description 129
- 238000000034 method Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 230000005236 sound signal Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 230000008859 change Effects 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000035945 sensitivity 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
- H04R29/00—Monitoring arrangements; Testing arrangements
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2201/00—Details of transducers, loudspeakers or microphones covered by H04R1/00 but not provided for in any of its subgroups
- H04R2201/10—Details of earpieces, attachments therefor, earphones or monophonic headphones covered by H04R1/10 but not provided for in any of its subgroups
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Otolaryngology (AREA)
- Headphones And Earphones (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention discloses an in-ear detection method, a device and a storage medium of a wireless earphone, aiming at the problems that the existing real wireless earphone adopts an IR sensor to detect the in-ear, and an infrared emission source and an infrared receiving sensor are added on the original structure of the wireless earphone, so that the volume and the weight of the wireless earphone are increased, and the production cost is increased, the in-ear detection of the wireless earphone is realized by calculating the change of an acoustic transmission function between a loudspeaker and a microphone in the wireless earphone in the in-ear and out-ear states of the wireless earphone. The purpose of completing in-ear detection of the wireless earphone on the premise of not increasing electronic parts is achieved, and on one hand, the volume and the weight of the wireless earphone are reduced, and the wireless earphone is convenient to wear; on the other hand, the production cost is reduced.
Description
Technical Field
The invention belongs to the technical field of wireless earphones, and particularly relates to an in-ear detection method and device of a wireless earphone and a storage medium.
Background
With the rapid development of artificial intelligence technology, people pursue intellectualization, function diversification, humanization and the like of life ways more and more. The earphone is widely used by people as a main transmission tool of audio signals of intelligent electronic products. The conventional wired earphones have failed to satisfy the requirements of people for simple functions, and thus, various wireless earphones have appeared.
Among them, TWS (true wireless stereo) headphones are the most popular listening devices at present, the market demand is rapidly increasing, and headphone manufacturers face strong competition, and must improve the sound quality, comfort and stability of products to increase the competitiveness. In addition, a very important factor is the battery capacity, so that the service time between two times of charging is improved as much as possible. If increase battery self electric quantity, must use the bigger battery of volume, will lead to the volume increase of true wireless earphone, weight increase, reduce and wear the comfort. It is therefore feasible to automatically stop the playback when the headset is removed from the ear and resume the playback when worn in the ear, saving power usage and allowing the use of a relatively small battery.
To achieve such a convenient function, there are many proposals to add an (infra red) sensor in the earphone, such as an IR sensor of the mobile phone, which can sense whether the mobile phone is close to the face during a call, so as to turn off the screen. Then, how this technology works in a true wireless bluetooth headset with a smaller size, it is detected whether the headset is in the ear or out of the ear, please see the following description:
basic principle of IR sensor: referring to fig. 1, an invisible IR radiation source emits modulated pulses of light, ideally with emitted optical power concentrated in a narrow band, with a photodiode (photosensor) having peak sensitivity at a wavelength matching the peak intensity of the emitter. By tightly controlling the wavelength and modulation pulse at which the system operates, the sensor system can be protected from external IR energy sources (e.g., sunlight) and internal reflections from other optical components. When the emitted infrared light strikes a target within the range, it is reflected to a photodiode, converting the measured infrared energy into a value that increases proportionally with the approach of the target.
The IR sensor of a true wireless headset is typically set to trigger a detection signal when the ear is within 3 mm and release a signal when outside 10 mm.
The above-mentioned true wireless earphone using IR sensor needs to add two electronic components, namely an infrared emission source and an infrared receiving sensor, to the original design. Thus, the weight and the production cost of the wireless headset are increased.
Disclosure of Invention
The invention aims to provide an in-ear detection method, device and storage medium of a wireless earphone, which can realize the in-ear detection of the wireless earphone under the premise of not increasing electronic parts, reduce the volume and weight of the wireless earphone and facilitate wearing; on the other hand, the production cost is reduced.
