Noise reduction processing method, device, equipment, earphone and storage medium

Abstract

The present invention provides a noise reduction processing method, device, equipment, headphones and storage medium, the method comprising the steps of: when it is detected that the noise reduction headphones are in a wearing state and the noise reduction mode is in an on state, collecting first voice data in the surrounding environment; extracting voiceprint feature information to be identified based on the first voice data; comparing the similarity of registered voiceprint feature information in a registered voiceprint library with the voiceprint feature information to be identified one by one; and when there is at least one similarity greater than a first preset threshold, performing a preset action on the noise reduction headphones; the present application avoids the problem that the user cannot hear other people's calls when wearing headphones, which is not conducive to communication, and improves the wearer's communication experience with others.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a noise reduction processing method, device, equipment, earphone and storage medium. Background Art

[0002] With the advancement of technology, the noise reduction performance of noise reduction headphones has been continuously improved, and noise reduction headphones have been loved by more and more users. Noise reduction headphones can effectively suppress environmental noise, allowing the wearer to enjoy wonderful audio data even in a noisy environment and hear the audio stream in the headphones more clearly.

[0003] However, since noise-cancelling headphones suppress the sound of people speaking while suppressing ambient noise, users cannot hear other people's calls when wearing the headphones, which causes embarrassment and affects the normal communication between two people. Summary of the invention

[0004] In view of the problems in the prior art, the purpose of the present invention is to provide a noise reduction processing method, device, equipment, headphones and storage medium to solve the problem that the existing noise reduction processing methods, while reducing noise, affect people's normal communication and are not conducive to communication.

[0005] To achieve the above object, the present invention provides a noise reduction processing method, which comprises the following steps:

[0006] S110, when it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state, collecting first voice data in the surrounding environment;

[0007] S120, extracting voiceprint feature information to be recognized based on the first voice data;

[0008] S130, comparing the similarity between the registered voiceprint feature information in the registered voiceprint database and the voiceprint feature information to be identified one by one; and

[0009] S140: When there is at least one similarity greater than a first preset threshold, a preset action is performed on the noise-cancelling headset to transmit external sound to a target user wearing the noise-cancelling headset.

[0010] Optionally, before step S130, the method further includes:

[0011] Collecting second voice data corresponding to historical conversations of a target user wearing the noise reduction headset within a first preset time period in the past;

[0012] All voiceprints in the second voice data are extracted, and N voiceprints with the highest frequency of occurrence among all voiceprints are registered to form a registered voiceprint library; N is an integer.

[0013] Optionally, before step S130, the method further includes:

[0014] While collecting the registered voiceprint feature information, the location information is collected, and the collected location information is associated with the registered voiceprint feature information, and a registered voiceprint library is formed based on the collected registered voiceprint feature information;

[0015] Grouping the registered voiceprint feature information based on the associated position information to form a first mapping relationship between the position information and the voiceprint group;

[0016] Get the current location information of the noise-canceling headphones;

[0017] Based on the first mapping relationship, determining a target voiceprint group matching the current location information;

[0018] Step S130 includes:

[0019] The similarities between the registered voiceprint feature information in the target voiceprint group and the voiceprint feature information to be identified are compared one by one.

[0020] Optionally, step S110 includes: simultaneously collecting current position information of the noise reduction headset;

[0021] Step S130 includes:

[0022] Building a training set based on historical conversation data of a target user wearing the noise-cancelling headset at different locations;

[0023] Based on the training set, a preset network model is trained to obtain an initial network model; in the initial network model, parameter weights for the same interlocutor at different positions are different, and the parameter weights are associated with the positions;

[0024] Based on the current location information, determining parameter weights in the initial network model to form a target network model;

[0025] Based on the target network model, the similarity between the registered voiceprint feature information in the voiceprint library and the voiceprint feature information to be identified is determined one by one.

[0026] Optionally, constructing a training set based on historical conversation data of a target user wearing the noise-cancelling headset at different locations includes:

[0027] Acquire historical conversation data of a target user wearing the noise cancelling headset at different locations within a historical time period as initial training data; the historical conversation data includes wearing state change data of the noise cancelling headset within a preset time period after the start of the conversation;

[0028] From the initial training data, historical conversation data corresponding to the switching of the noise cancelling headset from a wearing state to a non-wearing state within a preset time after the start of the conversation is selected as target training data;

[0029] A training set is constructed based on the target training data.

