Bluetooth earphone noise reduction method and system, Bluetooth earphone and readable storage medium

Abstract

The application discloses a Bluetooth earphone noise reduction method and system, a Bluetooth earphone and a readable storage medium. According to the application, the Bluetooth data is acquired, and the Bluetooth data is matched with a driving Bluetooth name library, so that the current environment state of a user can be quickly determined, and the sensitivity of noise reduction is adjusted according to the specific condition of the current environment, thereby avoiding that the noise reduction operation cannot be effectively performed in an outdoor environment. Meanwhile, the preset semantic voice recognition model can quickly and effectively acquire the recognition result of the personalized voice, so that the switching of the working mode can be quickly completed according to the recognition result. According to the Bluetooth earphone noise reduction method of the application, whether a person communicates with the user by speech can be quickly and effectively determined through the recognition of the environment state and the recognition of the environment audio data, and then the noise reduction mode can be timely exited, so that the normal communication of the user is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of Bluetooth earphones, in particular to a Bluetooth earphone noise reduction method and system, a Bluetooth earphone and a readable storage medium. BACKGROUND

[0002] Bluetooth earphones have gained more and more users' favor for their portability, but with the development of economy and technology, users are no longer satisfied with the simple portability demand, but hope to have a better music playing experience. Under this demand, noise reduction earphones have appeared on the market. Noise reduction earphones have good airtightness, and after the earphones enter the noise reduction mode, they can effectively filter the noise caused by the ambient sound to better improve the user's music playing experience. However, in this way, the user cannot hear the normal communication sound with others, which brings great inconvenience to the user. SUMMARY

[0003] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application proposes a Bluetooth earphone noise reduction method, which solves the problem of difficulty in normal communication with others after wearing a Bluetooth earphone.

[0004] The present application also proposes a Bluetooth earphone noise reduction system, and a storage medium for storing the Bluetooth earphone noise reduction method and computer executable instructions.

[0005] The Bluetooth earphone noise reduction method according to the first aspect of the present application comprises:

[0006] Obtaining Bluetooth data, the Bluetooth intensity data including the Bluetooth name of the Bluetooth device scanned by the Bluetooth earphone;

[0007] Determining the current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and the preset driving Bluetooth name library;

[0008] Determining the noise reduction execution sensitivity threshold according to the current environment state, wherein the noise reduction execution sensitivity threshold corresponding to the indoor environment is greater than the noise reduction execution sensitivity threshold corresponding to the outdoor environment;

[0009] Obtaining environmental audio data, the environmental audio data including environmental audio intensity and environmental audio content;

[0010] Executing a noise reduction strategy according to the noise reduction execution sensitivity threshold and the environmental audio intensity;

[0011] The noise reduction strategy comprises:

[0012] input the environmental audio content into a preset semantic voice recognition model to obtain a recognition result; the semantic voice recognition model is used to recognize a personalized word set from the environmental audio content to obtain the recognition result, and the personalized word set includes a plurality of personalized voice word entries;

[0013] adjust a working mode of the Bluetooth earphone according to the recognition result, wherein the working mode includes a noise reduction mode and an environmental sound mode.

[0014] The Bluetooth earphone noise reduction method according to the embodiments of the present application has at least the following technical effects:

[0015] By acquiring Bluetooth data and matching the Bluetooth data with a driving Bluetooth name library, the current environment state of the user can be quickly determined, so that the noise reduction sensitivity can be adjusted according to the specific circumstances of the current environment, avoiding the failure to effectively perform the noise reduction operation in an outdoor environment. Meanwhile, the preset semantic voice recognition model can quickly and effectively obtain the recognition result of the personalized voice, so that the working mode can be quickly switched according to the recognition result. The Bluetooth earphone noise reduction method according to the embodiments of the present application can quickly and effectively determine whether there is someone communicating with the user in speech by recognizing the environment state and the environmental audio data, and then the noise reduction mode can be exited in time to ensure the normal communication of the user.

[0016] According to some embodiments of the present application, the driving Bluetooth name library includes preset automobile Bluetooth name data and preset shared bicycle Bluetooth name data.

[0017] The current environment state is determined according to the scanned Bluetooth name corresponding to the Bluetooth device and the preset driving Bluetooth name library, including:

[0018] When the Bluetooth name corresponding to the scanned Bluetooth device is matched from the preset automobile Bluetooth name data and the preset shared bicycle Bluetooth name data, the current environment state is determined as the outdoor environment.

[0019] When the Bluetooth name corresponding to the scanned Bluetooth device is not matched from the preset automobile Bluetooth name data and the preset shared bicycle Bluetooth name data, the current environment state is determined as the indoor environment.

[0020] According to some embodiments of the present application, the noise reduction execution sensitivity threshold is determined according to the current environment state, including:

[0021] When the current environment state is the outdoor environment, the noise reduction execution sensitivity threshold is determined as an outdoor sensitivity threshold.

[0022] When the current environment state is the indoor environment, the noise reduction execution sensitivity threshold is determined as an indoor sensitivity threshold, and the indoor sensitivity threshold is greater than the outdoor sensitivity threshold.

[0023] According to some embodiments of the present application, the noise reduction strategy is executed according to the noise reduction execution sensitivity threshold and the environment audio intensity, including:

[0024] When the environment audio intensity is greater than the noise reduction execution sensitivity threshold, the noise reduction strategy is executed.