In order to solve the problems, the technical scheme of the invention is as follows:
an in-ear detection method of a wireless headset, comprising:
driving a loudspeaker of the wireless earphone to send out an audio detection signal, acquiring an audio signal received by a microphone in the wireless earphone, and calculating an acoustic transfer function from the loudspeaker to the microphone; the acoustic transfer function varies with changes in the environment in which the wireless headset is located;
and comparing the acoustic transfer functions obtained at different time points through a preset algorithm, and judging whether the wireless earphone is in an in-ear state or not according to a comparison result.
According to an embodiment of the present invention, the comparing, by a preset algorithm, the acoustic transfer functions obtained at different time points, and determining whether the wireless headset is in an in-ear state according to a comparison result further includes:
acquiring an acoustic transfer function of the wireless earphone in an in-ear state as a default transfer function;
taking an acoustic transfer function obtained in the process of sending the audio detection signal by the loudspeaker as a target transfer function;
and matching the target transfer function with the default transfer function through the neural network model, and if the matching is successful, determining that the wireless earphone is in an in-ear state.
According to an embodiment of the present invention, the matching the target transfer function and the default transfer function through the neural network model further includes:
and training the neural network model by adopting a machine learning algorithm to ensure that the recognition precision of the neural network model meets the working requirement.
According to an embodiment of the present invention, the comparing, by a preset algorithm, the acoustic transfer functions obtained at different time points, and determining whether the wireless headset is in an in-ear state according to a comparison result further includes:
extracting features of the acoustic transfer function at different time points and different frequencies, the extracted features including at least one of: phase, amplitude; wherein, the frequency refers to the frequency used by the audio detection signal;
and judging whether the extracted characteristic values of the acoustic transfer functions meet the requirement of the wireless headset to be in an ear or not, and if so, judging that the wireless headset is in an ear-in state.
According to an embodiment of the invention, the phase is represented by at least one of the following parameters: a phase value of an acoustic transfer function at each audio detection signal frequency;
the amplitude is represented by at least one of the following parameters: each audio detects an amplitude value of the acoustic transfer function at a frequency of the signal.
According to an embodiment of the present invention, the comparing, by a preset algorithm, the acoustic transfer functions obtained at different time points, and determining whether the wireless headset is in an in-ear state according to a comparison result further includes:
extracting features of the acoustic transfer function at different time points and different frequencies, the extracted features including at least one of: phase, amplitude; wherein, the frequency refers to the frequency used by the audio detection signal;
inputting the extracted features into an earphone mode recognition model, and recognizing the state of the wireless earphone; the earphone mode recognition model is obtained through training, the characteristics of an acoustic transfer function sample are used as input in the training process, and the earphone mode when the sample is extracted is used as output; wherein the earphone mode comprises an in-ear mode or comprises an in-ear mode and an out-ear mode.
According to an embodiment of the present invention, the comparing, by a preset algorithm, the acoustic transfer functions obtained at different time points, and determining whether the wireless headset is in an in-ear state according to a comparison result further includes:
and weighting the acoustic transfer functions at different time points or frequencies, and removing or reducing the acoustic transfer functions with weight values smaller than a preset threshold value when the acoustic transfer functions are compared.
An in-ear detection device of a wireless headset, comprising:
the measuring module is used for driving a loudspeaker of the wireless earphone to send out an audio detection signal, acquiring an audio signal received by a microphone in the wireless earphone and calculating an acoustic transfer function from the loudspeaker to the microphone; the acoustic transfer function varies with changes in the environment in which the wireless headset is located;
and the judging module is used for comparing the acoustic transfer functions acquired at different time points through a preset algorithm and judging whether the wireless earphone is in an in-ear state or not according to a comparison result.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements an in-ear detection method of a wireless headset in an embodiment of the present invention.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects:
the in-ear detection method of the wireless earphone in the embodiment of the invention aims at the problems that the existing true wireless earphone adopts the IR sensor to detect the in-ear, and the infrared emission source and the infrared receiving sensor are added on the original structure of the wireless earphone, so that the volume and the weight of the wireless earphone are increased, and the production cost is increased. The purpose of completing in-ear detection of the wireless earphone on the premise of not increasing electronic parts is achieved, and on one hand, the volume and the weight of the wireless earphone are reduced, and the wireless earphone is convenient to wear; on the other hand, the production cost is reduced.
