Noise reduction device

Abstract

The utility model provides a noise reduction device which is in communication connection with a user terminal for a user to input a plurality of source audios. The noise reduction equipment comprises a main control device, a sound sensor array, an audio pickup device, an audio recognition device and an audio noise reduction device, and the main control device is provided with a setting interface for a user to set types of a plurality of source audios in different scene modes and attributes of the plurality of source audios in the different scene modes to obtain a plurality of sample audios; the sound sensor array is used for acquiring audios in different directions; the audio pickup device picks up the sound of the noise reduction equipment in each direction in the current surrounding environment to obtain a plurality of audios to be processed; the audio recognition device recognizes a plurality of to-be-processed audios according to a plurality of sample audios to obtain attributes of various types of audios of the to-be-processed audios; the audio noise reduction device carries out audio processing according to attributes of various types of audios in a plurality of to-be-processed audios, and then carries out noise reduction on each plurality of to-be-processed audios to obtain a plurality of noise-reduced audios.

Description

Technical Field

[0001] The utility model relates to the technical field of voice playing, in particular to a noise reduction device. Background Art

[0002] At present, the active noise reduction technology mainly reduces noise by generating reverse noise reduction signals and performing noise reduction processing on all collected sounds. However, this noise reduction method only performs non-discriminatory noise reduction processing on the sounds collected in any direction. For example, when a sound with a warning feature is collected, it will be regarded as noise and reduced due to the frequency difference from other sounds, lacking directivity and easily causing isolation between the real world and the "noise reduction world", resulting in the loss of audio. At the same time, this noise reduction method also cannot adapt to different scenarios and perform noise reduction in different ways. For example, in an outdoor scenario, the sounds of birds or insects in the fields are often not desired to be filtered out, but they are regarded as noise and reduced due to the frequency difference from other sounds. Summary of the Utility Model

[0003] In view of this, it is necessary to propose a noise reduction device.

[0004] In a first aspect, an embodiment of the utility model provides a noise reduction device, which is communicatively connected to a user terminal for a user to input a plurality of source audio, and each source audio includes a type of audio; the noise reduction device includes a main control device, a sound sensor array, an audio pickup device, an audio recognition device, and an audio noise reduction device. The main control device is communicatively connected to the user terminal, and the main control device is provided with a setting interface including the plurality of source audio for the user to set the types of the plurality of source audio in different scenario modes, and the attributes of the plurality of source audio in different scenario modes to obtain a plurality of sample audio. The sample audio includes one or more scenario tags and one or more attribute flags. Each scenario mode corresponds to a scenario tag, and the attribute flags include noise and non-noise; the sound sensor array includes a plurality of sound sensors for obtaining audio in different directions; the audio pickup device is communicatively connected to the sound sensor array to pick up the sounds in all directions of the current surrounding environment of the noise reduction device to obtain a plurality of audio to be processed, and each audio to be processed includes multiple types of audio; the audio recognition device is communicatively connected to the main control device and the audio pickup device respectively to identify the plurality of audio to be processed according to the plurality of sample audio to obtain the attributes of various types of audio of the audio to be processed; the audio noise reduction device is communicatively connected to the audio recognition device to perform audio processing according to the attributes of various types of audio in the plurality of audio to be processed, and further perform noise reduction on each of the plurality of audio to be processed to obtain a plurality of noise-reduced audio.

[0005] Optionally, the audio noise reduction device is also communicatively connected to the user terminal for the user to receive the several noise-reduced audios.

[0006] Optionally, the audio processing includes sound cancellation processing and sound enhancement processing; the audio noise reduction device includes a first processor and a second processor, the first processor is configured to perform sound cancellation processing on the audio to be processed, and the second processor is configured to perform sound enhancement processing on the audio to be processed.

[0007] Optionally, the sound cancellation processing is to determine the directions of the several audios to be processed and output an audio in the opposite direction to cancel out one type or multiple types of audio marked with the attribute of noise; the sound enhancement processing is to amplify one type or multiple types of audio marked with the attribute of non-noise.