[0025] According to some embodiments of the present application, the working mode of the Bluetooth earphone is adjusted according to the identification result, including:

[0026] When the identification result indicates that the personalized word set is identified from the environment audio content, the Bluetooth earphone is adjusted to the environment sound mode, and the environment audio content is played through the Bluetooth earphone;

[0027] When the identification result indicates that the personalized word set is not identified from the environment audio content, the Bluetooth earphone is adjusted to the noise reduction mode.

[0028] According to some embodiments of the present application, the noise reduction strategy further includes:

[0029] When the Bluetooth earphone enters the environment sound mode, first feedback voice content of a user of the Bluetooth earphone within a first preset time threshold is collected;

[0030] The extension operation on the environment sound mode is executed according to the first voice feedback content.

[0031] According to some embodiments of the present application, the extension operation on the environment sound mode is executed according to the first voice feedback content, including:

[0032] When the first feedback voice content indicates that the user does not make voice reply, the Bluetooth earphone is switched to the noise reduction mode;

[0033] When the first feedback voice content indicates that the user makes voice reply, the environment sound mode is extended by a second preset time threshold.

[0034] According to some embodiments of the present application, the extension operation on the environment sound mode is executed according to the first voice feedback content, further including:

[0035] Second feedback voice content of a user of the Bluetooth earphone within the second preset time threshold is collected;

[0036] switching the Bluetooth earphone to a noise reduction mode when the second feedback voice content represents that the user does not make a voice reply;

[0037] extending the ambient sound mode by the second preset time threshold when the second feedback voice content represents that the user makes a voice reply.

[0038] According to some embodiments of the present application, the Bluetooth earphone noise reduction method further comprises:

[0039] obtaining a user-added personalized voice term, and uploading the added personalized voice term to a cloud end, so that the cloud end updates the semantic voice recognition model according to the added personalized voice term;

[0040] downloading the updated semantic voice recognition model.

[0041] According to some embodiments of the present application, the Bluetooth data further comprises Bluetooth strength information corresponding to the scanned Bluetooth device;

[0042] The Bluetooth earphone noise reduction method further comprises the following steps:

[0043] adjusting the working mode of the Bluetooth earphone to an ambient sound mode when the Bluetooth name of the Bluetooth device matches the preset car Bluetooth name data in the car Bluetooth name library, and the Bluetooth strength information of the Bluetooth device exceeds a preset Bluetooth strength threshold value.

[0044] The Bluetooth earphone noise reduction system according to the second aspect of the present application comprises:

[0045] a Bluetooth data acquisition module for acquiring Bluetooth data, wherein the Bluetooth strength data comprises a Bluetooth name of a Bluetooth device scanned by a Bluetooth earphone;

[0046] an environment determination module for determining a current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and a preset car Bluetooth name library;

[0047] a sensitivity determination module for determining a noise reduction execution sensitivity threshold according to the current environment state, wherein the noise reduction execution sensitivity threshold corresponding to the current environment state being an indoor environment is greater than the noise reduction execution sensitivity threshold corresponding to the current environment state being an outdoor environment;

[0048] an ambient sound acquisition module for acquiring ambient audio data, wherein the ambient audio data comprises ambient audio strength and ambient audio content;

[0049] a mode adjustment module for executing a noise reduction strategy according to the noise reduction execution sensitivity threshold and the ambient audio strength;

[0050] wherein the noise reduction strategy comprises:

[0051] inputting the environmental audio content into a preset semantic speech recognition model to obtain a recognition result; the semantic speech recognition model is used to recognize a personalized word set from the environmental audio content to obtain the recognition result, and the personalized word set comprises a plurality of personalized speech word entries;

[0052] adjusting a working mode of the Bluetooth earphone according to the recognition result, wherein the working mode comprises a noise reduction mode and an environmental sound mode.

[0053] The Bluetooth earphone noise reduction system according to the embodiment of the present application has at least the following technical effects:

[0054] By acquiring Bluetooth data and matching the Bluetooth data with a driving Bluetooth name library, the current environment state of the user can be quickly determined, so that the sensitivity of noise reduction can be adjusted according to the specific circumstances of the current environment, thereby avoiding ineffective noise reduction operation in an outdoor environment. Meanwhile, the preset semantic speech recognition model can quickly and effectively obtain the recognition result of personalized speech, so that the working mode can be quickly switched according to the recognition result. The Bluetooth earphone noise reduction method according to the embodiment of the present application can quickly and effectively determine whether there is someone communicating with the user through speech by recognizing the environmental state and the environmental audio data, and then the noise reduction mode can be exited in time to ensure normal communication of the user.

[0055] The Bluetooth earphone according to the third aspect of the present application comprises a memory, a communication module, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the Bluetooth earphone noise reduction method as described above when executing the computer program. Since the Bluetooth device adopts all the technical solutions of the Bluetooth earphone noise reduction method according to the above embodiments, it at least has all the beneficial effects brought by the technical solutions of the above embodiments.

[0056] The computer readable storage medium according to the fourth aspect of the present application stores computer executable instructions for causing a computer to execute the Bluetooth earphone noise reduction method as described above. Since the computer readable storage medium adopts all the technical solutions of the Bluetooth earphone noise reduction method according to the above embodiments, it at least has all the beneficial effects brought by the technical solutions of the above embodiments.