Drawings
FIG. 1 is a schematic diagram of the operation of an IR sensor in the background of the invention;
fig. 2 is a flow chart of in-ear detection for a wireless headset in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a wireless headset according to an embodiment of the invention;
fig. 4 is a block diagram of an in-ear detection apparatus of a wireless headset according to an embodiment of the invention.
Detailed Description
The following describes in detail an in-ear detection method, an in-ear detection device, and a storage medium of a wireless headset according to the present invention with reference to the accompanying drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims.
Example one
The in-ear detection method of the wireless earphone is provided, and in-ear detection of the wireless earphone is realized by calculating changes of acoustic transmission functions between a loudspeaker and a microphone in the wireless earphone in an in-ear state and an out-ear state of the wireless earphone. The purpose of completing in-ear detection of the wireless earphone on the premise of not increasing electronic parts is achieved, and on one hand, the volume and the weight of the wireless earphone are reduced, and the wireless earphone is convenient to wear; on the other hand, the production cost is reduced.
Specifically, referring to fig. 2, the method for detecting the in-ear position of the wireless headset includes the following steps:
s1: driving a loudspeaker of the wireless earphone to send out an audio detection signal, acquiring an audio signal received by a microphone in the wireless earphone, and calculating an acoustic transfer function from the loudspeaker to the microphone; the acoustic transfer function varies with changes in the environment in which the wireless headset is located;
s2: and comparing the acoustic transfer functions obtained at different time points through a preset algorithm, and judging whether the wireless earphone is in an in-ear state or not according to a comparison result.
Referring to fig. 3, the wireless headset in this embodiment includes a speaker a1, a microphone a2, and a controller A3, wherein the speaker a1 and the microphone a2 are respectively connected to the controller A3 through leads or a flexible circuit board. The execution body of the present embodiment may be the controller a3 in the wireless headset.
In step S1, it is understood that the controller A3 drives the speaker a1 of the wireless headset to emit a preset audio detection signal, acquires an audio signal received by the microphone a2 in the wireless headset, and calculates an acoustic transfer function from the speaker a1 to the microphone a 2.
The audio detection signal emitted from the speaker a1 may be a preset segment of audio detection signal, such as a segment of sinusoidal signal, where the sinusoidal signal is the signal with the most unique frequency component, and the frequency of the positive line signal is the preset frequency. It is understood that the length of the sinusoidal signal is not limited in this embodiment, and the length of the sinusoidal signal may be, for example, a 200Hz sinusoidal signal with a length of 0.5S. The audio detection signal may also be a pre-recorded voice, a broadcast voice, or a voice that is not sensitive to the human ear, such as a normal conversation voice or a piece of music.
It will be appreciated that the calculation of the transfer function requires a test (sonic detection) signal which is experienced by the user (without the experience of the general use being affected by the in-ear detection technique), a test signal which may be emitted by the user when using the test signal, or a sound signal which is perceived by the user as being relevant (prerecorded, broadcast, or sound which is not sensitive to the human ear). However, in this case, the transfer function with the same quality can not be calculated for all time or all frequency ranges of the (acoustic) signal, so that it is usually necessary to weight the change of the transfer function by using the characteristics of the test signal in the time domain, or the frequency domain, or both the time domain and the frequency domain, and then make the judgment for ear detection.
As for the acoustic transfer function, in a broad sense, the acoustic transfer function is a transfer function from a sound source to a reproduction region. In the present embodiment, the acoustic transfer function refers to a transfer function from the speaker a1 to the microphone a2 in the wireless headset.
For a fixed source, the position-dependent acoustic impulse response is usually denoted by h (x; t), meaning an acoustic impulse response at the x-point position at time t. And the acoustic impulse response is fourier transformed with respect to the wavenumber k, an acoustic transfer function H (x; k) is obtained. Since the variation of the acoustic transfer function of the speaker to the microphone of the wireless headset is sensitive to the state of the wireless headset (in-ear or out-of-ear), i.e. the acoustic transfer function varies with the environment in which the wireless headset is located. Therefore, the embodiment realizes in-ear detection based on the change of the transfer function from the loudspeaker to the microphone in the wireless headset, and does not need to additionally add a detection device (such as an IR sensor), thereby avoiding the increase of the weight and the production cost of the wireless headset.
