Sound emitting device adaptive adjustment method and system based on sound field direction recognition

Abstract

Embodiments of the present application provide a sound emitting device adaptive adjustment method, device and system based on sound field direction recognition, comprising: obtaining target sound source data received by a preset microphone matrix sequence of a current first device; processing the target sound source data through a preset sound source feature analysis algorithm to determine sound source feature data, the sound source feature data comprising sound field feature data; and distributing at least the sound channel of the current first device based on the sound source feature data. The sound source data received by the first device is analyzed for features, and the sound source feature data corresponding to the preset microphone matrix sequence is matched to determine the sound channel distribution of the first device and the corresponding second device. The above method can eliminate the need to distinguish the left and right attributes of the sound emitting device, complete the sound channel distribution directly during the process of wearing the sound emitting device, and improve the use efficiency and convenience of the sound emitting device.

Description

Technical Field

[0001] This invention relates to the field of headphone technology, and in particular to an adaptive adjustment method, device, system, electronic device, and storage medium for a sound-generating device based on sound field direction recognition. Background Technology

[0002] To improve audio playback quality and ensure that the audio devices are correctly worn on the user's left and right ears, the audio devices are usually configured to correspond to the left and right channels respectively. Furthermore, each audio device can be marked with "L" and "R" to indicate which ear it should be worn on.

[0003] Existing adaptive adjustment technologies for sound-emitting devices require users to manually identify the "L" and "R" markings on the device, which can lead to incorrect wearing, reversing the channel allocation and affecting the user's experience, thus reducing efficiency. Therefore, existing adaptive adjustment technologies based on sound field direction recognition cannot identify the left or right side of the device when it is worn, potentially leading to incorrect wearing, reversing the channel allocation, and impacting the user's experience, ultimately reducing efficiency. Summary of the Invention

[0004] This invention provides an adaptive adjustment method for a sound-generating device based on sound field direction recognition, in order to solve the problem that existing adaptive adjustment technologies for sound-generating devices based on sound field direction recognition cannot identify the left and right sides of the sound-generating device when it is worn, which may lead to incorrect wearing and reversed channel allocation.

[0005] In a first aspect, embodiments of the present invention provide an adaptive adjustment method for a sound-generating device based on sound field direction recognition. The sound-generating device includes at least a first device, the first device having a microphone matrix, the microphone matrix including at least three microphone units, the microphone matrix being located in planar space or three-dimensional space, and the method comprising the following steps:

[0006] Obtain the target sound source data received by the preset microphone matrix sequence of the current first device;

[0007] The target sound source data is processed by a preset sound source feature parsing algorithm to determine sound source feature data, which includes sound field feature data.

[0008] Based on the sound source feature data, at least the channels of the current first device are allocated.

[0009] Optionally, before acquiring the target sound source data received by the preset microphone matrix sequence of the current first device, the following steps are included:

[0010] Determine the sound source characteristic parameters of the preset microphone matrix sequence of the first device, wherein the sound source characteristic parameters include position parameters, direction parameters and / or phase parameters;

[0011] Based on the position parameters, direction parameters, and / or phase parameters, the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device are determined.

[0012] Optionally, the sound field feature data includes sound field difference data, and the step of processing the target sound source data using a preset sound source feature analysis algorithm to determine the sound source feature data includes:

[0013] By using a preset sound source feature parsing algorithm, the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device is parsed and processed to determine the sound field difference data of each microphone unit corresponding to the target sound source.

[0014] Optionally, the sound field feature data includes relative setting state data, and the method of processing the target sound source data through a preset sound source feature parsing algorithm to determine the sound source feature data further includes:

[0015] By using a preset acoustic model, acoustic matching processing is performed on the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device to obtain the acoustic matching result.

[0016] Based on the acoustic matching results, the relative setting status data of the microphone matrix corresponding to the target sound source is determined;

[0017] Based on the relative setting status data, the wearing status of the first device is determined.

[0018] Optionally, the allocation of audio channels for the current first device based on the audio source feature data includes:

[0019] Determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device;

[0020] Based on the sound source feature rules, the sound source feature data is matched to determine the channel allocation strategy of the first device;

[0021] Based on the channel allocation strategy of the first device, determine the channel allocation strategy of at least the second device.

[0022] Optionally, the step of parsing the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device using a preset sound source feature parsing algorithm to determine the sound field difference data of each microphone unit corresponding to the target sound source includes:

[0023] Determine the sound field direction data and the order data of each microphone unit in the preset microphone matrix sequence within the first device when acquiring target sound source data;

[0024] The sound field direction data and sequence data of each microphone unit are matched with the preset sound field direction data and sequence data in the sound source feature rules to determine the sound field difference data of each microphone unit.