[0057] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be learned through practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0058] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description, taken in conjunction with the following drawings in which:

[0059] Figure 1 is a schematic diagram of a system architecture provided by an embodiment of the present application;

[0060] Figure 2 is a flowchart of a noise reduction method for a Bluetooth headset provided by an embodiment of the present application;

[0061] Figure 3 is a flowchart of a noise reduction strategy provided by an embodiment of the present application;

[0062] Figure 4 is a flowchart of a noise reduction strategy provided by another embodiment of the present application;

[0063] Figure 5 is a flowchart of a noise reduction method for a Bluetooth headset provided by another embodiment of the present application. DETAILED DESCRIPTION

[0064] Embodiments of the present application are described in detail below with reference to the attached drawing figures, wherein the same or like component have the same or similar designations. The embodiments described below are presented by way of example only and are not intended to limit the present application as defined by the appended claims and their equivalents.

[0065] In the description of the present application, if there is a description to first, second, etc., it is only for the purpose of distinguishing technical features and should not be understood as indicating or implying that a relative importance or a specific order between the technical features indicated or implied.

[0066] In the description of the present application, it should be understood that, in relation to the orientation description, for example, the orientation or position relationship indicated by up, down, etc. is based on the orientation or position relationship shown in the drawings, and is only for the purpose of facilitating the description of the present application and simplifying the description, and should not be understood as indicating or implying that the device or element indicated must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present application.

[0067] In the description of the present application, it should be noted that, unless otherwise explicitly limited, the words such as setting, installing, connecting, etc. should be broadly understood, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0068] The technical solutions of the present application will be described below in conjunction with the drawings. Obviously, the following described embodiments are only part of the embodiments of the present application, not all embodiments.

[0069] For better description of the Bluetooth earphone noise reduction method, system, Bluetooth earphone and readable storage medium of the embodiment of the application, a system architecture is proposed here, referring to Figure 1 The system architecture includes a Bluetooth earphone and a cloud. The Bluetooth earphone can upload personalized voice terms set by a user to the cloud. The cloud is used to complete training of a semantic voice recognition model based on a machine learning method to obtain a semantic voice recognition model that can recognize personalized voice terms. At the same time, the Bluetooth earphone is provided with an ambient sound collection microphone and a user audio agent microphone that can respectively complete extraction of external ambient audio data and the user's own sound, facilitating subsequent extraction and judgment of the ambient audio data and the user's own sound. At the same time, the Bluetooth earphone can scan Bluetooth devices in the surrounding environment to obtain Bluetooth name and Bluetooth signal strength information of the Bluetooth devices.

[0070] It should be noted that the above-mentioned system architecture is only one case of implementing the Bluetooth earphone noise reduction method, system, Bluetooth earphone and readable storage medium of the embodiment of the application, and is not a limitation on the protection scope of the application.

[0071] Based on the above-mentioned architecture, various embodiments of the application are proposed. The embodiments of the application are further described below with reference to the accompanying drawings.

[0072] Referring to Figure 2 , the Figure 2 is a flowchart of a Bluetooth earphone noise reduction method provided by an embodiment of the application. The Bluetooth earphone noise reduction method includes but is not limited to steps S100 to S500:

[0073] S100, acquiring Bluetooth data, the Bluetooth strength data including a Bluetooth name of a Bluetooth device scanned by the Bluetooth earphone;

[0074] S200, determining a current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and a preset driving Bluetooth name library;

[0075] S300, determining a noise reduction execution sensitivity threshold according to the current environment state, wherein the noise reduction execution sensitivity threshold corresponding to the current environment state being an indoor environment is greater than the noise reduction execution sensitivity threshold corresponding to the current environment state being an outdoor environment;

[0076] S400, acquiring ambient audio data, the ambient audio data including ambient audio strength and ambient audio content;

[0077] S500, executing a noise reduction strategy according to the noise reduction execution sensitivity threshold and the ambient audio strength;

[0078] Referring to Figure 3 , the noise reduction strategy includes steps S510 to S520:

[0079] S510, input the environmental audio content into a preset semantic speech recognition model to obtain a recognition result; the semantic speech recognition model is used to recognize a personalized word set from the environmental audio content to obtain the recognition result, and the personalized word set includes a plurality of personalized speech word entries;

[0080] S520, adjusting a working mode of the Bluetooth earphone according to the recognition result, the working mode including a noise reduction mode and an environmental sound mode.

[0081] It should be noted that the Bluetooth data can be obtained by directly scanning the surrounding Bluetooth devices of the Bluetooth earphone, so as to determine the number of Bluetooth devices existing around the user and the Bluetooth name corresponding to each Bluetooth device.