[0008] Optionally, the user inputs, through the user terminal, noise reduction strategies corresponding to the several audios to be processed in different scenarios, so that the first processor and / or the second processor perform noise reduction processing on the corresponding audios to be processed according to the corresponding noise reduction strategies; each scenario mode corresponds to a scenario, and the noise reduction strategies corresponding to different audio scenarios are different; the scenarios include a warning transparency scenario, a directional transparency scenario, a human voice transparency scenario, and an original sound transparency scenario.

[0009] Optionally, the noise reduction strategy corresponding to the warning transparency scenario is that the second processor performs sound enhancement processing on the audio of the warning sound; the noise reduction strategy corresponding to the directional transparency scenario is that the first processor performs sound cancellation processing on the audio that is not a human voice in a specific direction; the noise reduction strategy corresponding to the human voice transparency scenario is that the second processor performs sound enhancement processing on the audio of the human voice; the noise reduction strategy corresponding to the original sound transparency scenario is that the first processor performs sound cancellation processing on the audio that is not a natural sound, or performs sound cancellation processing on the audio that is not a natural sound and part of the natural sound.

[0010] Optionally, the noise reduction device further includes a feedback device, the feedback device is communicatively connected to the user terminal to receive feedback information input by the user; the main control device is also communicatively connected to the feedback device to set the attributes of the several source audios according to the feedback information.

[0011] Optionally, the sound sensor array is formed by several sub-arrays each including several sound sensors, and each sub-array correspondingly collects one type of audio in one direction.

[0012] Optionally, the noise reduction device is further provided with a selection interface including a plurality of mode buttons, and the plurality of mode buttons include a warning mode button, a directional mode button, a voice mode button, and an original sound mode button that respectively correspond to the warning transparency scenario, the directional transparency scenario, the voice transparency scenario, and the original sound transparency scenario.

[0013] Optionally, different mode buttons generate different mode selection signals when the user selects a scenario mode, and each mode selection signal corresponds to a noise reduction strategy corresponding to an audio scenario, so that the first processor and / or the second processor perform noise reduction processing on the plurality of audio to be processed according to the mode selection signal.

[0014] The above-mentioned noise reduction device obtains a plurality of source audios through communication connection with a user terminal, and allows the user to set the types of the plurality of source audios in different scenario modes and the attributes of the plurality of source audios in different scenario modes to obtain a plurality of sample audios. After picking up the sounds in each direction of the current surrounding environment of the noise reduction device to obtain a plurality of audio to be processed, the attributes of various types of audio in the audio to be processed are identified through the plurality of sample audios, so as to perform noise reduction on each of the plurality of audio to be processed, and perform noise reduction in different noise reduction manners to adapt to different scenarios, thereby realizing the intelligence of noise reduction. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts.

[0016] Figure 1 Schematic diagram of the noise reduction device provided by the embodiment of the utility model.

[0017] Figure 2 Internal structure schematic diagram of the noise reduction device provided by the embodiment of the utility model.

[0018] Each component label

[0019]

[0020] The realization, functional characteristics, and advantages of the object of the present utility model will be further described in conjunction with the embodiments with reference to the drawings. Detailed Embodiments

[0021] In the description of the present utility model, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is the orientation or positional relationship based on the drawings. It is only for the convenience of describing the present utility model and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present utility model.

[0022] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present utility model, "a plurality of" means two or more, unless otherwise specifically defined.

[0023] In the present utility model, unless otherwise clearly specified and defined, the terms "installed", "connected", "connected to", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or a communication connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present utility model can be understood according to specific circumstances.

[0024] To make the content of the present utility model clearer and more accurate, it will be described in detail below with reference to the drawings. The drawings in the specification show examples of the embodiments of the present utility model, in which the same reference numerals represent the same elements. It can be understood that the scale shown in the drawings of the specification is not the actual implementation scale of the present utility model. It is only for illustrative purposes and is not drawn according to the original size.