[0025] Secondly, embodiments of the present invention also provide an adaptive adjustment device for a sound-generating device based on sound field direction recognition, the adaptive adjustment device for a sound-generating device based on sound field direction recognition comprising:

[0026] The acquisition module is used to acquire the target sound source data received by the preset microphone matrix sequence of the current first device;

[0027] The processing module is used to process the target sound source data through a preset sound source feature parsing algorithm to determine sound source feature data, wherein the sound source feature data includes sound field feature data;

[0028] The allocation module is used to allocate at least one channel of the current first device based on the sound source feature data.

[0029] Thirdly, embodiments of the present invention also provide an adaptive adjustment system for a sound-generating device based on sound field direction recognition. The adaptive adjustment system for a sound-generating device based on sound field direction recognition includes: an adaptive adjustment device for a sound-generating device based on sound field direction recognition, a server, and a sound-generating device.

[0030] Fourthly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the adaptive adjustment method for a sound-generating device based on sound field direction recognition provided in embodiments of the present invention.

[0031] Fifthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps in the adaptive adjustment method for a sound-generating device based on sound field direction recognition provided in the embodiments of the present invention.

[0032] In this embodiment of the invention, target sound source data received by a preset microphone matrix sequence of a first device is acquired; the target sound source data is processed using a preset sound source feature parsing algorithm to determine sound source feature data, including sound field feature data; based on the sound source feature data, at least one channel of the first device is allocated. By performing feature analysis on the sound source data received by the first device and matching it with the sound source feature data corresponding to the preset microphone matrix sequence, the channel allocation of the first device and the corresponding second device is determined. This method allows for direct channel allocation during the wearing of the sound device without distinguishing between left and right sides, improving the efficiency and convenience of using the sound device. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is an architecture diagram of an adaptive adjustment system for a sound-generating device based on sound field direction recognition, provided in an embodiment of the present invention.

[0035] Figure 2 This is a flowchart of an adaptive adjustment method for a sound-generating device based on sound field direction recognition, provided in an embodiment of the present invention.

[0036] Figure 3 yes Figure 2 Detailed flowchart before step 201;

[0037] Figure 4 yes Figure 2 The detailed flowchart of step 202;

[0038] Figure 5 yes Figure 2 Another specific flowchart for step 202;

[0039] Figure 6 yes Figure 2 The detailed flowchart of step 203;

[0040] Figure 7 yes Figure 3 The detailed flowchart for step 2021;

[0041] Figure 8 This is a schematic diagram of the structure of an adaptive adjustment device for a sound-generating device based on sound field direction recognition provided in an embodiment of the present invention;

[0042] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, Figure 1 This is an architectural diagram of an adaptive adjustment system 100 for a sound-generating device based on sound field direction recognition, provided in an embodiment of the present invention. The system includes: an adaptive adjustment device 800 for a sound-generating device based on sound field direction recognition, a server 101, and a sound-generating device 102. The adaptive adjustment device 800 further includes an acquisition module for acquiring target sound source data received by a preset microphone matrix sequence of the current first device; a processing module for processing the target sound source data using a preset sound source feature analysis algorithm to determine sound source feature data; and an allocation module for allocating at least one channel of the current first device based on the sound source feature data.

[0045] Specifically, the aforementioned sound-generating devices may include, but are not limited to, headphones, neckband speakers, multi-channel portable speakers, and other sound-generating devices with multi-channel transmission capabilities. It is understood that the aforementioned multi-channel transmission capability can be the parallel or serial output of sound data through different channels.

[0046] In this embodiment, the first device can be a dominant sound-generating device. For example, when the dominant sound-generating device is an earphone, the first device can be the main earphone. That is, the sound-generating device adaptive adjustment system based on sound field direction recognition will first determine the channel allocation status of the main earphone, and then allocate the channels of the corresponding secondary earphone. Generally speaking, the sound-generating device adaptive adjustment system based on sound field direction recognition only needs to determine the channel allocation status of the first device to directly allocate the channels of the corresponding second device without matching.

[0047] The aforementioned preset microphone matrix sequence can be an arrangement or combination of multiple microphone units, or different spatial layouts, to capture the directionality and spatial characteristics of sounds with different properties in a sound field. This preset microphone matrix sequence can include, but is not limited to, any microphone array capable of capturing sound in a sound field, such as linear arrays, stereo arrays, and beamforming arrays. It should be noted that the aforementioned preset microphone matrix sequence can be set according to different preset sound source feature analysis algorithms; that is, the preset sound source feature analysis algorithm analyzes the directionality of sound in different sound fields, thereby selecting the corresponding preset microphone matrix sequence to capture that sound.