[0082] The driving Bluetooth name library mainly includes the Bluetooth names of the road traffic participants, such as the Bluetooth devices in the car and the Bluetooth devices in the shared bicycle. It can be understood that the products of the car and the shared bicycle put on the market can be known in advance, and in most cases, there is no case of artificially modifying the Bluetooth name. Therefore, when the Bluetooth earphone scans these Bluetooth devices, it can be basically inferred that the user is currently in an outdoor environment, and the more the number of scanned Bluetooth devices, the more complex the current environment. On the contrary, when no Bluetooth device of the above traffic participants is scanned, it can be basically inferred that the current environment is indoors. In the embodiment of the application, a driving Bluetooth name library is constructed, and the driving Bluetooth name library stores preset car Bluetooth name data and preset shared bicycle Bluetooth name data. The preset car Bluetooth name data includes the Bluetooth names corresponding to a plurality of models of the common car brands on the market, and the preset shared bicycle Bluetooth name data includes the Bluetooth names of the shared bicycles on the market. When new products of the car or the bicycle appear on the market, the data in the driving Bluetooth name library will be updated. It can be understood that most products of the same series will use the same prefix as the beginning of the Bluetooth name. Therefore, when performing the Bluetooth device matching operation, only the prefix part of the Bluetooth name needs to be matched and recognized.

[0083] It can be understood that the environmental sound is more complex in the outdoor environment. Therefore, when someone shouts at the user in the outdoor environment, it is more likely to be suppressed by the environmental sound. In addition, the outdoor environment is more open, and the distance between the user and other people may be far. Therefore, in the outdoor environment, the noise reduction execution sensitivity threshold needs to be set lower to effectively avoid omission. Correspondingly, in the indoor environment, the environment is relatively quiet, and the distance between the user and other people is also closer. Therefore, in order to avoid repeated judgment, the noise reduction execution sensitivity threshold can be set higher.

[0084] After the sensitivity is determined, the environmental audio data can be collected by the environmental sound collection microphone, and the environmental audio intensity in the environmental audio data is compared with the noise reduction execution sensitivity threshold, and when the environmental audio intensity is higher than the noise reduction execution sensitivity threshold, the noise reduction strategy is entered.

[0085] When the noise reduction strategy is executed, the semantic speech recognition model is first used to identify the environmental audio content in the environmental audio data to determine whether the personalized word set is contained in the environmental audio content, and when the word in the personalized word set is identified, the Bluetooth earphone mode is switched to the environmental sound mode. It can be understood that the personalized word set includes a plurality of personalized speech terms, and only one of them needs to be identified to perform the mode switching operation. It can be understood that the personalized word set can include common greeting sentences (such as hello, hi, hello, handsome, etc.), and also include self-defined sentences (such as user nickname, user formal name, etc.).

[0086] It should be noted that if the current condition does not trigger the entry of the noise reduction strategy, the Bluetooth earphone can be directly kept in the noise reduction mode.

[0087] The Bluetooth earphone noise reduction method of the embodiment of the application can quickly determine the current environment state of the user by obtaining Bluetooth data and matching the Bluetooth data with the driving Bluetooth name library, so as to adjust the noise reduction execution sensitivity according to the specific circumstances of the current environment, thereby avoiding the failure to effectively perform the noise reduction operation in the outdoor environment. At the same time, the preset semantic speech recognition model can quickly and effectively obtain the recognition result of the personalized speech, so that the working mode can be quickly switched according to the recognition result. The Bluetooth earphone noise reduction method of the embodiment of the application can quickly and effectively determine whether the user is in verbal communication with the user by identifying the environmental state and the environmental audio data, and then the noise reduction mode can be exited in time to ensure the normal communication of the user.

[0088] In some embodiments, the driving Bluetooth name library includes preset car Bluetooth name data and preset shared bicycle Bluetooth name data; step S200 includes the following steps:

[0089] When the Bluetooth name corresponding to the scanned Bluetooth device is matched from the preset car Bluetooth name data and the preset shared bicycle Bluetooth name data, the current environment state is determined as an outdoor environment;

[0090] When the Bluetooth name corresponding to the scanned Bluetooth device is not matched from the preset car Bluetooth name data and the preset shared bicycle Bluetooth name data, the current environment state is determined as an indoor environment.

[0091] The automobile and shared bicycle are mainly distributed outdoors, so the name of the scanned Bluetooth device can be directly used to effectively determine whether the user is currently indoors or outdoors. Specifically, an embodiment of the present application directly constructs a driving Bluetooth name library, and imports preset automobile Bluetooth name data and preset shared bicycle Bluetooth name data in the driving Bluetooth name library. When a Bluetooth device is scanned, the name of the scanned Bluetooth device can be used to scan and match in the driving Bluetooth name library. After a word that meets the name consistency requirement is matched, it is determined that there is an automobile or shared bicycle around the user, and it is further determined that the current environment is an outdoor environment.

[0092] In some embodiments, step S300 comprises the following steps:

[0093] When the current environment state is an outdoor environment, the noise reduction execution sensitivity threshold is determined as an outdoor sensitivity threshold;

[0094] When the current environment state is an indoor environment, the noise reduction execution sensitivity threshold is determined as an indoor sensitivity threshold, and the indoor sensitivity threshold is greater than the outdoor sensitivity threshold.

[0095] The outdoor environment is more complex than the indoor environment, so when the environmental sound is judged outdoors, the noise reduction execution sensitivity threshold needs to be set lower to ensure that the person greeting the user can enter the environmental sound mode in time without the shouting sound being too small.

[0096] In some embodiments, step S500 comprises the following steps:

[0097] When the environmental sound intensity is greater than the noise reduction execution sensitivity threshold, the noise reduction strategy is executed.