Since the measurement calculation of the transfer function requires a detection signal and a reception signal, when the detection signal emitted from the speaker is relatively small in signal strength under some conditions, the signal received from the microphone receives an external interference signal in addition to the detection signal emitted from the speaker under some conditions, and the SNR (signal to noise ratio) of the signal at the frequency point or the time point is relatively poor, the transfer function calculated by using the detection signal or the reception signal at the frequency point or the time point is relatively unsuitable as a basis for the determination. Therefore, the present embodiment performs filtering processing on the audio detection signal transmitted by the speaker and/or the audio signal received by the microphone.
Specifically, the audio detection signal emitted by the speaker and/or the audio signal received by the microphone are filtered, and the signals meeting the following conditions are filtered out: the signal with the phase delay smaller than the set phase threshold value, or the signal with the phase delay smaller than the set phase threshold value and the intensity smaller than the set intensity threshold value, or the signal with the intensity smaller than the set intensity threshold value.
In step S2, comparing the acoustic transfer functions obtained at different time points by using a preset algorithm, and determining whether the wireless headset is in an in-ear state according to the comparison result further includes:
acquiring an acoustic transfer function of the wireless earphone in an in-ear state as a default transfer function;
taking an acoustic transfer function obtained in the process of sending the audio detection signal by the loudspeaker as a target transfer function;
and matching the target transfer function with the default transfer function, and if the matching is successful, determining that the wireless earphone is in an in-ear state.
In practical application, the transfer function of the wireless earphone in the in-ear state can be pre-calculated and used as the default transfer function for comparison in the subsequent judgment of the earphone state. When the controller A3 drives the speaker A1 to emit an audio detection signal, the audio signal received by the microphone is acquired, the transfer function from the speaker to the microphone is calculated, and the transfer function is taken as the target transfer function. And matching the target transfer function with the default transfer function, and if the matching is successful, determining that the wireless earphone is in an in-ear state. The default transfer function for the in-ear condition may be one or more of different transfer functions, such as when the headset is worn more tightly and when the headset is worn less tightly.
The transfer function of the wireless earphone in the ear state can be pre-calculated and used as the default transfer function for comparison in the subsequent judgment of the earphone state. When the controller A3 drives the speaker A1 to emit an audio detection signal, the audio signal received by the microphone is acquired, the transfer function from the speaker to the microphone is calculated, and the transfer function is taken as the target transfer function. And matching the target transfer function with the default transfer function, and if the matching is successful, determining that the wireless earphone is in an ear-out state.
The default transfer function for the out-of-ear state may be one or more of, for example, the headset is held in the air, the headset is placed face up, the headset is placed face down, etc. The transfer function has different characteristics for different headset positions.
The matching of the target transfer function and the default transfer function can be realized by the traditional absolute value comparison, relative value comparison, fuzzy comparison and the like, and can also be realized by the machine learning and neural network modes.
Besides the above algorithm, the in-ear detection of the wireless headset can be realized by the following method:
extracting features of the acoustic transfer function at different time points and different frequencies, wherein the extracted features include at least one of: phase, amplitude; wherein, the frequency refers to the frequency used by the audio detection signal;
and judging whether the extracted characteristic values of the acoustic transfer functions mark the requirement of the earphone to be in-ear, if so, judging that the wireless earphone is in an in-ear state.
The phase can be represented by at least one of the following parameters: the phase value of the acoustic transfer function at each audio detection signal frequency. The amplitude may be represented by at least one of the following parameters: each audio detects an amplitude value of the acoustic transfer function at a frequency of the signal.
When judging whether the extracted characteristic values of the acoustic transfer functions are in accordance with the requirement of the earphone to be in the ear, judging whether the characteristic values are in the value range by presetting the value range for identifying the earphone to be in the ear state, and if so, determining that the earphone is in the ear. The extracted characteristic values can be compared in absolute value or relative value to judge the state of the earphone.