[0048] The aforementioned preset sound source feature analysis algorithm can be used to analyze the sound captured in the sound field by a preset microphone matrix sequence, thereby determining the sound source and characteristics such as the hysteresis of the emitted sound. Generally, the preset sound source feature analysis algorithm analyzes the captured sound to obtain sound field direction features, and then matches these features with the order features of sound received by each microphone unit corresponding to the preset microphone matrix sequence. Based on the sound field direction, the channel allocation of the first device is determined. If the sound field direction features match the order features of sound received by the microphones corresponding to the preset microphone matrix sequence, then the channels of the first device are allocated according to preset matching rules.

[0049] The aforementioned preset matching rules can be determined based on the order in which each microphone unit in the preset microphone matrix sequence receives sound. For example, if the microphone units in the first device receive sound in the order of microphone a→microphone b→microphone c, it is determined that the first device is currently worn on the left ear or left side of the working area; if the microphone units in the first device receive sound in the order of microphone c→microphone b→microphone a, it is determined that the first device is currently worn on the right ear or right side of the working area. It is understood that the order in which the microphone units receive sound can be changed according to the specific implementation plan, or it can be determined by setting the preset microphone matrix sequence.

[0050] The aforementioned target audio source data may include, but is not limited to, target device audio sources and target environmental audio sources. The target device audio source can be obtained by capturing the sound emitted by the first device, while the target environmental audio source can be obtained by capturing sounds in the environment. It is understood that the aforementioned target environmental audio source can be used to determine whether the sound-emitting device is being worn, i.e., whether the sound-emitting device is worn on the ear or in any ready-to-operate state. The target device audio source is used to determine the channel allocation of the first device. Specifically, it involves analyzing the captured target device audio source and matching the analysis result with the sequence characteristics corresponding to a preset microphone matrix sequence. If a match is successful, the channels of the first device are allocated according to a preset matching rule.

[0051] The aforementioned sound source feature data may include, but is not limited to, sound field feature data. Specifically, since different sound fields may have different sound source feature data—that is, the sound generated at the sound source may have different positions, directions, and phase characteristics—the sound field features at the sound source can be determined by analyzing the sound field feature data. Generally, the sound of the sound field is captured using a preset microphone matrix sequence, and the sound is analyzed according to a preset sound source feature analysis algorithm to obtain the sound source feature data.

[0052] In one possible embodiment, the aforementioned sound-generating device adaptive adjustment system based on sound field direction recognition captures the sound emitted from the sound source through a preset microphone matrix sequence, analyzes the captured sound according to a preset sound source feature analysis algorithm, matches the analysis result with the sequence features of the sound received by each microphone unit corresponding to the preset microphone matrix sequence, and then allocates the sound of the first device according to the matching rules.

[0053] like Figure 2 As shown, Figure 2 This is a flowchart of an adaptive adjustment method for a sound-generating device based on sound field direction recognition, provided by an embodiment of the present invention. The adaptive adjustment method for a sound-generating device based on sound field direction recognition includes the following steps:

[0054] 201. Obtain the target sound source data received by the preset microphone matrix sequence of the current first device.

[0055] In this embodiment of the invention, the above-mentioned adaptive adjustment method for sound-generating devices based on sound field direction recognition can be applied to an adaptive adjustment system for sound-generating devices based on sound field direction recognition. The above-mentioned adaptive adjustment system for sound-generating devices based on sound field direction recognition has functions such as sound data processing, sound signal transmission and reception, and sound data storage, and can be built based on a server or server cluster. The server or server cluster can be an electronic device with sound data processing capabilities.

[0056] The aforementioned sound-generating device may include, but is not limited to, the first device, and the first device is equipped with a microphone matrix. The microphone matrix may include at least three microphone units, and the microphone matrix is ​​located in planar or three-dimensional space. That is, the aforementioned microphone matrix sequence may be an arrangement and combination of multiple microphone units, or different spatial layouts, thereby enabling the capture of the directionality and spatial characteristics of sounds with different properties in the sound field. This preset microphone matrix sequence may include, but is not limited to, any microphone array capable of capturing sound in a sound field, such as linear arrays, stereo arrays, and beamforming arrays. It should be noted that the aforementioned preset microphone matrix sequence can be set according to different preset sound source feature analysis algorithms; that is, the preset sound source feature analysis algorithm analyzes the directionality of sound in different sound fields, thereby selecting the corresponding preset microphone matrix sequence to capture the sound.