[0098] The noise reduction strategy is mainly to switch the Bluetooth earphone to the environmental sound mode when someone greets the user, so when the external volume is large, the noise reduction strategy is executed to determine whether someone is communicating with the user. It should be noted that when the environmental sound intensity is lower than the noise reduction execution sensitivity threshold, no operation is required.

[0099] In some embodiments, step S520 comprises the following steps:

[0100] When the recognition result represents that the personalized word set is recognized from the environmental sound content, the Bluetooth earphone is adjusted to the environmental sound mode, and the environmental sound content is played through the Bluetooth earphone;

[0101] When the recognition result represents that the personalized word set is not recognized from the environmental sound content, the Bluetooth earphone is adjusted to the noise reduction mode.

[0102] After the environmental audio data is collected, the environmental audio content corresponding to the environmental audio data is input into the voice semantic recognition model, and then it is determined by the voice semantic recognition model whether the current environmental audio content contains the personalized voice term in the personalized term set. Only when the personalized voice term is recognized, the Bluetooth earphone will be adjusted to the environmental sound mode. It can be understood that during the process of recognizing the personalized voice term, the person shouting the user may have stopped shouting. Therefore, if the environmental sound mode is directly entered at this time, it will cause the user to miss the content of the environmental audio data. Therefore, in order to ensure that the effective content of the user's communication with others is not missing, the environmental audio data will be played once through the speaker of the Bluetooth earphone when it is determined to enter the environmental sound mode.

[0103] Reference Figure 4 In some embodiments, the noise reduction strategy further includes steps S530-S540:

[0104] S530, when the Bluetooth earphone enters the environmental sound mode, collecting the first feedback voice content of the user of the Bluetooth earphone within a first preset time threshold;

[0105] S540, performing a prolonging operation on the environmental sound mode according to the first voice feedback content.

[0106] After entering the environmental sound mode, it is further necessary to determine whether the user has made an effective response, so as to avoid the user from being in the environmental sound mode continuously without making a response. At the same time, when the user makes an effective response, a prolonging operation can be performed to ensure normal communication between the user and others.

[0107] In some embodiments, performing a prolonging operation on the environmental sound mode according to the first voice feedback content includes:

[0108] When the first feedback voice content represents that the user does not make a voice response, the Bluetooth earphone is switched to the noise reduction mode;

[0109] When the first feedback voice content represents that the user makes a voice response, the environmental sound mode is prolonged by a second preset time threshold.

[0110] When the user makes an effective response, it can be determined that the user currently needs to communicate with others continuously, and the duration of the environmental sound mode should be further prolonged. Otherwise, when the user does not make an effective response, it means that the user has no communication desire or that the person who sends the personalized voice term has no communication demand relationship with the user.

[0111] In some embodiments, performing a prolonging operation on the environmental sound mode according to the first voice feedback content further includes:

[0112] collecting second feedback voice content of the user of the Bluetooth earphone within a second preset time threshold;

[0113] switching the Bluetooth earphone to the noise reduction mode when the second feedback voice content represents that the user does not make a voice reply;

[0114] extending the ambient sound mode by the second preset time threshold when the second feedback voice content represents that the user makes a voice reply.

[0115] It can be understood that during the extension of the ambient mode, the reply condition of the user is continuously identified, so that the ambient sound mode can be continuously maintained during the communication of the user, and the exit of the ambient sound mode can be delayed when the user does not make a reply, thereby improving the experience of the user.

[0116] It should be noted that in some embodiments, a mode manual switching button is arranged on the Bluetooth earphone, so that when the user feels that the automatically identified mode does not meet the use demand, manual switching can be performed, thereby further improving the use experience of the user.

[0117] In some embodiments, the Bluetooth earphone noise reduction method further comprises:

[0118] obtaining a newly added personalized voice term of the user, and uploading the newly added personalized voice term to the cloud end, so that the cloud end updates the semantic voice recognition model according to the newly added personalized voice term;

[0119] downloading the updated semantic voice recognition model.

[0120] In the use process, a pair of Bluetooth earphones may accompany the user for a long time, and the user may need to update the personalized voice term. At this time, the user can add personalized voice terms to complete the personalized term set and update the semantic voice recognition model.

[0121] It should be noted that the update of the semantic voice recognition model is completed in the cloud end, and is downloaded and updated by the user side after the update is completed. It can be understood that the update of the personalized voice term can be input by the user through the application program on the mobile phone and uploaded to the cloud end after the Bluetooth earphone is connected to the mobile phone. The update of the personalized term can also be uploaded to the cloud end after the user inputs the voice through the Bluetooth earphone after the Bluetooth earphone is connected to the mobile phone.

[0122] In some embodiments, the Bluetooth data further comprises Bluetooth strength information corresponding to the scanned Bluetooth device;

[0123] Reference Figure 5 , the Bluetooth earphone noise reduction method further comprises the following steps:

[0124] S600, when the Bluetooth name of the Bluetooth device matches the preset car Bluetooth name data in the driving Bluetooth name library, and the Bluetooth strength information of the Bluetooth device exceeds the preset Bluetooth strength threshold value, the working mode of the Bluetooth earphone is adjusted to the ambient sound mode.

[0125] The outdoor environment, especially on the road with heavy traffic, has a high risk. In order to avoid the user from being hit by a car and being injured, when the name of the scanned Bluetooth device matches the preset car Bluetooth name data in the driving Bluetooth name library, the strength relationship with the car Bluetooth device is further judged. If the strength exceeds the Bluetooth strength threshold value, it means that the car is close, and the Bluetooth earphone should be controlled to remain in the ambient sound mode until the Bluetooth strength information is weakened.