[0025] Please refer to Figure 1, which is a schematic diagram of the noise reduction device provided by the utility model embodiment. This application provides a noise reduction device 100. The noise reduction device 100 is communicatively connected to a user terminal 1 for the user to input a number of source audio through the user terminal 1. Among them, the user terminal 1 can be an electronic device such as a mobile phone or a tablet. The user can perform various operations through the user terminal 1. For example, operations such as recording and deleting the source audio, selecting the type of the recorded source audio in different scenario modes, and setting the noise reduction strategy corresponding to the source audio in different scenario modes. Each source audio includes one type of audio. The number of source audio is obtained by the user collecting and extracting the audio existing in the current surrounding environment through the noise reduction device 100, or can be input by the user from other devices or the historical audio collected by the noise reduction device 100. The number of source audio can be, but is not limited to, different types of audio such as human voices, vehicle driving sounds, alarm sounds, bird calls, and wind sounds. The noise reduction device 100 provided by this application can set the type of each source audio in different scenario modes according to the user's setting operations, and perform audio processing on the to-be-processed audio picked up by the noise reduction device 100 from the current surrounding environment based on the set audio, realizing the intelligence of noise reduction. The specific features of each component in the noise reduction device 100 will be specifically described below.

[0026] Please refer to Figure 2 , which is a schematic diagram of the internal structure of the noise reduction device provided by the utility model embodiment.

[0027] As Figure 2As shown in the figure, the noise reduction device 100 includes a main control device 2, a sound sensor array 3, an audio pickup device 4, an audio recognition device 5, and an audio noise reduction device 6. Among them, the main control device 2 is communicatively connected to the user terminal 1 to process the source audio in response to various operations of the user. Specifically, the main control device 2 is provided with a setting interface 21 containing a number of source audios for the user to set the types of a number of source audios in different scene modes, and the attributes of a number of source audios in different scene modes to obtain a number of sample audios. Among them, different scene modes include but are not limited to point-through mode, warning-through mode, original sound-through mode, full noise reduction mode, through mode, sleep mode, and other modes. It can be understood that one scene mode corresponds to one usage scenario of the noise reduction device 100, and different scene modes can be determined by reading the usage scenarios corresponding to each historical audio stored locally or in the cloud of the noise reduction device 100. The sample audio includes one or more scene markers and one or more attribute flags. Each scene mode corresponds to one scene marker. The attribute flags include noise and non-noise, which are respectively used to label the audio attributes of the source audio in the corresponding scene. That is to say, any source audio can be set to multiple scene modes and the audio attributes in the set scene modes. Therefore, for the same source audio, it can be noise or non-noise in different scene modes. In this embodiment, the setting interface 21 is located outside the main body of the noise reduction device 100 for the user to perform various operations. The specific features of the setting interface 21 in the main control device 2 will be described below.

[0028] In this embodiment, the main control device 2 realizes the setting of each source audio by generating a number of buttons for the user to operate on the setting interface 21 in response to the user's setting operations. The user's operation methods for the buttons include but are not limited to operations such as clicking and dragging on the setting interface 21. After obtaining the source audios corresponding to different types of audio, each source audio is configured to be displayed on the setting interface 21. The display method of each source audio can be to display each source audio by allocating a corresponding first button 211 to each source audio through the setting interface 21. Each first button 211 is configured to respond to the corresponding operations input by the user so that the user can intuitively set each source audio.

[0029] When the main control device 2 analyzes the setting operation and obtains the user's expected setting operations for each source audio. The main control device 2 controls the setting interface 21 to display corresponding second buttons 212 assigned to each scene mode according to the expected setting operations. Each second button 212 is configured to be able to establish an association relationship with other components. Whenever a first button 211 establishes an association relationship with a second button 212, it indicates that the corresponding original audio has been set to the corresponding scene mode, and a corresponding setting instruction is generated to indicate that the corresponding source audio needs to further set its audio attributes in the corresponding scene mode. Since a source audio may be noise or non-noise in different scene modes, therefore, the main control device 2 controls the setting interface 21 to display corresponding third buttons 213 assigned to the scene markers corresponding to the corresponding scene modes of each source audio to distinguish different scene modes, and display corresponding fourth buttons 214 assigned to the attribute markers corresponding to the corresponding scene modes of each source audio to distinguish the audio attributes of each source audio in each scene mode. Among them, attribute marker 1 and attribute marker 2 respectively represent noise and non-noise, so as to adapt to the usage scenario where any source audio may be noise or non-noise in different scene modes, and further improve the intelligence of noise reduction.