[0057] 202. The target sound source data is processed by a preset sound source feature analysis algorithm to determine the sound source feature data.

[0058] The aforementioned preset sound source feature analysis algorithm can be used to analyze the sound captured in the sound field by a preset microphone matrix sequence, thereby determining the sound source and characteristics such as the hysteresis of the emitted sound. Generally, the preset sound source feature analysis algorithm analyzes the captured sound to obtain the sound field direction features, and then matches these features with the order features of the sound received by each microphone unit corresponding to the preset microphone matrix sequence. Based on the sound field direction, the channel allocation of the first device is determined. If the sound field direction features match the order features of the sound received by the microphones corresponding to the preset microphone matrix sequence, then the channels of the first device are allocated according to the preset matching rules.

[0059] The aforementioned target audio source data may include, but is not limited to, target device audio sources and target environmental audio sources. The target device audio source can be obtained by capturing the sound emitted by the first device, while the target environmental audio source can be obtained by capturing sounds in the environment. It is understood that the aforementioned target environmental audio source can be used to determine whether the sound-emitting device is being worn, i.e., whether the sound-emitting device is worn on the ear or in any ready-to-operate state. The target device audio source is used to determine the channel allocation of the first device. Specifically, it involves analyzing the captured target device audio source and matching the analysis result with the sequence characteristics corresponding to a preset microphone matrix sequence. If a match is successful, the channels of the first device are allocated according to a preset matching rule.

[0060] The aforementioned sound source feature data may include, but is not limited to, sound field feature data. Specifically, since different sound fields may have different sound source feature data—that is, the sound generated at the sound source may have different positions, directions, and phase characteristics—the sound field features at the sound source can be determined by analyzing the sound field feature data. Generally, the sound of the sound field is captured using a preset microphone matrix sequence, and the sound is analyzed according to a preset sound source feature analysis algorithm to obtain the sound source feature data.

[0061] In one possible embodiment, the above-mentioned sound-generating device adaptive adjustment system based on sound field direction recognition can use the above-mentioned preset sound source feature parsing algorithm to parse and process the target sound source data captured by the preset microphone matrix sequence to obtain the corresponding sound source feature data.

[0062] 203. Based on the sound source feature data, at least the current first device's audio channels are allocated.

[0063] In this embodiment of the invention, the aforementioned sound source feature data may include, but is not limited to, sound field feature data. Specifically, since different sound fields may have different sound source feature data, that is, the sound generated at the sound source may have different positions, directions, and phase characteristics, the sound field features at the sound source can be determined by determining the sound field feature data. Generally, the sound of the sound field is captured by a preset microphone matrix sequence, and the sound is analyzed according to a preset sound source feature parsing algorithm to obtain the sound source feature data.

[0064] In one possible embodiment, the above-mentioned sound-generating device adaptive adjustment system based on sound field direction recognition determines the channel allocation strategy of the first device by matching the parsed sound source feature data with the matching rules corresponding to the preset microphone matrix sequence, and allocates the channels of the first device according to the channel allocation strategy.

[0065] In this embodiment of the invention, target audio source data received by a preset microphone matrix sequence of the current first device is acquired; the target audio source data is processed using a preset audio source feature parsing algorithm to determine audio source feature data, including sound field feature data; based on the audio source feature data, at least the channels of the current first device are allocated. By performing feature analysis on the audio source data received by the first device and matching it with the audio source feature data corresponding to the preset microphone matrix sequence, the channel allocation of the first device and the corresponding secondary earphone is determined. This method allows for channel allocation to be completed directly during earphone use without distinguishing between left and right earphone attributes, improving the efficiency and convenience of earphone use.

[0066] Optional, such as Figure 3As shown, before obtaining the target sound source data received by the preset microphone matrix sequence of the current first device in step 201, steps 2011-2012 are also included, wherein:

[0067] 2011. Determine the sound source characteristic parameters of the preset microphone matrix sequence of the first device.

[0068] In this embodiment of the invention, the aforementioned sound source feature parameters may include, but are not limited to, position parameters, direction parameters, and / or phase parameters corresponding to the matrix sequence. The position parameters may be the position information of each microphone unit in the first device within the preset microphone matrix sequence. Generally, different types of microphone matrix sequences can be constructed from different arrangements and combinations of microphone units. The constructed microphone matrix sequence can acquire and determine sound sources from corresponding directions, obtaining the corresponding direction parameters. Since different microphone units receive sound sources in different orders, the sound source data can be converted using waveform diagrams, and then the hysteresis characteristics of the phase parameters can be used to determine which microphone unit receives the sound source data first.