[0030] Optionally, before step S130, the method further includes:

[0031] Register based on the specified voiceprint feature information to form a registered voiceprint library.

[0032] Optionally, the method further comprises:

[0033] Acquire the registered voiceprint feature information corresponding to the similarity greater than the first preset threshold as the target voiceprint; and continue to collect the third voice data of the surrounding environment;

[0034] When the target voiceprint and the voiceprint feature information of the target user are continuously not recognized from the third voice data within a second preset time period, the noise reduction mode of the noise reduction headset is turned on.

[0035] Optionally, step S110 includes:

[0036] Voice data whose audio intensity from the noise reduction headset in the surrounding environment is greater than a second preset threshold is collected as the first voice data.

[0037] Optionally, step S130 includes:

[0038] When it is detected that the power of the noise-cancelling headset is lower than a third preset threshold, and the noise-cancelling headset is connected to a terminal device, the similarity between the registered voiceprint feature information in the registered voiceprint library and the voiceprint feature information to be identified is compared one by one based on the terminal device;

[0039] Step S140 is:

[0040] When there is at least one similarity greater than a first preset threshold, the terminal device sends a preset instruction to the noise reduction headset;

[0041] The noise reduction earphones perform preset tasks based on the preset instructions.

[0042] Optionally, the preset action is to turn off the noise reduction mode or turn on the transparency mode.

[0043] The present invention also provides a noise reduction processing device, which is used to implement the above-mentioned noise reduction processing method, and the device comprises:

[0044] The first voice data collection module collects first voice data in the surrounding environment when it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state;

[0045] A first voiceprint extraction module extracts voiceprint feature information to be identified based on the first voice data;

[0046] A first voiceprint comparison module compares the similarity between the registered voiceprint feature information in the registered voiceprint database and the voiceprint feature information to be identified one by one;

[0047] The execution module executes a preset action on the noise reduction headset when at least one similarity is greater than a first preset threshold.

[0048] The present invention also provides a noise reduction processing device, comprising:

[0049] processor;

[0050] a memory in which an executable program of the processor is stored;

[0051] The processor is configured to execute the steps of any one of the above-mentioned noise reduction processing methods by executing the executable program.

[0052] The present invention also provides an earphone, which comprises the above-mentioned noise reduction processing device.

[0053] The present invention also provides a computer-readable storage medium for storing a program, wherein the program, when executed by a processor, implements the steps of any one of the above-mentioned noise reduction processing methods.

[0054] Compared with the prior art, the present invention has the following advantages and outstanding effects:

[0055] The noise reduction processing method, device, equipment, earphone and storage medium provided by the present invention detect voice data in the environment, and when the registered voiceprint feature information is identified, a preset action is performed on the noise reduction earphone, such as turning off the noise reduction mode; this avoids the problem that the user cannot hear other people's calls when wearing earphones, which is not conducive to communication, and improves the wearer's communication experience with others. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Other features, objectives and advantages of the present invention will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following accompanying drawings.

[0057] Figure 1 A schematic diagram of a noise reduction processing method disclosed in an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of a noise reduction processing method disclosed in another embodiment of the present invention;

[0059] Figure 3 A schematic diagram of a noise reduction processing method disclosed in another embodiment of the present invention;

[0060] Figure 4 A schematic diagram of a noise reduction processing method disclosed in another embodiment of the present invention;

[0061] Figure 5 It is a flowchart of step S131 in the noise reduction processing method disclosed in one embodiment of the present invention;

[0062] Figure 6 A schematic diagram of the structure of a noise reduction processing device disclosed in one embodiment of the present invention;

[0063] Figure 7 A schematic diagram of the structure of a noise reduction processing device disclosed in one embodiment of the present invention;

[0064] Figure 8 A schematic diagram of the structure of a computer-readable storage medium disclosed in one embodiment of the present invention. DETAILED DESCRIPTION

[0065] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their repeated description will be omitted.