The characteristic value of the acoustic transfer function can be used as input through a neural network (neural networks), and the neural network is trained by adopting a machine learning algorithm, so that the neural network outputs a result (such as earphone in-ear or earphone out-ear) according to a trained mode. Namely: extracting features of the acoustic transfer function at different time points and different frequencies, the extracted features including at least one of: phase, amplitude; here, the frequency refers to a frequency used for the audio detection signal;
inputting the extracted features into an earphone mode recognition model (applying a neural network) and recognizing the state of the wireless earphone; the method comprises the steps that an earphone mode recognition model is obtained through training, the characteristics of an acoustic transfer function sample are used as input in the training process, and an earphone mode when the sample is extracted is used as output; the earphone mode comprises an in-ear mode or comprises an in-ear mode and an out-ear mode.
When the extracted features are used for identifying the state of the wireless earphone, a machine learning method is used for training an algorithm model with a classification function based on a sample to realize identification, and the extracted features are input into the classifier to obtain a classification result such as in-ear or out-ear. When there are a plurality of features used (for example, a plurality of different parameters such as phase and amplitude are used as features at the same time, but one parameter may also have a plurality of features such as power of signals at a plurality of frequencies), it may be determined to be in-ear or out-of-ear when the plurality of features all satisfy the condition, but the present invention is not limited thereto. The predetermined number or ratio of features may satisfy the condition, that is, the features are determined to be in-ear or out-of-ear, which may be determined in a suitable manner by training, learning, or statistics of the samples.
Since the transfer function needs to be calculated, the detection signal may be a (sound wave) signal originally emitted when the earphone is used, or may be a sound signal (prerecording, broadcast sound, or sound insensitive to human ears) which feels comfortable. Therefore, due to the diversity of the detection signals, there is a difference in the transfer function obtained at any time or at any frequency. Therefore, in order to improve the accuracy of the in-ear detection of the wireless headset, the change of the transfer function due to the characteristics of the detection signal in the time domain, the frequency domain, or the time domain plus the frequency domain needs to be weighted and then determined. That is, in this embodiment, the acoustic transfer functions at different time points or frequencies are weighted, and when the acoustic transfer functions are compared, the acoustic transfer functions with weight values smaller than the preset threshold are removed or reduced.
For example: as soon as the detection signal is not signaled at a certain time point, the accuracy of the transfer function calculated at that time point (i.e. the pause of the broadcast sound) is poor, and when making an in-ear decision, the decision of in-ear or out-of-ear calculated by the transfer function at the time instant of confidence in this time segment can be reduced.
In another example, a detection signal has no or very little energy in a frequency band a, and the characteristic of the transfer function calculated by using the detection signal in the frequency band a is not reliable. The weight of this portion is removed or reduced when making the ear decision.
Example two
The present embodiment provides an in-ear detection device for a wireless headset, please refer to fig. 4, which includes:
the measuring module 1 is used for driving a loudspeaker of the wireless earphone to send out an audio detection signal, acquiring an audio signal received by a microphone in the wireless earphone, and calculating an acoustic transfer function from the loudspeaker to the microphone; the acoustic transfer function varies with changes in the environment in which the wireless headset is located;
and the judging module 2 is used for comparing the acoustic transfer functions acquired at different time points through a preset algorithm and judging whether the wireless earphone is in an in-ear state according to a comparison result.
The determining module 2 includes a first determining unit, a second determining unit and a third determining unit. The first judging unit, the second judging unit and the third judging unit are independent and parallel units which can realize the judgment of the wireless earphone in the ear, and the difference is that different methods are adopted to realize the judgment of the wireless earphone in the ear.
Specifically, the first judging unit obtains an acoustic transfer function of the wireless earphone in an in-ear state as a default transfer function; taking an acoustic transfer function obtained in the process of sending the audio detection signal by the loudspeaker as a target transfer function; and matching the target transfer function with the default transfer function, and if the matching is successful, determining that the wireless earphone is in an in-ear state, so as to judge the in-ear state of the wireless earphone.