[0126] In order to better describe the noise reduction method of the Bluetooth earphone of the embodiment of the application, a specific embodiment is further described.

[0127] The voice semantic recognition model is trained in advance by using a preselected personalized word set to obtain a voice semantic recognition model that can recognize a plurality of personalized voice terms in the preselected personalized word set. If it is necessary to update the voice semantic recognition model, the user can upload new personalized voice terms to the cloud, and the cloud re-trains the voice semantic recognition model. The trained voice semantic recognition model is reloaded into the Bluetooth earphone.

[0128] A driving Bluetooth name library is constructed in advance, which includes preset car Bluetooth name data and preset shared bicycle Bluetooth name data.

[0129] The Bluetooth devices around the user are scanned, and the Bluetooth name and Bluetooth strength information corresponding to each Bluetooth device are obtained.

[0130] It is determined whether the Bluetooth name matches the result in the driving Bluetooth name library.

[0131] If the object that meets the requirements is matched, it means that the current environment is outdoor, and the noise reduction execution sensitivity threshold is set to the outdoor sensitivity threshold. Otherwise, it means that the current environment is indoor, and the noise reduction execution sensitivity threshold is set to the indoor sensitivity threshold.

[0132] The current ambient audio data is obtained, which includes ambient audio strength and ambient audio content.

[0133] When the ambient audio strength exceeds the noise reduction execution sensitivity threshold, the ambient audio content is input into the voice semantic recognition model, and the voice semantic recognition model judges whether the personalized voice terms in the personalized word set are included in the ambient audio content.

[0134] If the identification result is that the personalized voice keyword is identified, the working mode of the Bluetooth earphone is switched to the ambient sound mode, and it is further determined whether the user replies within a first preset time threshold;

[0135] If the user replies within the first preset time threshold, the ambient sound mode time is delayed to a second preset time threshold, and it is continuously determined whether the user replies within the delayed time, and if not, the noise reduction mode is switched back, and if yes, the second preset time threshold is continuously extended.

[0136] In addition, if the Bluetooth name matches the result in the preset car Bluetooth name data, it is simultaneously judged whether the Bluetooth signal strength information of the Bluetooth device exceeds the preset Bluetooth strength threshold value, and if the Bluetooth signal strength information of the Bluetooth device exceeds the Bluetooth strength threshold value, the ambient sound mode is directly entered until the Bluetooth signal strength information is lower than the Bluetooth strength threshold value, and then the current environment state is returned.

[0137] The Bluetooth earphone noise reduction method of the embodiment can quickly determine the current environment state of the user by obtaining Bluetooth data and matching the Bluetooth data with the driving Bluetooth name library, so as to adjust the noise reduction execution sensitivity according to the specific circumstances of the current environment, thereby avoiding that the noise reduction operation cannot be effectively performed in an outdoor environment. At the same time, the preset semantic voice recognition model can quickly and effectively obtain the identification result of the personalized voice, so that the working mode can be quickly switched according to the identification result. The Bluetooth earphone noise reduction method of the embodiment can quickly and effectively determine whether the user is in speech communication with the user by identifying the environment state and the environment audio data, and then the noise reduction mode can be exited in time to ensure normal communication of the user.

[0138] In addition, the embodiment of the application also provides a Bluetooth earphone noise reduction system, which comprises a Bluetooth data acquisition module, an environment determination module, a sensitivity determination module, an ambient sound acquisition module and a mode adjustment module.

[0139] The Bluetooth data acquisition module is used to acquire Bluetooth data, and the Bluetooth strength data comprises a Bluetooth name of a Bluetooth device scanned by the Bluetooth earphone.

[0140] The environment determination module is used to determine a current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and a preset driving Bluetooth name library.

[0141] The sensitivity determination module is used to determine a noise reduction execution sensitivity threshold according to the current environment state, wherein the noise reduction execution sensitivity threshold corresponding to the indoor environment state is greater than the noise reduction execution sensitivity threshold corresponding to the outdoor environment state.

[0142] The environmental sound acquisition module is configured to acquire environmental audio data, the environmental audio data including environmental audio intensity and environmental audio content;

[0143] The mode adjustment module is configured to execute the noise reduction strategy according to the noise reduction execution sensitivity threshold and the environmental audio intensity;

[0144] The noise reduction strategy includes:

[0145] The environmental audio content is input into a preset semantic speech recognition model to obtain a recognition result; the semantic speech recognition model is configured to recognize a personalized word set from the environmental audio content to obtain the recognition result, the personalized word set including a plurality of personalized speech word entries;

[0146] The working mode of the Bluetooth earphone is adjusted according to the recognition result, the working mode including a noise reduction mode and an environmental sound mode.

[0147] The Bluetooth data can be scanned by the Bluetooth earphone from surrounding Bluetooth devices, so that the number of Bluetooth devices existing around the user and the Bluetooth name corresponding to each Bluetooth device can be determined.