[0030] In the above embodiments, the display methods, display styles, operation methods of the source audio, scene mode, scene marker, attribute marker, etc. in the setting interface 21, and each button generated by the setting interface 21 are only an example of the setting interface 21, and are not a limitation to the setting interface 21, so details are not described here.

[0031] In this embodiment, the sound sensor array 3 includes a plurality of sound sensors 31. The sound sensor array 3 is used to acquire audio from different directions. Specifically, the sound sensor array is formed by a plurality of sub-arrays each containing a number of sound sensors. Each sub-array correspondingly collects one type of audio in one direction. In this application, the plurality of sound sensors 31 can be either located outside the main body of the noise reduction device 100 or inside the main body of the noise reduction device 100. When the plurality of sound sensors 31 are located outside the main body of the noise reduction device 100, they can be either on the same end face outside the main body of the noise reduction device 100 as the setting interface or on different end faces outside the main body of the noise reduction device 100.

[0032] In this embodiment, the audio pickup device 4 is communicatively connected to the sound sensor array 3 to pick up sounds from all directions in the current surrounding environment of the noise reduction device 100 to obtain a number of audio to be processed. Among them, each audio to be processed includes various types of audio. Each direction can be determined according to the pickup range of the sound sensor array 3 in the noise reduction device 100, or can be determined according to the pickup range of a sound pickup component such as a miniature microphone integrated with the sound sensor array 3 in the noise reduction device 100. For example, when the noise reduction device 100 is used in a meeting, the pickup range of the sound sensor array 3 can be adjusted accordingly according to the different directions of the participants in the meeting, so that the sound sensor can collect various types of audio from all directions in the meeting to obtain a number of audio to be processed.

[0033] In this embodiment, the audio recognition device 5 is communicatively connected to the main control device 2 and the audio pickup device 4 respectively to identify a number of audio to be processed according to a number of sample audio to obtain the attributes of various types of audio in the audio to be processed. Specifically, after the audio pickup device 4 picks up a number of audio to be processed obtained by the sound sensor array 3, the audio recognition device 5 analyzes each audio to be processed to obtain the audio frequencies of various audio in each audio to be processed. The audio recognition device 5 obtains the scene markers of various types of audio by comparing the audio frequencies of various audio with the audio frequencies of each source audio, so as to obtain the scene mode adapted to the current surrounding environment through the scene markers of various audio, and further obtain the audio attributes of various audio in the adapted scene mode.

[0034] In this embodiment, the audio noise reduction device 6 is communicatively connected to the audio recognition device 5 to perform audio processing according to the attributes of various types of audio in a number of audio to be processed, and then perform noise reduction on each of the number of audio to be processed to obtain a number of noise-reduced audio. The audio noise reduction device 6 is also communicatively connected to the user terminal 1 to output a number of noise-reduced audio to the user. The specific features of the audio noise reduction device 6 will be described in detail below.

[0035] In this embodiment, the audio processing includes sound cancellation processing and sound enhancement processing. The audio noise reduction device 6 includes a first processor 61 and a second processor 62. Among them, the first processor 61 is used to perform sound cancellation processing on the audio to be processed. The second processor 62 is used to perform sound enhancement processing on the audio to be processed. Specifically, the sound cancellation processing is to determine the directions of a number of audio to be processed, and output the audio in the opposite direction to cancel one type or multiple types of audio with the attribute flag of noise. The sound enhancement processing is to amplify one type or multiple types of audio with the attribute flag of non-noise. The principles of the sound cancellation processing and the sound enhancement processing will be described in detail below.

[0036] When performing sound cancellation processing, the azimuth of each audio to be processed is obtained according to the sound sensor array 3. Specifically, based on the sound source localization technology, the audio picked up by each sound sensor 31 is localized. For example, beamforming, super-resolution spectral estimation, or based on the time difference of arrival (TDOA), etc., to form the azimuth corresponding to each sound sensor 31, and then the azimuths of each audio are obtained. The azimuths of each audio can be used to confirm whether the audios to be processed are relevant, such as whether different audios to be processed are picked up from the same azimuth. In this embodiment, to enable the noise reduction device 100 to collect various types of audio, multiple sensors for collecting different types of audio are preset for each azimuth, so that each azimuth can pick up different types of audio through a sufficient number of sound sensors 31, thereby improving the comprehensiveness of audio pickup of the noise reduction device 100. Analyze each audio to be processed to obtain the audio frequencies of various types of audio in each audio to be processed. When the attribute flag of the audio is noise, the audio in the opposite azimuth is output and canceled based on the number of azimuths of each audio to be processed and the audio frequencies of various types of audio. Among them, the audio frequency of the audio in the opposite azimuth corresponds to the audio frequency of the audio with the attribute flag of noise. When performing sound enhancement processing, while amplifying the audio, it is also necessary to ensure that each audio with the attribute flag of non-noise is within the normal acceptance range of the user. For example, in a noisy environment, sound enhancement processing such as wavelet transform method is used for the identified human voice audio to ensure that both parties can communicate normally.