The second judging unit extracts features of the acoustic transfer function at different time points and different frequencies, wherein the extracted features comprise at least one of the following: phase, amplitude; the designated frequency refers to a frequency used by the audio detection signal; and judging whether the extracted characteristic values of the acoustic transfer functions meet the requirement of the wireless headset to enter the ear or not, if so, judging that the wireless headset is in an in-ear state, and judging the wireless headset to enter the ear. Specifically, the extracted feature values can be realized by absolute value comparison, relative value comparison, fuzzy comparison and the like.
The third judging unit extracts features of the acoustic transfer function at different time points and different frequencies, wherein the extracted features comprise at least one of the following: phase, amplitude; here, the frequency refers to a frequency used for the audio detection signal; and inputting the extracted features into an earphone mode recognition model, and recognizing the state of the wireless earphone to judge the in-ear state of the wireless earphone. The method comprises the steps that an earphone mode recognition model is obtained through training, the characteristics of an acoustic transfer function sample are used as input in the training process, and an earphone mode when the sample is extracted is used as output; the earphone mode comprises an in-ear mode or comprises an in-ear mode and an out-ear mode.
The functions and implementation manners of the measurement module 1 and the determination module 2 are as described in the first embodiment, and are not described herein again.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium. The computer-readable storage medium has instructions stored therein, which when executed on a computer, cause the computer to perform the steps of the in-ear detection method of a wireless headset according to the first embodiment.
The modules in the second embodiment, if implemented in the form of software functional modules and sold or used as independent products, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be substantially or partially implemented in software, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and devices may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, it is still within the scope of the present invention if they fall within the scope of the claims of the present invention and their equivalents.
Claims (9)
1. An in-ear detection method for a wireless headset, comprising:
driving a loudspeaker of the wireless earphone to send out an audio detection signal, acquiring an audio signal received by a microphone in the wireless earphone, and calculating an acoustic transfer function from the loudspeaker to the microphone; the acoustic transfer function varies with changes in the environment in which the wireless headset is located;
and comparing the acoustic transfer functions obtained at different time points through a preset algorithm, and judging whether the wireless earphone is in an in-ear state or not according to a comparison result.
2. The method as claimed in claim 1, wherein the comparing the acoustic transfer functions obtained at different time points by a predetermined algorithm, and the determining whether the wireless headset is in the in-ear state according to the comparison result further comprises:
acquiring an acoustic transfer function of the wireless earphone in an in-ear state as a default transfer function;
taking an acoustic transfer function obtained in the process of sending the audio detection signal by the loudspeaker as a target transfer function;
and matching the target transfer function with the default transfer function through the neural network model, and if the matching is successful, determining that the wireless earphone is in an in-ear state.
3. The in-ear detection method of a wireless headset of claim 2, wherein the matching the target transfer function to the default transfer function via the neural network model further comprises:
and training the neural network model by adopting a machine learning algorithm to ensure that the recognition precision of the neural network model meets the working requirement.
4. The method as claimed in claim 1, wherein the comparing the acoustic transfer functions obtained at different time points by a predetermined algorithm, and the determining whether the wireless headset is in the in-ear state according to the comparison result further comprises:
extracting features of the acoustic transfer function at different time points and different frequencies, the extracted features including at least one of: phase, amplitude; wherein, the frequency refers to the frequency used by the audio detection signal;
and judging whether the extracted characteristic values of the acoustic transfer functions meet the requirement of the wireless headset to be in an ear or not, and if so, judging that the wireless headset is in an ear-in state.
5. The in-ear detection method of a wireless headset according to claim 4, wherein the phase is represented by at least one of the following parameters: a phase value of an acoustic transfer function at each audio detection signal frequency;
the amplitude is represented by at least one of the following parameters: each audio detects an amplitude value of the acoustic transfer function at a frequency of the signal.
6. The method as claimed in claim 1, wherein the comparing the acoustic transfer functions obtained at different time points by a predetermined algorithm, and the determining whether the wireless headset is in the in-ear state according to the comparison result further comprises:
extracting features of the acoustic transfer function at different time points and different frequencies, the extracted features including at least one of: phase, amplitude; wherein, the frequency refers to the frequency used by the audio detection signal;
inputting the extracted features into an earphone mode recognition model, and recognizing the state of the wireless earphone; the earphone mode recognition model is obtained through training, the characteristics of an acoustic transfer function sample are used as input in the training process, and the earphone mode when the sample is extracted is used as output; wherein the earphone mode comprises an in-ear mode or comprises an in-ear mode and an out-ear mode.