[0066] Exemplarily, the present application exemplifies the structure and function of a noise reduction headset. The noise reduction headset may include a variety of sound modes, such as noise reduction mode, normal mode, transparent mode, etc. The noise reduction mode includes an active noise reduction function, which is to generate a reverse sound wave equal to the external noise through the noise reduction system to neutralize the noise, thereby achieving the effect of noise reduction. The normal mode is a mode without any additional processing of the sound, and the audio played in the headset is the audio effect of the original audio. The transparent mode means that the ambient sound data is not muted, so that the user can clearly hear the external environmental sound, allowing the headset user to communicate normally with the outside world.

[0067] like Figure 1 As shown, an embodiment of the present invention discloses a noise reduction processing method for a noise reduction headset, the method comprising the following steps:

[0068] S110, when it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state, first voice data in the surrounding environment is collected. Specifically, audio data of a person speaking in the environment is collected as the first voice data.

[0069] The above-mentioned wearing state detection can be realized by infrared sensor and other technologies. For example, when the second end of the earphone can detect the infrared signal emitted by the first end, it means that the earphone is in the wearing state. If no infrared signal is detected, it means that the earphone is not in the wearing state. This detection can also be realized by existing technology, and this application will not elaborate on it.

[0070] In one embodiment of the present application, in this step, voice data whose audio intensity in the surrounding environment is greater than a second preset threshold value at a distance from the noise-cancelling headset can be collected as the first voice data. That is, the position of the noise-cancelling headset is used as the collection point, and the audio data whose audio intensity is greater than the second preset threshold value is screened out from the collected surrounding voice data as the first voice data. That is, because the conversation between two people is usually face-to-face communication, this embodiment only collects audio data of the speaker who is closer to the headset wearer, which is conducive to improving the detection accuracy of the conversation audio with the headset wearer. Exemplarily, the above-mentioned second preset threshold value can be 60 decibels. This application is not limited to this.

[0071] S120, extracting the voiceprint feature information to be identified based on the first voice data. Specifically, for example, after performing voice endpoint detection on the first voice data, voice enhancement can be performed, and then effective voice can be extracted, and then voiceprint features can be extracted, so as to obtain the voiceprint feature information to be identified in the surrounding environment. In other embodiments, the implementation of this step can also be implemented with reference to the prior art.

[0072] S130, comparing the similarity of the registered voiceprint feature information in the registered voiceprint library with the voiceprint feature information to be identified one by one. Specifically, the registered voiceprint library is a voiceprint library composed of voiceprints that need to be compared. In specific implementation, the voiceprints of one or more specified persons can be extracted and registered to form a registered voiceprint library, or the voiceprints of all people in an environment (such as the wearer's workplace, company or home) can be extracted and registered to form a registered voiceprint library.

[0073] In one embodiment of the present application, if the headphone wearer needs to identify the voiceprints of one or more specified persons from the first voice data of the environment, then the above-mentioned registered voiceprint library can be registered based on the voiceprint feature information of the specified person, that is, registered based on the preset voiceprint feature information.

[0074] The above similarity is calculated by comparing the registered voiceprint feature information with the voiceprint feature information to be identified based on the voiceprint comparison algorithm. Among them, each registered voiceprint feature information in the registered voiceprint library corresponds to a calculated similarity, that is, a one-to-one correspondence. The implementation of the above voiceprint comparison algorithm can refer to the existing technology, such as using Euclidean distance, cosine similarity, etc., which will not be repeated in this embodiment.

[0075] S140, when there is at least one similarity greater than the first preset threshold, perform a preset action on the noise-cancelling headphones to transmit external sounds to the target user wearing the noise-cancelling headphones. That is, among the similarities corresponding to all registered voiceprint feature information calculated in the above steps, as long as there is a similarity greater than the first preset threshold, the noise reduction mode of the headphones is turned off or the transparency mode is turned on, so that the sound of other people talking outside can pass through the headphones and be transmitted to the ears of the headphone wearer. In this embodiment, the above preset action is to turn off the noise reduction mode or turn on the transparency mode. The above first preset threshold can be set as needed, for example, it can be 90%, and this application does not impose any restrictions on this.