[0069] 2012. Based on position parameters, direction parameters and / or phase parameters, determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device.

[0070] The aforementioned sound source feature rules can be determined based on the order in which the microphone units of the preset microphone matrix sequence of the first device receive the sound source. Generally, due to the different positions and orientations of the microphone units in different microphone matrix sequences, the order in which different microphone units receive the same sound source will be different. Therefore, based on this sequence feature, the corresponding sound source feature rules can be obtained by determining the position parameters, orientation parameters, and / or phase parameters corresponding to different microphone matrix sequences.

[0071] Optional, such as Figure 4 As shown, in step 202, the step of processing the target audio source data and determining the audio source feature data through a preset audio source feature parsing algorithm further includes step 2021, wherein:

[0072] 2021. Using a preset sound source feature analysis algorithm, the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device is analyzed and processed to determine the sound field difference data of each microphone unit corresponding to the target sound source.

[0073] In this embodiment of the invention, the aforementioned sound field difference data can be used to determine the different features of the sound source feature rules corresponding to the sounds received by each microphone unit. Generally, by confirming the preset microphone matrix sequence, the corresponding sound source feature rules can be determined. That is, after parsing the captured sound source data through the aforementioned preset sound source feature parsing algorithm, it can be matched with the corresponding sound source feature rules. If a match is found, the channels of the first device can be allocated according to the preset matching rules.

[0074] Specifically, if the sound source characteristic rule in the current preset microphone matrix sequence is determined as follows: when the microphone unit in the first device receives sound in the order of microphone a→microphone b→microphone c, it is determined that the first device is currently worn on the left ear or left side of the working area; when the microphone unit in the first device receives sound in the order of microphone c→microphone b→microphone a, it is determined that the first device is currently worn on the right ear or right side of the working area. Then, based on the above sound source characteristic rule, the sequence of sounds received by the microphone units after parsing is compared and matched, and the final channel allocation is determined based on the matching result.

[0075] It is understandable that the order in which the microphone units receive sound can be changed according to the specific implementation plan, or it can be determined by setting a preset microphone matrix sequence.

[0076] Optional, such as Figure 5 As shown, in step 202, the step of processing the target audio source data and determining the audio source feature data using a preset audio source feature parsing algorithm further includes steps 204-206, wherein:

[0077] 204. Using a preset acoustic model, perform acoustic matching processing on the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device to obtain the acoustic matching result.

[0078] In this embodiment of the invention, the aforementioned preset acoustic model can be used to detect the target sound source data received by the microphone unit, and determine whether the target sound source data is a target device sound source or a target environmental sound source. If it is a target environmental sound source, the target environmental sound source needs to be detected in the next step to determine the wearing status of the first device.

[0079] Specifically, a preset acoustic model can be constructed by acquiring different environmental sound sources and their corresponding acoustic wave characteristics. This constructed preset acoustic model is then used to detect the target sound source data received by the microphone unit, distinguishing between the target device sound source and the target environmental sound source. Understandably, the aforementioned target environmental sound source can be used to determine whether the sound-emitting device is being worn, i.e., whether it is being worn on the ear or in any ready-to-use state. The target device sound source is used to determine the channel allocation of the first device. This involves analyzing the captured sound from the target device sound source and matching the analysis results with the sequence features corresponding to the preset microphone matrix sequence. If a match is successful, the channels of the first device are allocated according to preset matching rules.

[0080] In one possible embodiment, the aforementioned sound-generating device adaptive adjustment system based on sound field direction recognition performs acoustic matching processing on the target sound source data through a preset acoustic model, thereby determining that the current target sound source data is caused by a certain environmental factor. For example, by performing acoustic matching processing on the friction sound when wearing headphones through a preset acoustic model, it is determined that the current target sound source data is the target environmental sound source, that is, the sound caused by friction when wearing headphones.

[0081] 205. Based on the acoustic matching results, determine the relative setting status data of the microphone matrix corresponding to the target sound source.

[0082] The aforementioned relative setting status data can be used to determine the wearing status of the first device. Generally, the acoustic matching result after acoustic matching processing through the aforementioned preset acoustic model is compared or matched with the relative setting status of the target sound source corresponding to the microphone matrix, thereby determining the wearing status of the first device.

[0083] Specifically, since the acoustic matching result processed by the above-mentioned preset acoustic model can be a sound wave or waveform corresponding to a certain target environmental sound source, it is matched with the preset sound wave or waveform. If the match is successful, the wearing state of the first device is determined according to the wearing state corresponding to the preset sound wave or waveform.