7. The method as claimed in claim 1, wherein the comparing the acoustic transfer functions obtained at different time points by a predetermined algorithm, and the determining whether the wireless headset is in the in-ear state according to the comparison result further comprises:
and weighting the acoustic transfer functions at different time points or frequencies, and removing or reducing the acoustic transfer functions with weight values smaller than a preset threshold value when the acoustic transfer functions are compared.
8. An in-ear detection device for a wireless headset, comprising:
the measuring module is used for driving a loudspeaker of the wireless earphone to send out an audio detection signal, acquiring an audio signal received by a microphone in the wireless earphone and calculating an acoustic transfer function from the loudspeaker to the microphone; the acoustic transfer function varies with changes in the environment in which the wireless headset is located;
and the judging module is used for comparing the acoustic transfer functions acquired at different time points through a preset algorithm and judging whether the wireless earphone is in an in-ear state or not according to a comparison result.
9. A computer-readable storage medium, having a computer program stored thereon, which, when being executed by a processor, implements a method of in-ear detection for a wireless headset according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111109240.1A CN113660597A (en) | 2021-09-22 | 2021-09-22 | In-ear detection method and device for wireless earphone and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111109240.1A CN113660597A (en) | 2021-09-22 | 2021-09-22 | In-ear detection method and device for wireless earphone and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113660597A true CN113660597A (en) | 2021-11-16 |
Family
ID=78484056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111109240.1A Pending CN113660597A (en) | 2021-09-22 | 2021-09-22 | In-ear detection method and device for wireless earphone and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113660597A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117528333A (en) * | 2024-01-05 | 2024-02-06 | 九音科技(南京)有限公司 | State detection method and device of ear-wearing type audio equipment, audio equipment and medium |
| CN117714939A (en) * | 2024-02-05 | 2024-03-15 | 九音科技(南京)有限公司 | In-ear detection method and system based on spectrum analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100189269A1 (en) * | 2009-01-23 | 2010-07-29 | Sony Ericsson Mobile Communications Ab | Acoustic in-ear detection for earpiece |
| WO2014061578A1 (en) * | 2012-10-15 | 2014-04-24 | Ｎｅｃカシオモバイルコミュニケーションズ株式会社 | Electronic device and acoustic reproduction method |
| CN110326305A (en) * | 2017-02-24 | 2019-10-11 | 伯斯有限公司 | In-Ear Headphones are detected from head |
| US20200374617A1 (en) * | 2019-05-23 | 2020-11-26 | Beijing Xiaoniao Tingting Technology Co., Ltd | Method and device for detecting wearing state of earphone and earphone |
| CN112272346A (en) * | 2020-11-27 | 2021-01-26 | 歌尔科技有限公司 | In-ear detection method, earphone and computer readable storage medium |
| US10939193B1 (en) * | 2020-03-02 | 2021-03-02 | Ifory Limited | In-ear detection method for a wireless earphone and a wireless earphone |
| CN112911485A (en) * | 2021-02-09 | 2021-06-04 | 恒玄科技(上海)股份有限公司 | Wireless earphone in and out ear detection method, wireless earphone and medium |
| CN112911487A (en) * | 2021-02-09 | 2021-06-04 | 恒玄科技(上海)股份有限公司 | In-ear detection method for wireless headset, wireless headset and storage medium |
| CN113115148A (en) * | 2020-01-10 | 2021-07-13 | 北京钛方科技有限责任公司 | Earphone and in-ear detection method and device |
-
2021
- 2021-09-22 CN CN202111109240.1A patent/CN113660597A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100189269A1 (en) * | 2009-01-23 | 2010-07-29 | Sony Ericsson Mobile Communications Ab | Acoustic in-ear detection for earpiece |
| WO2014061578A1 (en) * | 2012-10-15 | 2014-04-24 | Ｎｅｃカシオモバイルコミュニケーションズ株式会社 | Electronic device and acoustic reproduction method |