[0076] In one embodiment, as long as one similarity is greater than a first preset threshold, the calculation of the similarity corresponding to the subsequent registered voiceprint feature information can be stopped, which can improve the voiceprint detection efficiency.

[0077] In another embodiment of the present application, another noise reduction processing method is disclosed. Figure 2 As shown, based on the above embodiment, the method further includes the following steps between step S120 and step S130:

[0078] S150, collecting second voice data corresponding to historical conversations of the target user wearing the noise reduction headset in the past first preset time period. And

[0079] S160, extracting all voiceprints from the second voice data, and registering N voiceprints with the highest frequency among all voiceprints to form a registered voiceprint library, where N is a positive integer.

[0080] Specifically, the target user wearing the noise cancelling headphones is the wearer of the noise cancelling headphones, that is, the user of the noise cancelling headphones. The historical conversation refers to a conversation that must involve the target user, which can be a conversation between the target user and another party, or a conversation between multiple parties including the target user.

[0081] The voiceprint feature information contained in the registered voiceprint database is the N people with the highest frequency in daily conversations with the target user, which is conducive to improving the efficiency and accuracy of voiceprint recognition detection, and further helps to improve the user's communication experience.

[0082] The above-mentioned first preset time period can be set as needed, for example, it can be one month before the current time, and this application does not impose any restrictions on this.

[0083] In another embodiment of the present application, another noise reduction processing method is disclosed. Figure 3 As shown, based on the above embodiment, the method further includes the following steps between step S120 and step S130:

[0084] S170, while collecting the registered voiceprint feature information, collect the location information, and associate the collected location information with the registered voiceprint feature information, and form a registered voiceprint library based on the collected registered voiceprint feature information. It should be noted that the location information refers to the collection location corresponding to the voiceprint feature information, that is, the location where the human voice occurs.

[0085] S180, grouping the registered voiceprint feature information based on the associated position information to form a first mapping relationship between the position information and the voiceprint group. Each group of registered voiceprint feature information after grouping corresponds to one position information, and each group of registered voiceprint feature information is one voiceprint group.

[0086] S190: Obtain current location information of the noise reduction headset.

[0087] S200: Based on the first mapping relationship, determine a target voiceprint group that matches the current position information.

[0088] Step S130 is:

[0089] The similarities between the registered voiceprint feature information in the target voiceprint group and the voiceprint feature information to be identified are compared one by one.

[0090] Specifically, for example, at home and at work, the people who often talk to the wearer of the noise-canceling headphones are different, so the registered voiceprint feature information collected can be grouped according to different locations. For example, the interlocutors at home and at work are in two different groups. In this way, when performing voiceprint recognition, the scope of voiceprints to be compared can be narrowed based on geographic location information, which is conducive to improving the efficiency and accuracy of voiceprint recognition detection, and thus helping to improve the user's communication experience.

[0091] In another embodiment of the present application, another noise reduction processing method is disclosed. Figure 4 As shown, based on the above embodiment, step S110 of the method is:

[0092] When it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state, the current position information of the noise reduction headset and the first voice data in the surrounding environment are collected.

[0093] Step S130 includes:

[0094] S131, constructing a training set based on historical conversation data of the target user wearing the noise reduction headset at different locations. Specifically, the implementation of this step can be implemented with reference to the above embodiment. The historical conversation data can be conversation data between the headset wearer and other people in the past first preset time period. The different locations can include homes and companies.

[0095] S132, based on the above training set, train the preset network model to obtain an initial network model. In the above initial network model, the parameter weights for the same interlocutor at different positions are different, and the above parameter weights are associated with the above positions. Specifically, the implementation of the preset network model can refer to the existing technology implementation, such as the implementation of the convolutional neural network model based on the existing technology. During the specific implementation, in this step, in a preset network model, each position corresponds to a set of model parameter weight combinations. It is also possible to have an initial network model in which each parameter weight is a fixed value for each position. That is, there can be multiple initial network models, and each position corresponds to an initial network model.

[0096] S133, based on the current location information, determining the parameter weights in the initial network model to form a target network model. That is, this step determines the model parameter weights corresponding to the current location information.