[0084] 206. Determine the wearing status of the first device based on the relative setting status data.

[0085] In one possible embodiment, the above-mentioned sound-generating device adaptive adjustment system based on sound field direction recognition performs acoustic matching processing on the target sound source data through a preset acoustic model to obtain an acoustic matching result. The acoustic matching result is then matched with the relative setting state data of the target sound source corresponding to the preset microphone matrix. Based on the state corresponding to the matching result, the wearing state of the first device is determined.

[0086] Optional, such as Figure 6As shown, in step 203, the step of allocating at least the channels of the current first device based on the sound source feature data, further includes steps 2031-2033, wherein:

[0087] 2031. Determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device.

[0088] In this embodiment of the invention, a preset microphone matrix sequence of the first device can be determined according to a specific implementation plan and the current environmental state. The above-mentioned sound source feature rules can be determined according to the arrangement and combination of microphone units corresponding to the preset microphone matrix sequence. Specifically, it can be determined according to the order in which the microphone units corresponding to the preset microphone matrix sequence of the first device receive the sound source. Since the position and direction settings of the microphone units in different microphone matrix sequences will cause different microphone units to receive the same sound source in different orders, the corresponding sound source feature rules can be obtained by determining the position parameters, direction parameters and / or phase parameters corresponding to different microphone matrix sequences based on this order feature.

[0089] It should be noted that the aforementioned phase parameters can be processed by algorithms such as delay summation algorithm, frequency domain beamforming algorithm, and machine learning-based algorithm to process the signals and sound sources acquired by each microphone in the microphone array, calculate the time difference of sound waves from different sound sources reaching each microphone unit, and use the time difference to estimate the distance from the sound source to each microphone unit, so as to calculate the order in which each microphone unit receives the sound, thereby determining the phase parameters corresponding to each microphone unit.

[0090] 2032. Based on the sound source feature rules, match the sound source feature data to determine the channel allocation strategy of the first device.

[0091] The aforementioned channel allocation strategy can be determined based on the arrangement and combination characteristics of microphone units corresponding to the preset microphone matrix sequence. Specifically, if the corresponding sound source characteristic rule in the current preset microphone matrix sequence is determined to be: when the order in which the microphone units in the first device receive sound is microphone a→microphone b→microphone c, then it is determined that the first device is currently worn on the left ear or the left side of the working area, and the aforementioned sound-field direction recognition-based adaptive adjustment system allocates left channel audio data to the first device. When the order in which the microphone units in the first device receive sound is microphone c→microphone b→microphone a, then it is determined that the first device is currently worn on the right ear or the right side of the working area, and the aforementioned sound-field direction recognition-based adaptive adjustment system allocates right channel audio data to the first device.

[0092] 2033. Based on the channel allocation strategy of the first device, determine at least the channel allocation strategy of the second device.

[0093] In one possible embodiment, the above-mentioned sound field direction recognition-based adaptive adjustment system for sound-generating devices, after determining the channel allocation strategy of the first device, allocates the audio data of the other channel to the second device corresponding to the first device.

[0094] In another possible embodiment, the above-mentioned sound-generating device adaptive adjustment system based on sound field direction recognition can also optimize the corresponding channel allocation strategy of the second device according to the channel allocation strategy of the first device. For example, if the volume allocated in the channel allocation strategy of the first device is too low, the volume of the corresponding channel of the second device will be automatically allocated to a certain level so as to achieve a moderate volume when using both ears.

[0095] Optional, such as Figure 7 As shown, in step 2021, the step of analyzing the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device through a preset sound source feature analysis algorithm to determine the sound field difference data of each microphone unit corresponding to the target sound source, further includes steps 20211-20212, wherein:

[0096] 20211. Determine the sound field direction data and the order of acquisition of target sound source data for each microphone unit in the preset microphone matrix sequence within the first device.

[0097] In this embodiment of the invention, the aforementioned adaptive adjustment system for a sound-generating device based on sound field direction recognition determines the order in which microphone units in a preset microphone matrix sequence receive target sound source data, according to the arrangement and combination of microphone units corresponding to the preset microphone matrix sequence. Furthermore, because the positions of each microphone unit in the preset microphone matrix sequence result in different sensor directions for each microphone unit receiving target sound source data, the final received waveform intensity for target sound source data from the same direction will also be different. Therefore, the sound field direction data of each microphone unit when acquiring target sound source data can be obtained by measuring the difference in waveform intensity.

[0098] 20212. Match the sound field direction data and sequence data of each microphone unit with the preset sound field direction data and sequence data in the sound source feature rules to determine the sound field difference data of each microphone unit.