[0037] In this embodiment, the user inputs the noise reduction strategies corresponding to several audios to be processed in different scenarios through the user terminal 1, so that the first processor 61 and / or the second processor 62 perform noise reduction processing on the corresponding audios to be processed according to the corresponding noise reduction strategies. Among them, each scenario mode corresponds to a scenario, and the noise reduction strategies corresponding to different audio scenarios are different. The scenarios include the warning transparency scenario, the directional transparency scenario, the human voice transparency scenario, and the original sound transparency scenario.

[0038] Furthermore, the noise reduction strategy corresponding to the warning transparency scenario is that the second processor 62 performs sound enhancement processing on the audio of the warning sound. The noise reduction strategy corresponding to the directional transparency scenario is that the first processor 61 performs sound cancellation processing on the audio that is not the human voice in a specific direction. The noise reduction strategy corresponding to the human voice transparency scenario is that the second processor 62 performs sound enhancement processing on the audio of the human voice. The noise reduction strategy corresponding to the original sound transparency scenario is that the first processor 61 performs sound cancellation processing on the audio that is not the natural sound, or performs sound cancellation processing on the audio that is not the natural sound and part of the natural sound. The noise reduction strategies corresponding to different scenarios will be specifically described below.

[0039] In this embodiment, the transparent transmission of the audio of the warning sound in the audio to be processed specifically means that the second processor 62 performs sound enhancement processing on the audio of the warning sound. Specifically, the audio noise reduction device 6 determines whether there is audio of a warning sound in each audio to be processed. When the audio noise reduction device 6 determines that there is audio of a warning sound in the audio to be processed, the second processor 62 performs sound enhancement processing on the audio of the warning sound in the corresponding audio to be processed, and the first processor 61 performs sound cancellation processing on other audio, or does not process it.

[0040] In this embodiment, the transparent transmission of the audio of the human voice in a specific direction in the audio to be processed specifically means that the first processor 61 performs sound cancellation processing on the audio that is not the human voice in the specific direction. Specifically, the audio noise reduction device 6 determines whether each audio orientation is a specific direction. For example, the front directly ahead, the front left side, and the front right side of the noise reduction device 100 are set as specific directions. At this time, the audio noise reduction device 6 needs to determine whether each audio orientation is one of the front directly ahead, the front left side, and the front right side. When the audio noise reduction device 6 determines that the audio to be processed is in a specific direction, the audio noise reduction device 6 further determines whether there is human voice audio in the corresponding audio to be processed. When there is human voice audio in the corresponding audio to be processed, the first processor 61 performs sound cancellation processing on the non-human voice audio in the corresponding audio to be processed and other audio to be processed that is not in the specific direction.

[0041] In this embodiment, the transparent transmission of the audio of the human voice specifically means that the second processor 62 performs sound enhancement processing on the audio of the human voice. Specifically, the audio noise reduction device 6 determines whether there is human voice audio in each audio to be processed. When there is human voice audio in the audio to be processed, the second processor 62 performs sound enhancement processing on the human voice audio in the corresponding audio to be processed, and the first processor 61 performs sound cancellation processing on other audio, or does not process it.

[0042] In this embodiment, the transparent transmission of the audio of natural sounds specifically means that the first processor 61 performs sound cancellation processing on the audio that is not a natural sound, or performs sound cancellation processing on the audio that is not a natural sound and part of the audio of natural sounds. Specifically, the audio noise reduction device 6 first determines whether there is audio of natural sounds in each audio to be processed. When there is audio of natural sounds in the audio to be processed, the first processor 61 performs sound cancellation processing on all the audio that is not audio of natural sounds in the audio to be processed. If the attributes of various audio in the audio of natural sounds are adjusted through the user's setting operation, the first processor 61 obtains the attributes set for each audio in the audio of natural sounds after the response setting operation, so as to determine whether various audio included in the natural audio in the audio to be processed are noise or non-noise, and then performs sound cancellation processing on the audio whose attribute is marked as noise in the audio of natural sounds.

[0043] In this embodiment, the noise reduction device 100 further includes a feedback device 7. The feedback device 7 is communicatively connected to the user terminal 1 to receive feedback information input by the user. The main control device 2 is also communicatively connected to the feedback device 7 to set the attributes of a plurality of source audio according to the feedback information.

[0044] It can be understood that since the living scenarios of different users are different, for different users, the acceptance levels of the same audio in the same scenario mode are different, and it may be recognized as noise or non-noise. Therefore, when receiving the setting operation of the user, a corresponding feedback mechanism can also be established through the feedback device 7 to receive the feedback information of the user on the output audio after audio processing, so as to reprocess the audio that has been audio processed in the same scenario mode when needed, thereby improving the intelligence of the noise reduction of the noise reduction device 100.

[0045] Exemplarily, the user can pre-enter or select the audio whose attribute flag is set as non-noise by the system through the user terminal 1, such as entering the voice information of relatives, selecting the source audio attribute flags such as alarm sounds, bird calls, and wind sounds as non-noise in each scenario mode, and obtaining their corresponding sample audio. When the feedback device 7 receives feedback information such as "the bird calls are too noisy in a certain scenario mode" through the feedback mechanism, the original "attribute flag of the bird call audio is set as non-noise" in the corresponding scenario mode can be adjusted to "attribute flag of the bird call audio is set as noise" according to the feedback information, and the setting device is made to set the attributes of a plurality of source audio according to the feedback information, so that the audio noise reduction device 6 performs noise reduction on the corresponding audio such as the bird call audio in the audio to be processed or the bird call audio that has been audio processed based on this adjustment.

[0046] In this embodiment, the noise reduction device 100 is further provided with a selection interface 11 including a plurality of mode buttons. The selection interface 11 is located outside the main body of the noise reduction device 100. The selection interface 11 can be on the same end face outside the main body of the noise reduction device 100 as the setting interface 21 and / or a plurality of sound sensors 31, or can be on different end faces outside the main body of the noise reduction device 100. Optionally, the selection interface 11 and the setting interface 21 are on the same end face outside the main body of the noise reduction device 100, and the plurality of sound sensors 31 and the selection interface 11 and the setting interface 21 are respectively on different end faces outside the main body of the noise reduction device 100.

[0047] Further, several mode buttons include a warning mode button 111, a directional mode button 112, a vocal mode button 113, and an original sound mode button 114 that correspond one-to-one to a warning transparency scenario, a directional transparency scenario, a vocal transparency scenario, and an original sound transparency scenario. The user can directly select different scenario modes through different mode buttons, and different mode selection signals are generated when the same mode button is used by the user to select a scenario mode. Each mode selection signal corresponds to a noise reduction strategy for an audio scenario, so that the first processor 61 and / or the second processor 62 can perform noise reduction processing on several audio to be processed according to the mode selection signal.

[0048] In the above embodiment, a user terminal is communicatively connected to obtain several source audios, and the types of several source audios in different scenario modes and the attributes of several source audios in different scenario modes are set by the user to obtain several sample audios. After picking up the sounds in each direction of the current surrounding environment of the noise reduction device to obtain several audio to be processed, the attributes of various types of audio of the audio to be processed are identified through several sample audios, so as to perform noise reduction on each of the several audio to be processed, and different noise reduction methods are used for noise reduction to adapt to different scenarios, thereby realizing the intelligence of noise reduction.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of this application. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