[0097] S134, based on the target network model, determine the similarity between the registered voiceprint feature information in the voiceprint library and the voiceprint feature information to be identified one by one. Specifically, the registered voiceprint feature information and the voiceprint feature information to be identified are used as inputs of the target network model, and the similarity between the two voiceprints is output.

[0098] like Figure 5 As shown, in another embodiment of the present application, the above step S131 includes:

[0099] S1311, obtaining historical conversation data of a target user wearing the noise cancelling headset at different locations within a historical time period as initial training data. The historical conversation data includes wearing state change data of the noise cancelling headset within a preset time period after the conversation starts.

[0100] S1312, filtering out historical conversation data corresponding to the switching of the noise cancelling headset from a wearing state to a non-wearing state within a preset time period after the start of the conversation from the above initial training data as target training data.

[0101] S1313: Construct a training set based on the target training data.

[0102] In this embodiment, the above-mentioned wearing state change data can be four types: switching from wearing state to non-wearing state, maintaining the wearing state unchanged, maintaining the non-wearing state unchanged, or switching from non-wearing state to wearing state. Generally speaking, when the headphone wearer, i.e. the target user, hears or sees someone greeting him, the conversation has already begun, and then the wearer will take off the headphone to participate in the conversation. Therefore, this embodiment uses the historical conversation data of the conversation after the wearer takes off the headphone. In this way, the extracted historical conversation data has higher training value, and the obtained model recognition and detection voiceprint is more accurate, which is conducive to improving the efficiency of headphone recognition voiceprint.

[0103] That is, the present application filters the training data according to the wearing status change data, and can filter out the historical conversation data of the wearer talking with others after each time taking off the headphones as training data, so that the training accuracy of the training set is higher, which is beneficial to improve the subsequent voiceprint detection accuracy and efficiency, and thus is beneficial to improving the user's communication experience.

[0104] In another embodiment, the above step S1312 can be: from the above initial training data, filter out the historical conversation data corresponding to the above noise reduction headset switching from a wearing state to a non-wearing state within a preset time period before the target user speaks in the conversation, as the target training data.

[0105] The above historical time period and preset duration can be set as needed. For example, the historical time period can be one month before the current time, and the preset duration can be 5 seconds; this application does not impose any restrictions on this.

[0106] In another embodiment of the present application, another noise reduction processing method is disclosed. Based on the above embodiment, the method further includes the steps of:

[0107] The registered voiceprint feature information corresponding to the similarity greater than the first preset threshold in step S140 is obtained as the target voiceprint; and the third voice data of the surrounding environment is continued to be collected.

[0108] When the target voiceprint and the voiceprint feature information of the target user are continuously not recognized from the third voice data within a second preset time period, the noise reduction mode of the noise reduction headset is turned on.

[0109] Specifically, when the voiceprint of the headphone wearer and the aforementioned interlocutor is not detected in the ambient audio data, the headphone noise reduction mode continues to be automatically turned on to perform noise reduction. In other embodiments, the headphone noise reduction mode may also be turned on after receiving a trigger signal, such as a trigger signal manually triggered by the target user.

[0110] The second preset time period can be set as needed, for example, it can be 30 seconds; this is not limited in the present application.

[0111] In another embodiment of the present application, another noise reduction processing method is disclosed. Based on the above embodiment, step S130 of the method includes:

[0112] Determine whether the power of the noise cancelling headset is lower than a third preset threshold value, if it is detected that the power of the noise cancelling headset is lower than the third preset threshold value, and the noise cancelling headset is connected to a terminal device, then compare the similarity of the registered voiceprint feature information in the registered voiceprint library with the voiceprint feature information to be identified one by one based on the terminal device, and execute steps S210 and S220.

[0113] S210: When there is at least one similarity greater than a first preset threshold, the terminal device sends a preset instruction to the noise reduction headset.

[0114] S220, the noise reduction headset performs a preset task based on the preset instruction.

[0115] If the power level of the noise cancelling headset is not lower than the third preset threshold, the similarity between the registered voiceprint feature information in the registered voiceprint library and the voiceprint feature information to be identified is compared one by one based on the noise cancelling headset, and then the above step S140 is executed.