[0099] In this embodiment of the invention, after the captured audio source data is parsed by the above-mentioned preset audio source feature parsing algorithm, it can be matched with the corresponding audio source feature rules. If a match is found, the channels of the first device can be allocated according to the preset matching rules.

[0100] Specifically, in one possible embodiment, the aforementioned sound-generating device adaptive adjustment system based on sound field direction recognition matches the order in which the microphone units of the first device receive the sound source with the sound field direction data and the order data of each microphone unit according to the preset microphone matrix sequence, thereby determining the sound field difference data of each microphone unit.

[0101] like Figure 8 As shown, this embodiment of the invention also provides an adaptive adjustment device 800 for a sound-generating device based on sound field direction recognition. This adaptive adjustment device for a sound-generating device based on sound field direction recognition includes:

[0102] The acquisition module is used to acquire the target sound source data received by the preset microphone matrix sequence of the current first device;

[0103] The processing module is used to process the target sound source data through a preset sound source feature parsing algorithm to determine sound source feature data, wherein the sound source feature data includes sound field feature data;

[0104] The allocation module is used to allocate at least one channel of the current first device based on the sound source feature data.

[0105] Optionally, the above-mentioned device further includes:

[0106] The first determining module is used to determine the sound source feature parameters of the preset microphone matrix sequence of the first device, wherein the sound source feature parameters include position parameters, direction parameters and / or phase parameters;

[0107] The second determining module is used to determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device based on the position parameters, direction parameters and / or phase parameters.

[0108] Optionally, the above processing module includes:

[0109] The first determining submodule is used to analyze the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device through a preset sound source feature analysis algorithm, and determine the sound field difference data of each microphone unit corresponding to the target sound source.

[0110] Optionally, the above processing module further includes:

[0111] The first matching module is used to perform acoustic matching processing on the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device through a preset acoustic model, and obtain an acoustic matching result.

[0112] The second determining submodule is used to determine the relative setting state data of the target sound source corresponding to the microphone matrix based on the acoustic matching result;

[0113] The third determining submodule is used to determine the wearing status of the first device based on the relative setting status data.

[0114] Optionally, the above allocation module includes:

[0115] The fourth determination submodule is used to determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device;

[0116] The fifth determining submodule is used to match the sound source feature data based on the sound source feature rules to determine the channel allocation strategy of the first device;

[0117] The sixth determining submodule is used to determine the channel allocation strategy of at least the second device based on the channel allocation strategy of the first device.

[0118] Optionally, the first determining submodule mentioned above includes:

[0119] The acquisition unit is used to determine the sound field direction data and the order data of each microphone unit in the preset microphone matrix sequence within the first device when acquiring target sound source data.

[0120] The determining unit is used to match the sound field direction data and sequence data of each microphone unit with the preset sound field direction data and sequence data in the sound source feature rules to determine the sound field difference data of each microphone unit.

[0121] like Figure 9 As shown, this embodiment of the invention also provides an electronic device 900, including a processor, which can execute any of the above-mentioned adaptive adjustment methods for sound-emitting devices based on sound field direction recognition.

[0122] Specifically, it includes a processor 901 and a memory 902, as well as a computer program stored in the memory 902 and capable of running on the processor 901, which executes a sound-generating device adaptive adjustment method based on sound field direction recognition, wherein:

[0123] The processor 901 executes the calculator program stored in the memory 902, which is a sound-generating device adaptive adjustment method based on sound field direction recognition, and performs the following steps:

[0124] Obtain the target sound source data received by the preset microphone matrix sequence of the first device;

[0125] The target sound source data is processed by a preset sound source feature parsing algorithm to determine sound source feature data, which includes sound field feature data.

[0126] Based on the sound source feature data, at least the channels of the current first device are allocated.

[0127] Optionally, before the processor 901 executes the step of acquiring the target sound source data received from the preset microphone matrix sequence of the current first device, it includes:

[0128] Determine the sound source characteristic parameters of the preset microphone matrix sequence of the first device, wherein the sound source characteristic parameters include position parameters, direction parameters and / or phase parameters;

[0129] Based on the position parameters, direction parameters, and / or phase parameters, the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device are determined.

[0130] Optionally, the processor 901 executes the sound field feature data, including sound field difference data. The step of processing the target sound source data using a preset sound source feature parsing algorithm to determine the sound source feature data includes:

[0131] By using a preset sound source feature parsing algorithm, the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device is parsed and processed to determine the sound field difference data of each microphone unit corresponding to the target sound source.