[0050] The above are only the preferred embodiments of the present invention, and of course, the scope of the rights of the present invention cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A noise reduction device, characterized in that, The noise reduction device is communicatively connected to a user terminal for a user to input a plurality of source audio, and each of the source audio includes one type of audio; the noise reduction device includes: A main control device communicatively connected to the user terminal. The main control device is provided with a setting interface including the plurality of source audio for the user to set the types of the plurality of source audio in different scene modes and the attributes of the plurality of source audio in different scene modes to obtain a plurality of sample audio. The sample audio includes one or more scene markers and one or more attribute flags. Each scene mode corresponds to one scene marker, and the attribute flags include noise and non-noise; An acoustic sensor array including a plurality of acoustic sensors for acquiring audio from different directions; An audio pickup device communicatively connected to the acoustic sensor array to pick up sounds from all directions in the current surrounding environment of the noise reduction device to obtain a plurality of audio to be processed, and each audio to be processed includes multiple types of audio; An audio recognition device communicatively connected to the main control device and the audio pickup device respectively to identify the plurality of audio to be processed according to the plurality of sample audio to obtain the attributes of various types of audio of the audio to be processed; and An audio noise reduction device communicatively connected to the audio recognition device to perform audio processing according to the attributes of various types of audio in the plurality of audio to be processed, and further perform noise reduction on each of the plurality of audio to be processed to obtain a plurality of noise-reduced audio.

2. The noise reduction device according to claim 1, characterized in that, The audio noise reduction device is also communicatively connected to the user terminal for the user to receive the plurality of noise-reduced audio.

3. The noise reduction device according to claim 2, wherein, The audio processing includes sound cancellation processing and sound enhancement processing; the audio noise reduction device includes a first processor and a second processor. The first processor is used to perform sound cancellation processing on the audio to be processed, and the second processor is used to perform sound enhancement processing on the audio to be processed.

4. The noise reduction device according to claim 3, characterized in that, The sound cancellation processing is to determine the directions of the plurality of audio to be processed and output audio in the opposite direction to cancel one type or multiple types of audio with the attribute flag of noise; The sound enhancement processing is to amplify one type or multiple types of audio with the attribute flag of non-noise.

5. The noise reduction device according to claim 4, wherein, The user inputs a noise reduction strategy corresponding to the plurality of audio to be processed in different scenarios through the user terminal, so that the first processor and / or the second processor perform noise reduction processing on the corresponding audio to be processed according to the corresponding noise reduction strategy; Each scene mode corresponds to one scene, and different audio scenes correspond to different noise reduction strategies; The scenes include a warning transparency scene, a directional transparency scene, a human voice transparency scene, and an original sound transparency scene.

6. The noise reduction device according to claim 5, wherein, The noise reduction strategy corresponding to the warning transparency scene is that the second processor performs sound enhancement processing on the audio of the warning sound; the noise reduction strategy corresponding to the directional transparency scene is that the first processor performs sound cancellation processing on the audio that is not the human voice in a specific direction; The noise reduction strategy corresponding to the human voice transparency scene is that the second processor performs sound enhancement processing on the audio of the human voice; The noise reduction strategy corresponding to the original sound transparency scenario is that the first processor performs sound cancellation processing on audio that is not natural sound, or performs sound cancellation processing on audio that is not natural sound and part of the natural sound audio.

7. The noise reduction device according to claim 1, characterized in that, The noise reduction device further includes a feedback device, which is communicatively connected to the user terminal to receive feedback information input by the user; the main control device is also communicatively connected to the feedback device to set the attributes of the several source audio according to the feedback information.

8. The noise reduction device according to claim 1, characterized in that, The sound sensor array is formed by several sub-arrays each containing several sound sensors, and each sub-array corresponds to collecting one type of audio in one direction.

9. The noise reduction device according to claim 5, characterized in that, The noise reduction device is further provided with a selection interface including several mode buttons, and the several mode buttons include a warning mode button, a directivity mode button, a human voice mode button, and an original sound mode button corresponding to the warning transparency scenario, the directivity transparency scenario, the human voice transparency scenario, and the original sound transparency scenario respectively.

10. The noise reduction device according to claim 9, characterized in that, Different mode buttons generate different mode selection signals when the user selects a scenario mode, and each mode selection signal corresponds to a noise reduction strategy corresponding to an audio scenario, so that the first processor and / or the second processor perform noise reduction processing on the several audio to be processed according to the mode selection signal.

Images