[0116] Specifically, the terminal device can be a device such as a mobile phone or a tablet computer, and the noise-cancelling headset can be connected to the terminal device through Bluetooth. Then when the power of the noise-cancelling headset is low, such as less than 20%, a command is sent to the terminal device. After receiving the command, the terminal device collects and turns on the noise reduction mode of the headset, and compares and calculates the similarity. And when the voiceprint feature with a similarity greater than the first preset threshold is calculated, a preset command is sent to the headset to inform the headset to turn off the noise reduction mode or turn on the transparency mode.

[0117] This can save power consumption of the noise-canceling headphones and extend their battery life. It can detect the interlocutor's voiceprint without affecting battery life, which is beneficial to improving user experience.

[0118] It should be noted that all the above embodiments disclosed in this application can be freely combined, and the technical solutions obtained after the combination are also within the protection scope of this application.

[0119] like Figure 6 As shown, an embodiment of the present invention further discloses a noise reduction processing device 6, which includes:

[0120] The first voice data collection module 61 collects first voice data in the surrounding environment when it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state.

[0121] The first voiceprint extraction module 62 extracts the voiceprint feature information to be identified based on the first speech data.

[0122] The first voiceprint comparison module 63 compares the similarity between the registered voiceprint feature information in the registered voiceprint database and the voiceprint feature information to be identified one by one.

[0123] The execution module 64 executes a preset action on the noise reduction headset when at least one similarity is greater than a first preset threshold.

[0124] It can be understood that the noise reduction processing device of the present invention also includes other existing functional modules that support the operation of the noise reduction processing device. Figure 6 The noise reduction processing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0125] The noise reduction processing device in this embodiment is used to implement the above-mentioned noise reduction processing method. Therefore, the specific implementation steps of the noise reduction processing device can refer to the above-mentioned description of the noise reduction processing method, which will not be repeated here.

[0126] An embodiment of the present invention further discloses a noise reduction processing device, including a processor and a memory, wherein the memory stores an executable program of the processor; the processor is configured to execute the steps in the above-mentioned noise reduction processing method by executing the executable program. Figure 7 Schematic diagram of the structure of the noise reduction processing device disclosed in the present invention. Figure 7 The electronic device 600 according to this embodiment of the present invention is described. Figure 7 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0127] like Figure 7 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0128] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above noise reduction processing method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0129] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0130] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0131] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0132] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0133] An embodiment of the present invention further discloses a noise reduction headset, which includes the noise reduction processing device disclosed in the above embodiment.

[0134] The present invention also discloses a computer-readable storage medium for storing a program, which implements the steps in the above-mentioned noise reduction processing method when executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present invention described in the above-mentioned noise reduction processing method of this specification.

[0135] As shown above, when the program of the computer-readable storage medium of this embodiment is executed, it detects the voice data in the environment, and when the registered voiceprint feature information is recognized, it performs a preset action on the noise reduction headphones, such as turning off the noise reduction mode; this avoids the problem that the user cannot hear other people's calls when wearing headphones, which is not conducive to communication, and improves the wearer's communication experience with others.

[0136] Figure 8 Schematic diagram of the structure of the computer-readable storage medium of the present invention. Figure 8 As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0137] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0138] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0139] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0140] The noise reduction processing method, device, equipment, earphone and storage medium provided by the embodiments of the present invention detect voice data in the environment, and when the registered voiceprint feature information is identified, a preset action is performed on the noise reduction earphone, such as turning off the noise reduction mode; this avoids the problem that the user cannot hear other people's calls when wearing earphones, which is not conducive to communication, and improves the wearer's communication experience with others.

[0141] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the scope of protection of the present invention.