| CN110326305A (en) * | 2017-02-24 | 2019-10-11 | 伯斯有限公司 | In-Ear Headphones are detected from head |
| US20200374617A1 (en) * | 2019-05-23 | 2020-11-26 | Beijing Xiaoniao Tingting Technology Co., Ltd | Method and device for detecting wearing state of earphone and earphone |
| CN113115148A (en) * | 2020-01-10 | 2021-07-13 | 北京钛方科技有限责任公司 | Earphone and in-ear detection method and device |
| US10939193B1 (en) * | 2020-03-02 | 2021-03-02 | Ifory Limited | In-ear detection method for a wireless earphone and a wireless earphone |
| CN112272346A (en) * | 2020-11-27 | 2021-01-26 | 歌尔科技有限公司 | In-ear detection method, earphone and computer readable storage medium |
| CN112911485A (en) * | 2021-02-09 | 2021-06-04 | 恒玄科技(上海)股份有限公司 | Wireless earphone in and out ear detection method, wireless earphone and medium |
| CN112911487A (en) * | 2021-02-09 | 2021-06-04 | 恒玄科技(上海)股份有限公司 | In-ear detection method for wireless headset, wireless headset and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 郭小朝: "头部关联传递函数线性滤波器模型建构方法", 人类工效学, vol. 6, no. 03, 30 September 2000 (2000-09-30), pages 58 - 59 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117528333A (en) * | 2024-01-05 | 2024-02-06 | 九音科技(南京)有限公司 | State detection method and device of ear-wearing type audio equipment, audio equipment and medium |
| CN117528333B (en) * | 2024-01-05 | 2024-04-12 | 九音科技(南京)有限公司 | State detection method and device of ear-wearing type audio equipment, audio equipment and medium |
| CN117714939A (en) * | 2024-02-05 | 2024-03-15 | 九音科技(南京)有限公司 | In-ear detection method and system based on spectrum analysis |
| CN117714939B (en) * | 2024-02-05 | 2024-05-24 | 九音科技(南京)有限公司 | In-ear detection method and system based on spectrum analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110785808B (en) | Audio device with wake-up word detection | |
| CN113709613B (en) | Volume adjustment method and device and computer readable storage medium | |
| CN113660597A (en) | In-ear detection method and device for wireless earphone and storage medium | |
| CN108540900B (en) | Volume adjusting method and related product | |
| WO2021179280A1 (en) | Earphone and method for detecting wearing state thereof | |
| CN113630708B (en) | Method and device for detecting abnormal earphone microphone, earphone kit and storage medium | |
| CN101828410A (en) | Be used for the auxiliary method and system of wireless hearing | |
| US20210144495A1 (en) | Microphone Hole Blockage Detection Method, Microphone Hole Blockage Detection Device, and First Wireless Earphone | |
| CN101843118A (en) | Be used for the auxiliary method and system of wireless hearing | |
| CN112992169A (en) | Voice signal acquisition method and device, electronic equipment and storage medium | |
| CN112218198A (en) | Portable device and operation method thereof | |
| CN104168369A (en) | Adjusting method and apparatus of terminal scene mode | |
| CN106604183B (en) | Method and device for controlling pickup range of multi-microphone noise reduction of terminal | |
| CN104754462A (en) | Automatic regulating device and method for volume and earphone | |
| US11297429B2 (en) | Proximity detection for wireless in-ear listening devices | |
| US20240257795A1 (en) | Noise reduction parameter setting method and apparatus, earphone device and storage medium | |
| US20220230657A1 (en) | Voice control method and apparatus, chip, earphones, and system | |
| CN108696813A (en) | Method for operating a hearing device and hearing device | |
| CN104601825A (en) | Control method and control device | |
| CN218162834U (en) | Sound box system | |
| CN111885459B (en) | Audio processing method, audio processing device and intelligent earphone | |
| CN109151195B (en) | Earphone control method and control system during running exercise | |
| CA3196230A1 (en) | Systems and methods for own voice detection in a hearing system | |
| CN105721731B (en) | A kind of mobile phone ringtone volume automatic regulating method and its device | |
| CN111711915B (en) | Audio part selection method and audio part selection device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |