Sound noise reduction processing method and system based on noise reduction earmuff environment sound monitoring

Abstract

The invention belongs to the field of audio signal processing, provides a sound noise reduction processing method and system based on noise reduction earmuff environment sound monitoring, and aims to solve the problem of low sound noise reduction effectiveness of a noise reduction earmuff in the prior art. The method comprises the steps of acquiring a sound signal corresponding to a surrounding environment, determining a corresponding preset two-stage noise reduction model which comprises a preset first-stage noise reduction model and a preset second-stage noise reduction model, monitoring the environment sound of the surrounding environment, and when the sound signal corresponding to the environment sound is monitored, performing noise reduction on the basis of the preset first-stage noise reduction model. Performing first noise reduction processing on the sound signal to obtain a preliminary noise reduction sound signal, and performing second noise reduction processing on the preliminary noise reduction sound signal based on a preset second-level noise reduction model to obtain a target noise reduction sound signal under the condition that the preliminary noise reduction sound signal is not empty, the noise reduction effectiveness and accuracy in different environments can be improved.

Description

Technical Field

[0001] The present invention relates to the field of audio signal processing, and particularly to a sound noise reduction processing method and system based on ambient sound monitoring of noise-canceling earcups. Background Art

[0002] An earcup is a hearing protection device used to protect the ears from noise. It usually consists of a housing that can cover the auricle, and this housing is connected together by an arch-shaped connecting piece for easy wearing and use. The inside of the earcup is usually filled with sound-absorbing materials and sealing gaskets to enhance its sound insulation effect and comfort. The main function of the earcup is to protect hearing by providing good sealing to reduce the impact of ambient noise on hearing, thereby effectively reducing the impact of noise on the ears. Earcups can generally be divided into sound-insulating earcups and noise-canceling earcups. Sound-insulating earcups usually refer to earcups that isolate external sounds. For example, the sound-insulating earcups used during sleep are mainly used to isolate the influence of all external sounds to help with sleep. Noise-canceling earcups refer to earcups that reduce noise and focus on useful sounds.

[0003] Ambient sound refers to the sounds of the surrounding environment collected through audio devices such as earcups. Sound noise reduction processing generally transmits the useful sounds contained in the ambient sound to the user's ears, enabling the user to still hear relevant external sounds when wearing devices such as earcups, to help the user maintain contact with the surrounding environment. The realization of sound noise reduction processing can transmit the useful sounds in the surrounding environment to the user's ears, making the user feel as if they are not wearing headphones, thus enabling the user to maintain as real a connection with the surrounding environment as possible. With the application of ambient sound, the user can clearly hear the sounds of the surrounding environment, which is suitable for scenarios where it is necessary to maintain awareness of the external environment. For example, using ambient sound in public transportation can help the user better notice changes in relevant environmental factors such as pedestrians and vehicles in the surrounding environment.

[0004] For the sound noise reduction processing of ambient sound by noise-canceling earcups, it generally involves identifying useful sounds in the environment and filtering out the useless sounds, thereby achieving the noise reduction processing of ambient sound. However, for the changing surrounding environment, since the noise is also changing, it is difficult to perform effective sound noise reduction processing.

[0005] Therefore, how to improve the sound noise reduction effectiveness of noise-canceling earcups has become an urgent problem to be solved. Summary of the Invention

[0006] The technical problem solved by the present invention is the technical problem of the relatively low sound noise reduction effectiveness of noise-canceling earcups.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: in response to a setting instruction corresponding to a selection operation of a preset noise-canceling earphone usage environment, determine the surrounding environment type corresponding to the surrounding environment where the preset noise-canceling earphone is used; determine the surrounding environment type identifier corresponding to the surrounding environment type, and based on the surrounding environment type identifier, determine a corresponding preset two-stage noise-canceling model, where the preset two-stage noise-canceling model includes a preset first-stage noise-canceling model and a preset second-stage noise-canceling model; based on the preset noise-canceling earphone, monitor the ambient sound of the surrounding environment; in the case of monitoring the sound signal corresponding to the ambient sound, based on the preset first-stage noise-canceling model, perform a first noise-canceling process on the sound signal to obtain a preliminary noise-canceling sound signal; determine whether the preliminary noise-canceling sound signal is empty; in the case where the preliminary noise-canceling sound signal is not empty, based on the preset second-stage noise-canceling model, perform a second noise-canceling process on the preliminary noise-canceling sound signal to obtain a target noise-canceling sound signal

[0008] As a preferred solution of the sound noise-canceling process based on the ambient sound monitoring of the noise-canceling earphone according to the present invention, performing a first noise-canceling process on the sound signal based on the preset first-stage noise-canceling model to obtain a preliminary noise-canceling sound signal includes at least one of the following: performing noise-canceling processing on the noise components in the sound signal that are greater than or equal to a preset first volume threshold; performing noise-canceling processing on the noise components in the sound signal that are less than or equal to a preset second volume threshold, where the preset second volume threshold is less than the preset first volume threshold; performing noise-canceling processing on the noise components outside the preset tone range included in the sound signal.

[0009] The beneficial effects of the present invention: By classifying the surrounding environment where the user uses the preset noise-canceling earphone into different environment types, for each type of surrounding environment, a corresponding preset two-stage noise-canceling model is set for noise cancellation, and the user sets the corresponding environment type according to the surrounding environment where the preset noise-canceling earphone is used, and then automatically determines the corresponding preset two-stage noise-canceling model for noise cancellation according to the environment type. The user sets the corresponding environment type according to the surrounding environment where the preset noise-canceling earphone is used. Compared with automatically identifying the surrounding environment, it can improve the accuracy of determining the environment type, thereby improving the accuracy and effectiveness of noise cancellation. On this basis, adopting the noise-canceling model corresponding to this environment type for noise cancellation, due to the correspondence and adaptability between the environment type and the noise-canceling model, it can further improve the accuracy and effectiveness of noise cancellation, and adopting the preset two-stage noise-canceling model can further improve the accuracy and effectiveness of noise cancellation. Thus, for the changing surrounding environment, it can automatically adjust the corresponding noise-canceling model according to the change of the environment type, and adopt the corresponding preset two-stage noise-canceling model to perform precise and adaptive noise-canceling processing, which can improve the noise-canceling effectiveness and accuracy in different environments. Brief Description of the Drawings

[0010] Figure 1 It is a schematic flowchart of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earcups provided by an embodiment of the present invention;

[0011] Figure 2 It is a schematic diagram of the relationship between the surrounding environment and the preset two-stage noise reduction model of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earcups provided by an embodiment of the present invention;

[0012] Figure 3 It is a schematic flowchart of the first sub-process of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earcups provided by an embodiment of the present invention;

[0013] Figure 4 It is a schematic flowchart of the second sub-process of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earcups provided by an embodiment of the present invention. Detailed Embodiments

[0014] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following provides a detailed description of the specific embodiments of the present invention with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them.

[0015] An embodiment of the present invention provides a sound noise reduction processing method based on ambient sound monitoring of noise-canceling earcups. The method can be applied to devices including but not limited to noise-canceling earcups and is adopted when performing sound detection on, including but not limited to, noise-canceling earcups.

[0016] In view of the technical problem of the low sound noise reduction effectiveness of noise-canceling earmuffs in the traditional technology, the inventor proposes a sound noise reduction processing method based on ambient sound monitoring of noise-canceling earmuffs according to the embodiments of the present invention. The core idea of the embodiments of the present invention is as follows: the surrounding environment where the user wears the noise-canceling earmuffs is divided into different environment types. For each type of surrounding environment, a corresponding rough noise reduction and fine noise reduction preset two-stage noise reduction model is set for noise reduction. And the user sets the corresponding environment type according to the surrounding environment where the noise-canceling earmuffs are used, and then automatically determines the corresponding preset two-stage noise reduction model for noise reduction according to the environment type. The user setting the corresponding environment type according to the surrounding environment where the noise-canceling earmuffs are used can improve the accuracy of determining the environment type compared with automatically identifying the surrounding environment, thereby improving the accuracy and effectiveness of noise reduction. On this basis, the corresponding noise reduction model of this environment type is adopted for noise reduction. Due to the correlation and adaptability between the environment type and the noise reduction model, the accuracy and effectiveness of noise reduction can be further improved. And the preset two-stage noise reduction model is adopted, with rough noise reduction first and then fine noise reduction, which can further improve the accuracy and effectiveness of noise reduction. Thus, for the changing surrounding environment, the corresponding noise reduction model can be automatically adjusted according to the change of the environment type, and the corresponding preset two-stage noise reduction model is adopted for precise and adaptive noise reduction processing, which can improve the noise reduction effectiveness in different environments.

[0017] Embodiment 1. Please refer to Figure 1 and Figure 2 , Figure 1 which is a schematic flow chart of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earmuffs provided by the embodiments of the present invention. Figure 2 which is a schematic diagram of the relationship between the surrounding environment and the preset two-stage noise reduction model of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earmuffs provided by the embodiments of the present invention. As Figure 1 shown, in this embodiment, the method includes but is not limited to the following steps S11-S17:

[0018] S11. Respond to the setting instruction corresponding to the selection operation of the preset noise-canceling earmuff usage environment, and determine the surrounding environment type corresponding to the surrounding environment where the preset noise-canceling earmuffs are used.

[0019] Explanatorily, the noise-canceling earmuffs are preset in advance, that is, the preset noise-canceling earmuffs. The preset noise-canceling earmuffs represent a device used to reduce environmental noise, mainly used to reduce the interference of external noise on hearing and focus on useful target sounds as much as possible.

[0020] A setting function is pre-configured on the preset noise-canceling earmuffs. The setting function is used for the user to set the usage environment of the preset noise-canceling earmuffs. The implementation of the setting function includes, but is not limited to, physical buttons and virtual buttons. Thus, the user can set the usage environment of the preset noise-canceling earmuffs through the setting function. Moreover, the corresponding relationships among the surrounding environment, the surrounding environment type, and the surrounding environment type identifier are pre-set. For example, Figure 2 as shown, exemplarily, when the surrounding environment where the preset noise-canceling earmuffs are used is a road, the corresponding relationship among the road, the road environment type, and the road environment type identifier is established. Similarly, the corresponding relationship among the residence, the residence environment type, and the residence environment type identifier is established. The corresponding relationship among the market, the market environment type, and the market environment type identifier can also be established. Among them, the road can be a traffic road. The noise characteristics of the ambient sounds of the traffic road, the residential community, and the market including, but not limited to, the farmers' market are different. The ambient sound is mainly related to the location and time. The setting of the corresponding relationship among the surrounding environment, the surrounding environment type, and the surrounding environment type identifier is mainly determined according to the specific surrounding environment corresponding to several regions or times involved in the business carried out by the user of the preset noise-canceling earmuffs, so as to distinguish the surrounding environments corresponding to the ambient sounds with different noise characteristics.

[0021] When the user uses the preset noise-canceling earmuffs, according to the actual usage environment of the preset noise-canceling earmuffs and based on the configuration of the above-mentioned setting function, the user performs an operation to select the usage environment of the preset noise-canceling earmuffs. In response to the selection operation, the preset noise-canceling earmuffs will generate corresponding setting instructions. Thus, the preset noise-canceling earmuffs respond to the setting instructions corresponding to the operation of the user to select the usage environment of the preset noise-canceling earmuffs, and determine the surrounding environment type corresponding to the surrounding environment where the preset noise-canceling earmuffs are used.

[0022] S12. Determine the surrounding environment type identifier corresponding to the surrounding environment type, and determine the corresponding preset two-level noise-canceling model according to the surrounding environment type identifier, where the preset two-level noise-canceling model includes a preset first-level noise-canceling model and a preset second-level noise-canceling model.

[0023] Explanatorily, a two-level noise reduction model is preset, that is, a two-level noise reduction model is preset. The preset two-level noise reduction model represents a model that performs noise reduction in two levels successively. The preset two-level noise reduction model includes a preset first-level noise reduction model and a preset second-level noise reduction model. The preset first-level noise reduction model represents a noise reduction model at the first level that is preset. The preset second-level noise reduction model represents a noise reduction model at the second level that is preset. The preset first-level noise reduction model is a speech recognition model, which is used to recognize various speech components included in the sound signal corresponding to the ambient sound. For example, the sound signal corresponding to the ambient sound may include various speech components such as human voices, vehicle sounds, wind sounds, and rain sounds. The preset first-level noise reduction model includes, but is not limited to, Hidden Markov Model (HMM), Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory Network (LSTM). The preset second-level noise reduction model is a speech adjustment model, and the preset second-level noise reduction model includes, but is not limited to, the deep learning models corresponding to RNNoise, Wav-U-net, and Conv-TasNet.

[0024] Please continue to refer to Figure 2 , such as Figure 2As shown, the corresponding relationships among the preset surrounding environment, the preset surrounding environment type, the preset surrounding environment type identifier, and the preset two-level noise reduction model are preset. Among them, the preset two-level noise reduction model includes a preset first-level noise reduction model and a preset second-level noise reduction model. The preset two-level noise reduction model not only indicates that it includes two noise reduction models, but also indicates the sequential hierarchical order of the two noise reduction models. Among them, the preset two-level noise reduction model is trained using the noise training samples of the corresponding surrounding environment, and the preset first-level noise reduction model is used for the first noise reduction process. The first noise reduction process is a rough noise reduction process or a noise reduction preprocessing process, including but not limited to eliminating or reducing the lowest sound, the highest sound, and non-useful sounds. For example, in the case of on-duty on the road, human voices and vehicle sounds are useful target sounds. In this case, sounds such as firecracker sounds, wind sounds, thunder sounds, and rain sounds other than human voices and vehicle sounds are regarded as noise and noise reduction processing is performed. The preset second-level noise reduction model is used for the second noise reduction process. The second noise reduction process is a fine noise reduction process, including but not limited to adjusting useful sounds. For example, in the case where human voices and vehicle sounds are useful target sounds, the human voices and vehicle sounds are adjusted to an appropriate sound volume to avoid being too loud and harsh, or too soft to be heard clearly, or the human voices and vehicle sounds are subjected to fidelity adjustment and modification, so that the human voices and vehicle sounds have a good auditory effect. Thus, the noise reduction model corresponding to the environment type is adopted for noise reduction. Due to the correspondence and adaptability association between the environment type and the noise reduction model, the preset two-level noise reduction model can better adapt to the environmental sound characteristics of the corresponding surrounding environment for noise reduction. For different surrounding environments, the accuracy and effectiveness of noise reduction can be further improved, better noise reduction effects can be achieved, and by using the preset two-level noise reduction model, different-level noise reduction models are divided into tasks and cooperate, which can further improve the accuracy and effectiveness of noise reduction.

[0025] As described above, when the user selects the surrounding environment, according to the user's selection of the surrounding environment, based on the above corresponding relationship, the surrounding environment type identifier corresponding to the surrounding environment type is determined. Furthermore, based on the surrounding environment type identifier, the corresponding preset two-level noise reduction model is determined. Among them, the preset two-level noise reduction model includes a preset first-level noise reduction model and a preset second-level noise reduction model.

[0026] Exemplarily, when the user determines that the usage environment of the preset noise-canceling earmuffs is to be used beside a road, for example, a law enforcement officer on a traffic road, that is, the surrounding environment of the preset noise-canceling earmuffs is a road, determine that the surrounding environment type of the preset noise-canceling earmuffs is a road environment type. Then, according to the road environment type, determine the road environment type identifier. Further, according to the road environment type identifier, determine that the corresponding preset two-level noise-canceling model includes a preset first-level A noise-canceling model and a preset second-level B noise-canceling model. Among them, the preset first-level A noise-canceling model and the preset second-level B noise-canceling model are trained accordingly using road noise training samples to improve the accuracy and effectiveness of the preset first-level A noise-canceling model and the preset second-level B noise-canceling model in noise-canceling processing of road noise according to the characteristics of road noise. And so on for others. Determine that the preset two-level noise-canceling model corresponding to the residential environment includes a preset first-level C noise-canceling model and a preset second-level D noise-canceling model, and determine that the preset two-level noise-canceling model corresponding to the market environment includes a preset first-level E noise-canceling model and a preset second-level F noise-canceling model, and respectively perform corresponding training using noise training samples of the corresponding surrounding environment to improve the accuracy and effectiveness of noise-canceling processing of the noise in the corresponding surrounding environment.

[0027] S13. Based on the preset noise-canceling earmuffs, monitor the ambient sound of the surrounding environment.

[0028] Explanatorily, the preset noise-canceling earmuffs usually have dedicated ambient sound monitoring microphones provided on one or both sides of the earmuffs. These microphones can capture the sound signals in the surrounding environment, that is, the ambient sound. The ambient sound refers to the sound of the surrounding environment collected through the headphone microphone. Then, through acoustic structure design and signal compensation processing, the user can clearly hear the external sounds.

[0029] S14. When the sound signal corresponding to the ambient sound is monitored, based on the preset first-level noise-canceling model, perform the first noise-canceling processing on the sound signal to obtain a preliminarily noise-canceled sound signal.

[0030] Explanatorily, as described above, in the case of detecting a sound signal corresponding to ambient sound, based on a preset first-level noise reduction model, the sound signal is subjected to a first noise reduction process. The first noise reduction process is a rough noise reduction process or a noise reduction preprocessing process, including but not limited to eliminating or reducing the sounds corresponding to the following options: including but not limited to the lowest sounds corresponding to wind sounds, rain sounds, and insect sounds; including but not limited to the highest sounds corresponding to thunder sounds and firecracker sounds; non-useful sounds other than the target sound. For example, in the case where human voices and vehicle sounds are useful target sounds, non-useful sounds such as dog barks, cat meows, and cow moos other than human voices and vehicle sounds are regarded as noise and subjected to noise reduction processing to obtain a preliminary noise-reduced sound signal. The preliminary noise-reduced sound signal represents the useful target sound retained after the preliminary noise reduction process. For example, in the application scenario of a walkie-talkie, the preliminary noise-reduced sound signal generally refers to human voices. In the application scenario of road driving, the preliminary noise-reduced sound signal generally includes human voices and vehicle sounds.

[0031] S15. Determine whether the preliminary noise-reduced sound signal is empty.

[0032] Explanatorily, determining whether the preliminary noise-reduced sound signal is empty mainly determines whether the sound signal corresponding to the ambient sound contains a useful target sound signal. If the above determination is yes, it is determined that the preliminary noise-reduced sound signal is not empty, that is, the sound signal corresponding to the ambient sound contains a useful target sound signal. Otherwise, if the above determination is no, it is determined that the preliminary noise-reduced sound signal is empty, that is, the sound signal corresponding to the ambient sound does not contain a useful target sound signal.

[0033] Exemplarily, in the application scenario of a walkie-talkie, the preliminary noise-reduced sound signal generally refers to human voices. In the case where the sound signal corresponding to the ambient sound contains human voices, it is determined that the preliminary noise-reduced sound signal is not empty. Otherwise, in the case where the sound signal corresponding to the ambient sound does not contain human voices, it is determined that the preliminary noise-reduced sound signal is empty.

[0034] S16. In the case where the preliminary noise-reduced sound signal is not empty, based on the preset second-level noise reduction model, the preliminary noise-reduced sound signal is subjected to a second noise reduction process to obtain a target noise-reduced sound signal.

[0035] Explanatorily, as described above, when the preliminary noise-reduced sound signal is not empty, that is, when the sound signal corresponding to the ambient sound contains a useful target sound signal, based on a preset second-level noise reduction model, the preliminary noise-reduced sound signal is subjected to a second noise reduction process. The second noise reduction process is a precise noise reduction process, including but not limited to adjusting the useful sound. For example, when human voices and vehicle sounds are useful target sounds, the human voices and vehicle sounds are adjusted to an appropriate sound volume to avoid being too loud and harsh, or too soft to be clearly heard, or the human voices and vehicle sounds are subjected to fidelity adjustment and modification, so that the human voices and vehicle sounds have a good auditory effect, thereby obtaining a target noise-reduced sound signal, that is, the sound signal after noise reduction processing. Thus, the sound of the surrounding environment monitored based on the noise-canceling earcups is subjected to noise reduction processing, and the target noise-reduced sound signal is transmitted to the user in a sound manner. The user hears the sound of the surrounding environment, so that noise reduction can be better performed and the surrounding environment can be perceived. For example, in the case where the noise-canceling earcups are applied to the walkie-talkie used by the duty personnel in a residential community, the duty personnel not only need to pay attention to the human voices and vehicle sounds in the community, but also need to pay attention to the public network intercom sounds transmitted in the walkie-talkie. Based on the above noise reduction processing, the above-mentioned duty personnel can not only effectively pay attention to the intercom sound of the walkie-talkie through noise reduction, but also can well perceive the useful target sounds in the surrounding environment. Thus, through the preset two-level noise reduction model, through division of labor and cooperation, the accuracy of noise reduction processing of the preset first-level noise reduction model and the preset second-level noise reduction model in their respective surrounding environments can be improved, thereby improving the effectiveness of noise reduction.

[0036] S17. When the preliminary noise-reduced sound signal is empty, the preliminary noise-reduced sound signal is not subjected to a second noise reduction process.

[0037] Explanatorily, when the preliminary noise-reduced sound signal is empty, that is, when the sound signal corresponding to the ambient sound does not contain a useful target sound signal, the preliminary noise-reduced sound signal is not subjected to a second noise reduction process. Exemplarily, when human voices and vehicle sounds are useful target sounds, and it is monitored that the sound signal corresponding to the ambient sound contains non-useful sounds such as wind sounds, rain sounds, dog barks, cat meows, cow moos, firecracker sounds, etc., the sound signal corresponding to the ambient sound does not contain a useful target sound signal, the preliminary noise-reduced sound signal is empty, and the preliminary noise-reduced sound signal is not subjected to a second noise reduction process, which can shorten the noise reduction process of the sound signal corresponding to the ambient sound and improve the efficiency of noise reduction processing.

[0038] In an embodiment of the present invention, by responding to a setting instruction corresponding to a selection operation of a preset noise-canceling earmuff usage environment, the surrounding environment type corresponding to the surrounding environment where the preset noise-canceling earmuff is used is determined, and the surrounding environment type identifier corresponding to the surrounding environment type is determined. Then, according to the surrounding environment type identifier, a corresponding preset two-level noise-canceling model is determined. The preset two-level noise-canceling model includes a preset first-level noise-canceling model and a preset second-level noise-canceling model. Based on the preset noise-canceling earmuff, the ambient sound of the surrounding environment is monitored. When the sound signal corresponding to the ambient sound is detected, based on the preset first-level noise-canceling model, the sound signal is subjected to a first noise-canceling process to obtain a preliminary noise-canceling sound signal. Then, it is determined whether the preliminary noise-canceling sound signal is empty. When the preliminary noise-canceling sound signal is not empty, based on the preset second-level noise-canceling model, the preliminary noise-canceling sound signal is subjected to a second noise-canceling process to obtain a target noise-canceling sound signal. Thus, the noise of the surrounding environment monitored based on the preset noise-canceling earmuff is processed, realizing that by classifying the surrounding environment where the user uses the preset noise-canceling earmuff into different environment types, for each type of surrounding environment, a corresponding preset two-level noise-canceling model is set for noise cancellation, and the user sets the corresponding environment type according to the surrounding environment where the preset noise-canceling earmuff is used. Then, according to the environment type, the corresponding preset two-level noise-canceling model is automatically determined for noise cancellation. By setting the corresponding environment type according to the surrounding environment where the preset noise-canceling earmuff is used by the user, compared with automatically identifying the surrounding environment, the accuracy of determining the environment type can be improved, thereby improving the accuracy and effectiveness of noise cancellation. On this basis, by adopting the noise-canceling model corresponding to this environment type for noise cancellation, due to the correlation and adaptability between the environment type and the noise-canceling model, the accuracy and effectiveness of noise cancellation can be further improved. Moreover, by using the preset two-level noise-canceling model, the accuracy and effectiveness of noise cancellation can be further improved. Therefore, for the changing surrounding environment, according to the change of the environment type, the corresponding noise-canceling model can be automatically adjusted, and the corresponding preset two-level noise-canceling model is adopted for accurate and adaptive noise-canceling processing, which can improve the noise-canceling effectiveness and accuracy in different environments.

[0039] In one embodiment, based on the preset first-level noise-canceling model, subjecting the sound signal to a first noise-canceling process to obtain a preliminary noise-canceling sound signal includes at least one of the following:

[0040] Performing noise cancellation on the noise components in the sound signal that are greater than or equal to a preset first volume threshold;

[0041] Performing noise cancellation on the noise components in the sound signal that are less than or equal to a preset second volume threshold, where the preset second volume threshold is less than the preset first volume threshold;

[0042] Performing noise cancellation on the noise components outside the preset tone range in the sound signal.

[0043] Explanatorily, noise reduction refers to reducing or eliminating background noise through various technical means. It can also be understood that noise reduction means reducing the intensity, frequency, or duration of noise to an acceptable level through corresponding means and methods.

[0044] Volume represents the high or low, or strong or weak, of a sound. A first volume threshold is preset, that is, a first volume threshold is preset. The preset first volume threshold represents the sound components with too high a sound volume, and the sound components greater than or equal to the preset first volume threshold are regarded as noise components. For example, the sound components with too high a volume such as thunder and firecracker sounds. And a second volume threshold is preset, that is, a second volume threshold is preset. The preset second volume threshold represents the sound components with relatively low sound volume, such as inaudible whispering sounds. And the sound components less than or equal to the preset second volume threshold are regarded as noise components. Among them, the preset second volume threshold is less than the preset first volume threshold. The preset first volume threshold represents the threshold of the volume of relatively large noise components, and the preset second volume threshold represents the threshold of the volume of relatively small noise components.

[0045] At the same time, since different sounds are mainly distinguished based on the timbre of the sound, and the timbre reflects the quality and characteristics of the sound and is a characteristic determined by the sound source itself. Therefore, a timbre range is preset, that is, a preset timbre range. The preset timbre range represents the range of timbres corresponding to the useful target sound components. For example, in the case where human voices and vehicle sounds are useful target sounds, the range of timbres composed of human voices and vehicle sounds is used as the preset timbre range. The preset timbre range can be a timbre interval or a timbre set.

[0046] According to the above concept and setting, when performing the first noise reduction process on the sound signal based on the preset first-level noise reduction model to obtain a preliminarily noise-reduced sound signal, it includes at least one of the following: reducing or eliminating the noise components in the sound signal that are greater than or equal to the preset first volume threshold to reduce them to an acceptable level, so as to perform noise reduction on the larger sound components outside the useful target sound; reducing or eliminating the noise components in the sound signal that are less than or equal to the preset second volume threshold to reduce them to an acceptable level, so as to perform noise reduction on the smaller sound components outside the useful target sound; reducing or eliminating the noise components outside the preset timbre range in the sound signal to reduce them to an acceptable level, so as to perform noise reduction on other sound components outside the useful target sound.

[0047] In an embodiment of the present invention, through at least one of the following: performing noise reduction processing on noise components in the sound signal that are greater than or equal to a preset first volume threshold; performing noise reduction processing on noise components in the sound signal that are less than or equal to a preset second volume threshold; performing noise reduction processing on noise components outside a preset tone color range in the sound signal, thereby performing a first noise reduction processing on the sound signal, that is, rough noise reduction processing, based on a preset first-level noise reduction model, to obtain a preliminarily noise-reduced sound signal, achieving the retention of useful initial target sound signals, and being able to improve the accuracy and effectiveness of the rough noise reduction corresponding to the first noise reduction by virtue of the adaptability and precise division of labor of the preset first-level noise reduction model for noise reduction processing in the corresponding surrounding environment, and further improving the effectiveness and accuracy of the overall noise reduction.

[0048] In one embodiment, performing noise reduction processing on noise components outside a preset tone color range in the sound signal includes:

[0049] Based on a preset tone color recognition model, recognizing the tone color of the sound contained in the sound signal;

[0050] According to the preset tone color range, determining whether the tone color is included in the preset tone color range;

[0051] If the above determination is negative, performing noise reduction processing on the sound component corresponding to the tone color;

[0052] If the above determination is positive, not performing noise reduction processing on the sound component corresponding to the tone color.

[0053] Explanatorily, timbre refers to the unique quality of a sound, which is determined by different overtones. The main basis for distinguishing different sounds is the timbre of the sound. The timbre reflects the quality and characteristics of the sound and is a characteristic determined by the sound source itself. Therefore, a tone color recognition model is preset in advance, that is, a preset tone color recognition model, and the preset tone color recognition model represents a recognition model for recognizing several sound signals included in ambient sound. For example, in the case where ambient sound includes various sounds such as wind sound, rain sound, human voice, and vehicle sound, based on the preset tone color recognition model, according to the tone color, various sound components included in the ambient sound are recognized, useful target sounds are retained, and sound components other than the useful target sounds are subjected to noise reduction processing.

[0054] According to the above concept and setting, based on the preset tone color recognition model, the tone color of the sound contained in the sound signal is recognized, and according to the preset tone color range, it is determined whether the tone color is included in the preset tone color range. If not, the sound component corresponding to the tone color is subjected to noise reduction processing. If so, the sound component corresponding to the tone color is not subjected to noise reduction processing, thereby retaining useful target sounds and treating sound components other than the useful target sounds as noise and performing noise reduction processing to filter out noise components.

[0055] In an embodiment of the present invention, based on a preset timbre recognition model, the timbre of the sound signal is recognized, and according to a preset timbre range, it is judged whether the timbre of the sound is included in the preset timbre range. If not, that is, the timbre of the sound is not included in the preset timbre range, the sound component corresponding to the timbre of the sound is subjected to noise reduction processing. If so, that is, the timbre of the sound is included in the preset timbre range, the sound component corresponding to the timbre of the sound is not subjected to noise reduction processing, that is, the sound component corresponding to the above timbre of the sound is retained, and as a preliminary noise-reduced sound signal, the preliminary noise-reduced sound signal is a useful sound signal, that is, the target sound signal, which can initially and effectively reduce the noise and invalid sounds in the ambient sound, realize retaining the useful initial target sound signal, and can improve the accuracy and effectiveness of the rough noise reduction corresponding to the first noise reduction by means of the adaptability and precise division of labor of the preset first-level noise reduction model for noise reduction processing in the corresponding surrounding environment, thereby improving the effectiveness and accuracy of the overall noise reduction.

[0056] In one embodiment, please refer to Figure 3 , Figure 3 which is the schematic diagram of the first sub-process of the sound noise reduction processing method based on the ambient sound monitoring of noise-canceling earphones provided by the embodiment of the present invention. As Figure 3 shown, in this embodiment, when the preliminary noise-reduced sound signal is not empty, based on the preset second-level noise reduction model, the preliminary noise-reduced sound signal is subjected to a second noise reduction process to obtain a target noise-reduced sound signal, including:

[0057] S31. Determine the initial sound volume corresponding to the preset target initial sound signal included in the preliminary noise-reduced sound signal;

[0058] S32. Judge whether the initial sound volume falls into the following preset target volume range: {preset third volume threshold, preset fourth volume threshold}, where the preset third volume threshold is less than the preset fourth volume threshold;

[0059] S33. If the above judgment is negative, adjust the initial sound volume to the preset target volume range;

[0060] S34. If the above judgment is positive, do not adjust the initial sound volume.

[0061] Explanatorily, a third volume threshold is preset, that is, the third volume threshold is preset, and a fourth volume threshold is preset, that is, the fourth volume threshold is preset, and the preset third volume threshold is less than the preset fourth volume threshold. That is, the preset third volume threshold represents the lower limit of the volume, and the preset fourth volume threshold represents the upper limit of the volume. Thus, the preset third volume threshold and the preset fourth volume threshold form a preset target volume range, that is, {preset third volume threshold, preset fourth volume threshold}. The preset target volume range represents the upper and lower limit ranges of the appropriate volume suitable for human ear hearing. Otherwise, for sounds outside the preset target volume range, the sound is too loud and easy to be harsh, or the sound is too small and people are also likely to hear unclearly.

[0062] According to the above concept and setting, identify the initial sound volume corresponding to the preset target initial sound signal included in the preliminary noise reduction sound signal, and determine whether the initial sound volume falls within the following preset target volume range: {preset third volume threshold, preset fourth volume threshold}, that is, determine whether the initial sound volume is greater than or equal to the preset third volume threshold and less than or equal to the preset fourth volume threshold, where the preset third volume threshold is less than the preset fourth volume threshold. If not, that is, the initial sound volume does not fall within the following preset target volume range, adjust the initial sound volume to the preset target volume range. If so, that is, the initial sound volume falls within the following preset target volume range, do not adjust the initial sound volume.

[0063] Further, adjusting the initial sound volume to the preset target volume range includes:

[0064] In the case where the initial sound volume is less than the preset third volume threshold, increase the initial sound volume to be greater than or equal to the preset third volume threshold;

[0065] Or, in the case where the initial sound volume is greater than the preset fourth volume threshold, decrease the initial sound volume to be less than or equal to the preset fourth volume threshold.

[0066] Specifically, in the case where the initial sound volume is less than the preset third volume threshold, increase the initial sound volume to be greater than or equal to the preset third volume threshold, and the increased degree will also be less than or equal to the preset fourth volume threshold. Or, in the case where the initial sound volume is greater than the preset fourth volume threshold, decrease the initial sound volume to be less than or equal to the preset fourth volume threshold, and the decreased degree will also be greater than or equal to the preset third volume threshold, so that the corresponding sound can be suitable for hearing, avoiding hearing damage or unclear sound due to too small sound.

[0067] In an embodiment of the present invention, by identifying the initial sound volume corresponding to the preset target initial sound signal included in the initially noise-reduced sound signal, and determining whether the initial sound volume falls within the following preset target volume range: {preset third volume threshold, preset fourth volume threshold}, where the preset third volume threshold is less than the preset fourth volume threshold, and if not, adjusting the initial sound volume to the preset target volume range, and if so, not adjusting the initial sound volume. Thus, by adjusting the volume of the identified preset target initial sound signal, not only can the adaptability and division of labor accuracy of noise reduction processing in the corresponding surrounding environment by means of the preset second-level noise reduction model be utilized to improve the accuracy and effectiveness of the precise noise reduction corresponding to the second noise reduction, but also the clarity and auditory comfort of the target noise-reduced sound signal can be improved by automatically adjusting the initial sound volume based on the preset second-level noise reduction model, so as to enhance the further noise reduction effect of the target noise-reduced sound signal, thereby improving the effectiveness and accuracy of overall noise reduction.

[0068] In one embodiment, please refer to Figure 4 , Figure 4 which is the schematic diagram of the second sub-process of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earphones provided by the embodiment of the present invention. As Figure 4 shown, in this embodiment, when the initial sound volume is less than the preset third volume threshold, increasing the initial sound volume to be greater than or equal to the preset third volume threshold includes:

[0069] S41. Increase the initial sound volume according to the preset volume increase amplitude to obtain an initially increased sound;

[0070] S42. Determine the increased sound volume corresponding to the initially increased sound;

[0071] S43. Determine whether the increased sound volume is greater than the preset fourth volume threshold;

[0072] S44. If the above determination is yes, cyclically reduce the increased sound volume according to the preset volume reduction step until the increased sound volume is less than or equal to the preset fourth volume threshold;

[0073] S45. If the above determination is no, do not cyclically reduce the increased sound volume.

[0074] Explanatorily, a preset volume increase amplitude is set in advance, that is, a preset volume increase amplitude, which represents the magnitude of the volume increase, that is, the magnitude of the volume change. And a preset volume decrease step is set in advance, that is, a preset volume decrease step, which represents that the step is the adjustment amount taken each time the volume size is updated, and it controls the speed at which the volume approaches the target size. The step is also known as the Learning Rate in English.

[0075] According to the above concept and setting, when the initial sound volume is less than the preset third volume threshold, when the initial sound volume is increased to be greater than or equal to the preset third volume threshold, first, according to the preset volume increase amplitude, the initial sound volume is increased to obtain an initial increased sound. Then, the increased sound volume corresponding to the initial increased sound is determined, and it is judged whether the increased sound volume is greater than the preset fourth volume threshold. If so, that is, it is determined that the increased sound volume is too large, and then according to the preset volume decrease step, the increased sound volume is cyclically probed and decreased until the increased sound volume is less than or equal to the preset fourth volume threshold, so as to ensure that the increased sound volume falls within the above preset target volume range: {preset third volume threshold, preset fourth volume threshold}. And if not, that is, it is determined that the increased sound volume is not greater than the preset fourth volume threshold, that is, the increased sound volume falls within the above preset target volume range, and the increased sound volume is not cyclically decreased.

[0076] In an embodiment of the present invention, by increasing the initial sound volume according to the preset volume increase amplitude to obtain an initial increased sound, determining the increased sound volume corresponding to the initial increased sound, and judging whether the increased sound volume is greater than the preset fourth volume threshold. If so, according to the preset volume decrease step, the increased sound volume is cyclically decreased until the increased sound volume is less than or equal to the preset fourth volume threshold. If not, the increased sound volume is not cyclically decreased, it is possible to automatically explore and adjust the initial sound volume. When the initial sound volume is increased too much, on the basis of the preset volume increase amplitude, the increase amplitude of the initial sound volume can be automatically decreased through the preset volume decrease step, avoiding damage to hearing caused by high volume, realizing the protection of the hearing of the wearer of the noise-canceling earphone, and further improving the effectiveness and accuracy of the sound noise reduction processing based on the ambient sound monitoring of the noise-canceling earphone.

[0077] In one embodiment, after obtaining the target noise reduction sound signal, it further includes:

[0078] Based on the communication connection between the preset noise-canceling earphone and the preset intercom device, the target noise reduction sound signal is transmitted to the preset intercom device, and then the preset intercom device communicates with other preset intercom devices according to the target noise reduction sound signal.

[0079] Explanatorily, a walkie-talkie device is preset, that is, a preset walkie-talkie device, and the preset walkie-talkie device includes but is not limited to a walkie-talkie mobile phone. The preset walkie-talkie device is communicatively connected to a preset noise-canceling earphone, and the above communicative connection is a wireless connection or a wired connection. The wired connection includes but is not limited to a connecting line between the preset noise-canceling earphone and the preset walkie-talkie device, so that the preset noise-canceling earphone and the preset walkie-talkie device can communicate and cooperate to conduct a walkie-talkie on the public network.

[0080] According to the above settings, based on the communicative connection between the preset noise-canceling earphone and the preset walkie-talkie device, a target noise-canceling sound signal is transmitted to the preset walkie-talkie device. Then, the preset walkie-talkie device communicates with other preset walkie-talkie devices according to the target noise-canceling sound signal to realize the walkie-talkie communication of the public network based on the noise-canceling earphone. This can enable the wearer of the noise-canceling earphone to hear useful walkie-talkie information more clearly and enable the wearer to better perceive useful target sounds in the surrounding environment. Especially for some people and services that need to pay attention to the walkie-talkie information on the public network at any time and better perceive the surrounding environment, it can improve the noise-canceling effectiveness and communication quality in different environments.

[0081] In an embodiment of the present invention, based on the communicative connection between the preset noise-canceling earphone and the preset walkie-talkie device, a target noise-canceling sound signal is transmitted to the preset walkie-talkie device including but not limited to a walkie-talkie mobile phone. Then, the preset walkie-talkie device communicates with other preset walkie-talkie devices according to the target noise-canceling sound signal to realize the public network walkie-talkie of the environment sound monitoring of the preset noise-canceling earphone and the walkie-talkie device. As described above, due to the sound noise-canceling processing based on the environment sound monitoring of the preset noise-canceling earphone, it can improve the noise-canceling effectiveness and accuracy in different environments. Based on this, it can improve the communication efficiency and effect of the public network walkie-talkie in different surrounding environment situations, and further improve the service quality of the service corresponding to the public network walkie-talkie. In some cases, it is necessary to pay attention to the walkie-talkie information on the public network at any time and better perceive the surrounding environment. For example, for the law enforcement officers on the road, they need to pay attention to the vehicles and pedestrians on the road to better perceive the surrounding environment and also need to pay attention to the public network communication transmitted by the walkie-talkie device, which can improve the noise-canceling effectiveness and communication quality in different environments.

[0082] In one embodiment, responding to the setting instruction corresponding to the selection operation of the usage environment of the preset noise-canceling earphone includes:

[0083] Based on the preset button configured on the preset noise-canceling earphone, receiving the selection operation of the user operating the preset button;

[0084] Responding to the selection operation, determining the setting instruction corresponding to the usage environment of the preset noise-canceling earphone, and responding to the setting instruction.

[0085] Explanatorily, keys are pre-configured on the preset noise-canceling earmuffs, namely, preset keys, and the preset keys represent keys for a user to set the usage environment of the noise-canceling earmuffs. The preset keys include, but are not limited to, physical keys and virtual keys. By operating the preset keys, the user can perform selection operations and settings for the usage environment of the noise-canceling earmuffs. Please continue to refer to Figure 2 , such as Figure 2 shown, three surrounding environments can be selected and set through the preset keys. For example, for security personnel in a residential community, the usage environment of the noise-canceling earmuffs can be selected as the residential environment, and noise reduction can be performed through the corresponding two-stage noise reduction model. For duty personnel in a farmers' market, the market environment can be selected, and noise reduction can be performed through the corresponding two-stage noise reduction model. For duty personnel on the road, the road environment can be selected, and noise reduction can be performed through the corresponding two-stage noise reduction model.

[0086] According to the above concept and setting, when implementing the setting instruction corresponding to the selection operation of the preset noise-canceling earmuff usage environment, specifically, based on the preset keys configured on the preset noise-canceling earmuffs, the selection operation of the user operating the preset keys is received, and in response to the selection operation, the setting instruction corresponding to the preset noise-canceling earmuff usage environment is determined, and the setting instruction is responded to.

[0087] In the embodiment of the present invention, by receiving the selection operation of the user operating the preset keys based on the preset keys configured on the preset noise-canceling earmuffs, responding to the selection operation, determining the setting instruction corresponding to the preset noise-canceling earmuff usage environment, and responding to the setting instruction, it is possible to facilitate the user to select the surrounding environment for using the noise-canceling earmuffs, and then conveniently and accurately determine the surrounding environment type corresponding to the surrounding environment for using the noise-canceling earmuffs, thereby improving the accuracy of determining the environment type. On this basis, the noise reduction model corresponding to this environment type is adopted for noise reduction, and the above-mentioned sound noise reduction processing method based on the ambient sound monitoring of the noise-canceling earmuffs is implemented to improve the accuracy and effectiveness of noise reduction, and the noise reduction effectiveness and accuracy in different environments can be improved.

[0088] It should be noted that for the above-mentioned sound noise reduction processing method based on the ambient sound monitoring of the noise-canceling earmuffs in each of the above embodiments, the technical features included in different embodiments can be recombined as needed to obtain the combined implementation scheme, but all are within the protection scope required by the present invention.

[0089] An embodiment of the present invention further provides a sound noise reduction processing system based on ambient sound monitoring of noise-canceling earcups. The sound noise reduction processing system includes a preset noise-canceling earcup and a preset intercom device communicatively connected to the preset noise-canceling earcup. The preset noise-canceling earcup includes a memory and an embedded processor connected to the memory. The memory is used to store a computer program. The embedded processor is used to run the computer program to execute the steps of the sound noise reduction processing method based on ambient sound monitoring of noise-canceling earcups described in any of the above embodiments. Among them, the embedded processor includes, but is not limited to, a single-chip microcomputer (MCU), a microprocessor (MPU), a digital signal processor (DSP), and a field programmable gate array (FPGA).

[0090] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks specified in the function.

[0091] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A sound noise reduction processing method based on noise reduction earmuffs ambient sound monitoring, characterized in that: include: In response to a setting instruction corresponding to a selection operation of a preset noise reduction earmuff usage environment, determining an ambient environment type corresponding to an ambient environment in which the preset noise reduction earmuff is used; Determine an ambient environment type identifier corresponding to the ambient environment type, and determine a corresponding preset two-stage noise reduction model according to the ambient environment type identifier, wherein the preset two-stage noise reduction model includes a preset first-level noise reduction model and a preset second-level noise reduction model; Based on the preset noise reduction earmuffs, monitoring the ambient sound of the surrounding environment; When a sound signal corresponding to the ambient sound is monitored, the sound signal is subjected to a first noise reduction process based on the preset first-level noise reduction model to obtain a preliminary noise-reduced sound signal; Determining whether the preliminary noise reduction sound signal is empty; When the preliminary noise reduction sound signal is not empty, the preliminary noise reduction sound signal is subjected to a second noise reduction process based on the preset second-level noise reduction model to obtain a target noise reduction sound signal.

2. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 1, characterized in that: Based on the preset first-level noise reduction model, the sound signal is subjected to a first noise reduction process to obtain a preliminary noise-reduced sound signal, including at least one of the following: Performing noise reduction processing on the noise component contained in the sound signal that is greater than or equal to a preset first volume threshold; Performing noise reduction processing on the noise component contained in the sound signal that is less than or equal to a preset second volume threshold, wherein the preset second volume threshold is less than the preset first volume threshold; Noise components outside the preset timbre range contained in the sound signal are subjected to noise reduction processing.

3. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 2, characterized in that: The noise components outside the preset timbre range contained in the sound signal are subjected to noise reduction processing, including: Based on a preset timbre recognition model, identifying the timbre of the sound contained in the sound signal; According to a preset timbre range, determining whether the timbre of the sound is within the preset timbre range; If the above judgment is no, the sound component corresponding to the sound timbre is subjected to noise reduction processing.

4. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 1, characterized in that: In the case that the preliminary noise reduction sound signal is not empty, based on the preset second-level noise reduction model, the preliminary noise reduction sound signal is subjected to a second noise reduction process to obtain a target noise reduction sound signal, including: Identifying an initial sound volume corresponding to a preset target initial sound signal contained in the preliminary noise reduction sound signal; Determining whether the initial sound volume falls within the following preset target volume range: {preset third volume threshold, preset fourth volume threshold}, wherein the preset third volume threshold is less than the preset fourth volume threshold; If the above judgment is no, the initial sound volume is adjusted to the preset target volume range.

5. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 4, characterized in that: Adjusting the initial sound volume to the preset target volume range includes: When the volume of the initial sound is less than the preset third volume threshold, increasing the volume of the initial sound to be greater than or equal to the preset third volume threshold; Alternatively, when the initial sound volume is greater than the preset fourth volume threshold, the initial sound volume is reduced to be less than or equal to the preset fourth volume threshold.

6. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 5, characterized in that: When the initial sound volume is less than the preset third volume threshold, increasing the initial sound volume to be greater than or equal to the preset third volume threshold includes: According to a preset volume increase amplitude, the volume of the initial sound is increased to obtain an initial increased sound; Determining a volume of a raised sound corresponding to the initial raised sound; Determining whether the volume of the increased sound is greater than the preset fourth volume threshold; If the above judgment is yes, the volume of the increased sound is cyclically reduced according to the preset volume reduction step until the volume of the increased sound is less than or equal to the preset fourth volume threshold.

7. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 1, characterized in that: The method further comprises: In the case that the preliminary noise reduction audio signal is empty, the preliminary noise reduction audio signal is not subjected to a second noise reduction process.

8. The method for noise reduction processing based on environmental sound monitoring using noise reduction earmuffs according to any one of claims 1 to 7, characterized in that: After obtaining the target noise reduction sound signal, the method further includes: Based on the communication connection between the preset noise reduction earmuffs and the preset intercom device, the target noise reduction sound signal is transmitted to the preset intercom device, and then the preset intercom device communicates with other preset intercom devices according to the target noise reduction sound signal.

9. The method for noise reduction processing based on noise reduction earmuffs environmental sound monitoring according to claim 8, characterized in that: The setting instructions corresponding to the selection operation of the preset noise reduction earmuff usage environment include: Based on a preset button configured for the preset noise reduction earmuff, receiving a selection operation of the preset button by a user; In response to the selection operation, a setting instruction corresponding to the preset noise reduction earmuff usage environment is determined, and the setting instruction is responded to.

10. A sound noise reduction processing system based on noise reduction earmuffs for environmental sound monitoring, the sound noise reduction processing system comprising a preset noise reduction earmuff and a preset intercom device that establishes a communication connection with the preset noise reduction earmuffs, characterized in that: The preset noise reduction earmuffs include a memory and an embedded processor connected to the memory; the memory is used to store a computer program; the embedded processor is used to run the computer program to perform the steps of the method according to any one of claims 1 to 9.

Images