Claims

1. A noise reduction method, characterized in that: The following steps are involved: S110, when it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state, collecting first voice data in the surrounding environment; S120, extracting voiceprint feature information to be recognized based on the first voice data; Collecting second voice data corresponding to historical conversations of a target user wearing the noise reduction headset within a first preset time period in the past; Extract all voiceprints from the second voice data, and register N voiceprints with the highest frequency among all voiceprints to form a registered voiceprint library, where N is an integer; While collecting the registered voiceprint feature information, the location information is collected, and the collected location information is associated with the registered voiceprint feature information, and a registered voiceprint library is formed based on the collected registered voiceprint feature information; Grouping the registered voiceprint feature information based on the associated position information to form a first mapping relationship between the position information and the voiceprint group; Get the current location information of the noise-canceling headphones; Based on the first mapping relationship, determining a target voiceprint group matching the current location information; S130, comparing the similarity between the registered voiceprint feature information in the registered voiceprint database and the voiceprint feature information to be identified one by one, and comparing the similarity between the registered voiceprint feature information in the target voiceprint group and the voiceprint feature information to be identified one by one; Building a training set based on historical conversation data of a target user wearing the noise-cancelling headset at different locations; Based on the training set, training the preset network model to obtain an initial network model; In the initial network model, parameter weights for the same interlocutor at different positions are different, and the parameter weights are associated with the positions; Based on the current location information, determining parameter weights in the initial network model to form a target network model; Based on the target network model, determining the similarity between the registered voiceprint feature information in the voiceprint library and the voiceprint feature information to be identified one by one; The step of constructing a training set based on historical conversation data of a target user wearing the noise-cancelling headset at different locations includes: Acquire historical conversation data of a target user wearing the noise cancelling headset at different locations within a historical time period as initial training data; the historical conversation data includes wearing state change data of the noise cancelling headset within a preset time period after the start of the conversation; From the initial training data, historical conversation data corresponding to the switching of the noise cancelling headset from a wearing state to a non-wearing state within a preset time after the start of the conversation is selected as target training data; Based on the target training data, construct a training set; and S140: When there is at least one similarity greater than a first preset threshold, a preset action is performed on the noise-cancelling headset to transmit external sound to a target user wearing the noise-cancelling headset.

2. The noise reduction method according to claim 1, wherein: Before step S130, the method further includes: Register based on the specified voiceprint feature information to form a registered voiceprint library.

3. The noise reduction method according to claim 1, wherein: The method further comprises: Acquire the registered voiceprint feature information corresponding to the similarity greater than the first preset threshold as the target voiceprint; and continue to collect the third voice data of the surrounding environment; When the target voiceprint and the voiceprint feature information of the target user are continuously not recognized from the third voice data within a second preset time period, the noise reduction mode of the noise reduction headset is turned on.

4. The noise reduction method according to claim 1, wherein: Step S110 includes: Voice data whose audio intensity from the noise reduction headset in the surrounding environment is greater than a second preset threshold is collected as the first voice data.

5. The noise reduction method according to claim 1, wherein: Step S130 includes: When it is detected that the power of the noise-cancelling headset is lower than a third preset threshold, and the noise-cancelling headset is connected to a terminal device, the similarity between the registered voiceprint feature information in the registered voiceprint library and the voiceprint feature information to be identified is compared one by one based on the terminal device; Step S140 is: When there is at least one similarity greater than a first preset threshold, the terminal device sends a preset instruction to the noise reduction headset; The noise reduction earphones perform preset tasks based on the preset instructions.

6. The noise reduction method according to claim 1, wherein: The preset action is to turn off the noise reduction mode or turn on the transparency mode.

7. A noise reduction processing device, used to implement the noise reduction processing method according to claim 1, characterized in that: The device comprises: The first voice data collection module collects first voice data in the surrounding environment when it is detected that the noise reduction headset is in a wearing state and the noise reduction mode is in an on state; A first voiceprint extraction module extracts voiceprint feature information to be identified based on the first voice data; A first voiceprint comparison module compares the similarity between the registered voiceprint feature information in the registered voiceprint library and the voiceprint feature information to be identified one by one; The execution module executes a preset action on the noise reduction headset when at least one similarity is greater than a first preset threshold.

8. A noise reduction processing device, characterized in that: include: processor; a memory in which an executable program of the processor is stored; The processor is configured to execute the steps of the noise reduction method according to any one of claims 1 to 6 by executing the executable program.

9. A headset, characterized in that: The noise reduction processing device as claimed in claim 8 is included.

10. A computer-readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the noise reduction method according to any one of claims 1 to 6 are implemented.

Images