[0148] The driving Bluetooth name library mainly includes the Bluetooth names of traffic participants on the road, for example, the Bluetooth devices in the car and the Bluetooth devices in the shared bicycle. It can be understood that the products of the car and the shared bicycle on the market can be known in advance, and in most cases, the Bluetooth name is not modified by human. Therefore, when the Bluetooth earphone scans these Bluetooth devices, it can be basically determined that the user is currently in an outdoor environment, and the more the number of scanned Bluetooth devices, the more complex the current environment. Conversely, when no Bluetooth device of the above traffic participant is scanned, it can be basically determined that the current environment is an indoor environment. In the embodiment of the application, a driving Bluetooth name library is constructed, and the driving Bluetooth name library stores preset car Bluetooth name data and preset shared bicycle Bluetooth name data. The preset car Bluetooth name data includes the Bluetooth names corresponding to a plurality of models of common car brands on the market, and the preset shared bicycle Bluetooth name data includes the Bluetooth names of shared bicycles on the market. When new products of cars or bicycles appear on the market, the data in the driving Bluetooth name library will be updated. It can be understood that most products of the same series will use the same prefix as the beginning of the Bluetooth name. Therefore, when performing the Bluetooth device matching operation, only the prefix part of the Bluetooth name needs to be matched and recognized.

[0149] It can be understood that the environmental sound is more complex in the outdoor environment, so when someone shouts the user in the outdoor environment, it is more likely to be suppressed by the environmental sound, and the outdoor is more open, and the distance between the user and other people can be farther, so in the outdoor environment, the noise reduction execution sensitivity threshold needs to be set lower, so as to effectively avoid missing. Correspondingly, in the indoor environment, the environment is relatively quiet, and the distance between the user and other people will also be closer, so in order to avoid repeated judgment, the noise reduction execution sensitivity threshold can be set higher.

[0150] After determining the sensitivity, the environmental audio data can be collected by the environmental sound collecting microphone, and the environmental audio intensity in the environmental audio data is compared with the noise reduction execution sensitivity threshold, and when the environmental audio intensity is higher than the noise reduction execution sensitivity threshold, the noise reduction strategy is entered.

[0151] When the noise reduction strategy is executed, the semantic speech recognition model is first used to recognize the environmental audio content in the environmental audio data to determine whether the personalized word set is contained in the environmental audio content, and when the word in the personalized word set is recognized, the Bluetooth earphone mode is switched to the environmental sound mode. It can be understood that the personalized word set includes a plurality of personalized speech word entries, and only one of them needs to be recognized to perform the mode switching operation. It can be understood that the personalized word set can include common greeting sentences (such as hello, hi, hello, handsome, etc.), and also include self-defined word sentences (such as user nickname, user formal name, etc.).

[0152] It should be noted that if the current condition does not trigger the entry of the noise reduction strategy, the Bluetooth earphone can be directly kept in the noise reduction mode.

[0153] The Bluetooth earphone noise reduction system of the embodiment of the application can quickly determine the current environment state of the user by acquiring Bluetooth data and matching the Bluetooth data with the driving Bluetooth name library, so as to adjust the noise reduction execution sensitivity according to the specific circumstances of the current environment, and avoid that the noise reduction operation cannot be effectively performed in the outdoor environment. At the same time, the preset semantic speech recognition model can quickly and effectively obtain the recognition result of the personalized speech, so that the working mode can be quickly switched according to the recognition result. The Bluetooth earphone noise reduction system of the embodiment of the application can quickly and effectively determine whether someone is in verbal communication with the user through the recognition of the environmental state and the recognition of the environmental audio data, and then the noise reduction mode can be exited in time to ensure the normal communication of the user.

[0154] In addition, one embodiment of the present application also provides a Bluetooth headset, which comprises a memory, a communication module, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the Bluetooth headset noise reduction method as described above when executing the computer program.

[0155] In addition, one embodiment of the present application also provides a computer readable storage medium, which stores computer executable instructions for executing the Bluetooth headset noise reduction method as described above, for example, executed by a processor in the above-mentioned Bluetooth headset, so as to make the processor execute the Bluetooth headset noise reduction method in the above-mentioned embodiments, for example, execute the method described above.

[0156] The non-transitory software program and instructions required for implementing the Bluetooth headset noise reduction method in the above-mentioned embodiments are stored in the memory, and when executed by the processor, the Bluetooth headset noise reduction method in the above-mentioned embodiments, for example, the method described above, is executed.

[0157] Those skilled in the art can understand that all or some steps in the above-mentioned method and system can be implemented as software, firmware, hardware and appropriate combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on a computer readable medium, which can include computer storage media or non-transitory media and communication media or transitory media. As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory unit technology, CD-ROM, digital versatile disk DVD or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, as known to those skilled in the art, communication media generally includes computer readable instructions, data structures, program modules or other data in modulated data signals such as carriers or other transmission mechanisms, and can include any information delivery medium.

[0158] The embodiments of the present application are described in detail above in combination with the drawings, but the present application is not limited to the above-mentioned embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the purpose of the present application.

Claims

1. A Bluetooth earphone noise reduction method, characterized in that, The method comprises: acquiring Bluetooth data, wherein the Bluetooth data comprises a Bluetooth name of a Bluetooth device scanned by a Bluetooth earphone; determining a current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and a preset Bluetooth name library for driving; determining a noise reduction execution sensitivity threshold according to the current environment state, wherein the noise reduction execution sensitivity threshold corresponding to the indoor environment is greater than the noise reduction execution sensitivity threshold corresponding to the outdoor environment; acquiring environment audio data, wherein the environment audio data comprises environment audio intensity and environment audio content; executing a noise reduction strategy according to the noise reduction execution sensitivity threshold and the environment audio intensity; the noise reduction strategy comprises: inputting the environment audio content into a preset semantic speech recognition model to obtain a recognition result; the semantic speech recognition model is used to recognize a personalized word set from the environment audio content to obtain the recognition result, and the personalized word set comprises a plurality of personalized speech word entries; when the recognition result indicates that the personalized word set is recognized from the environment audio content, the Bluetooth earphone is adjusted to an ambient sound mode, and the environment audio content is played through the Bluetooth earphone; adjusting a working mode of the Bluetooth earphone according to the recognition result, wherein the working mode comprises a noise reduction mode and an ambient sound mode; when the environment audio intensity is greater than the noise reduction execution sensitivity threshold, the noise reduction strategy is executed. the Bluetooth name library for driving comprises preset automobile Bluetooth name data and preset shared bicycle Bluetooth name data; 2. The Bluetooth headset noise reduction method of claim 1, wherein, determining the current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and the preset Bluetooth name library for driving comprises: when the Bluetooth name corresponding to the scanned Bluetooth device is matched from the preset automobile Bluetooth name data and the preset shared bicycle Bluetooth name data, the current environment state is determined to be the outdoor environment; when the Bluetooth name corresponding to the scanned Bluetooth device is not matched from the preset automobile Bluetooth name data and the preset shared bicycle Bluetooth name data, the current environment state is determined to be the indoor environment. adjusting the working mode of the Bluetooth earphone according to the recognition result comprises:

3. The Bluetooth headset noise reduction method of claim 1, wherein, when the recognition result indicates that the personalized word set is not recognized from the environment audio content, the Bluetooth earphone is adjusted to the noise reduction mode. the noise reduction strategy further comprises:

4. The Bluetooth headset noise reduction method of claim 1, wherein, when the Bluetooth earphone enters the ambient sound mode, collecting first feedback speech content of a user of the Bluetooth earphone within a first preset time threshold; performing an extension operation on the ambient sound mode according to the first feedback speech content. performing the extension operation on the ambient sound mode according to the first feedback speech content comprises:

5. The Bluetooth headset noise reduction method of claim 4, wherein, when the first feedback speech content indicates that the user does not make a speech reply, switching the Bluetooth earphone to the noise reduction mode; when the first feedback speech content indicates that the user makes a speech reply, extending the ambient sound mode by a second preset time threshold. the Bluetooth earphone noise reduction method further comprises:

6. The Bluetooth headset noise reduction method of claim 1, wherein, ​ Obtaining a user-added personalized voice term, and uploading the added personalized voice term to the cloud to enable the cloud to update the semantic voice recognition model according to the added personalized voice term; Downloading the updated semantic voice recognition model.

7. The Bluetooth headset noise reduction method of claim 1, wherein, The Bluetooth data further includes Bluetooth strength information corresponding to the scanned Bluetooth device; The Bluetooth earphone noise reduction method further includes the following steps: When the Bluetooth name of the Bluetooth device matches the preset car Bluetooth name data in the car Bluetooth name library, and the Bluetooth strength information of the Bluetooth device exceeds the preset Bluetooth strength threshold, the working mode of the Bluetooth earphone is adjusted to the ambient sound mode.

8. A Bluetooth headset noise reduction system characterized by, Comprise: A Bluetooth data acquisition module for acquiring Bluetooth data, the Bluetooth data including the Bluetooth name of the Bluetooth device scanned by the Bluetooth earphone; An environment determination module for determining the current environment state according to the Bluetooth name corresponding to the scanned Bluetooth device and the preset car Bluetooth name library; A sensitivity determination module for determining a noise reduction execution sensitivity threshold according to the current environment state, wherein the noise reduction execution sensitivity threshold corresponding to the current environment state being an indoor environment is greater than the noise reduction execution sensitivity threshold corresponding to the current environment state being an outdoor environment; An ambient sound acquisition module for acquiring ambient audio data, the ambient audio data including ambient audio strength and ambient audio content; A mode adjustment module for executing a noise reduction strategy according to the noise reduction execution sensitivity threshold and the ambient audio strength; The noise reduction strategy includes: inputting the ambient audio content into a preset semantic voice recognition model to obtain a recognition result; the semantic voice recognition model is used to recognize a personalized term set from the ambient audio content to obtain the recognition result, the personalized term set including a plurality of personalized voice terms; when the recognition result represents that the personalized term set is recognized from the ambient audio content, the Bluetooth earphone is adjusted to the ambient sound mode, and the ambient audio content is played through the Bluetooth earphone; adjusting the working mode of the Bluetooth earphone according to the recognition result, the working mode including a noise reduction mode and an ambient sound mode; The noise reduction strategy is executed according to the noise reduction execution sensitivity threshold and the ambient audio strength, including: when the ambient audio strength is greater than the noise reduction execution sensitivity threshold, the noise reduction strategy is executed.

9. A Bluetooth earpiece, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to execute a Bluetooth earphone noise reduction method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores computer executable instructions for causing a computer to execute a Bluetooth earphone noise reduction method as claimed in any one of claims 1 to 7.

Images