[0132] Optionally, the processor 901 executes the sound field feature data including relative setting state data, and the method further includes processing the target sound source data through a preset sound source feature parsing algorithm to determine the sound source feature data.

[0133] By using a preset acoustic model, acoustic matching processing is performed on the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device to obtain the acoustic matching result;

[0134] Based on the acoustic matching results, the relative setting status data of the microphone matrix corresponding to the target sound source is determined;

[0135] Based on the relative setting status data, the wearing status of the first device is determined.

[0136] Optionally, the processor 901 performs the allocation of channels for the current first device based on the sound source feature data, including:

[0137] Determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device;

[0138] Based on the sound source feature rules, the sound source feature data is matched to determine the channel allocation strategy of the first device;

[0139] Based on the channel allocation strategy of the first device, determine the channel allocation strategy of at least the second device.

[0140] Optionally, the processor 901 further executes the method described above, which uses a preset sound source feature parsing algorithm to parse the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device, and determines the sound field difference data of each microphone unit corresponding to the target sound source, including:

[0141] Determine the sound field direction data and the order data of each microphone unit in the preset microphone matrix sequence within the first device when acquiring target sound source data;

[0142] The sound field direction data and sequence data of each microphone unit are matched with the preset sound field direction data and sequence data in the sound source feature rules to determine the sound field difference data of each microphone unit.

[0143] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the sound-generating device adaptive adjustment method based on sound field direction recognition provided in this invention, or the application-side sound-generating device adaptive adjustment method based on sound field direction recognition, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0144] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be done by a computer program instructing related hardware, and can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0145] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. An adaptive adjustment method for a sound-generating device based on sound field direction recognition, characterized in that, The sound-generating device includes at least a first device, the first device being equipped with a microphone matrix, the microphone matrix including at least three microphone units, the microphone matrix being located in planar space or three-dimensional space, and the method comprising: Obtain the target sound source data received by the preset microphone matrix sequence of the current first device; The target sound source data is processed by a preset sound source feature parsing algorithm to determine sound source feature data, which includes sound field feature data. Based on the sound source feature data, at least the audio channels of the current first device are allocated; Before acquiring the target sound source data received by the preset microphone matrix sequence of the current first device, the following steps are included: Determine the sound source characteristic parameters of the preset microphone matrix sequence of the first device, wherein the sound source characteristic parameters include position parameters, direction parameters and / or phase parameters; Based on the position parameters, direction parameters, and / or phase parameters, determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device; Specifically, based on the specific implementation plan and the current environmental conditions, the preset microphone matrix sequence of the first device is determined, and the above-mentioned sound source feature rules are determined according to the arrangement and combination of microphone units corresponding to the preset microphone matrix sequence. Specifically, the sound source feature rules are determined according to the order in which the microphone units corresponding to the preset microphone matrix sequence of the first device receive the sound source. The order in which different microphone units receive the same sound source is determined by setting the position and direction of the microphone units in different microphone matrix sequences. The corresponding sound source feature rules are obtained by determining the position parameters, direction parameters and / or phase parameters corresponding to different microphone matrix sequences. The phase parameters are processed by algorithms such as delay summation algorithm, frequency domain beamforming algorithm and machine learning-based algorithm to process the signals and sound sources acquired by each microphone in the microphone array, calculate the time difference of sound waves from different sound sources to each microphone unit, and use the time difference to estimate the distance from the sound source to each microphone unit, so as to calculate the order in which each microphone unit receives the sound, thereby determining the phase parameters corresponding to each microphone unit. The sound field feature data includes sound field difference data. The step of processing the target sound source data using a preset sound source feature analysis algorithm to determine the sound source feature data includes: By using a preset sound source feature parsing algorithm, the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device is parsed and processed to determine the sound field difference data of each microphone unit corresponding to the target sound source. The process of allocating audio channels for the current first device based on the sound source feature data includes: Determine the sound source feature rules corresponding to the preset microphone matrix sequence of the current first device; Based on the sound source feature rules, the sound source feature data is matched to determine the channel allocation strategy of the first device; Based on the channel allocation strategy of the first device, determine at least the channel allocation strategy of the second device; The step of parsing the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device using a preset sound source feature parsing algorithm to determine the sound field difference data of each microphone unit corresponding to the target sound source includes: Determine the sound field direction data and the order data of each microphone unit in the preset microphone matrix sequence within the first device when acquiring target sound source data; The sound field direction data and sequence data of each microphone unit are matched with the preset sound field direction data and sequence data in the sound source feature rules to determine the sound field difference data of each microphone unit.

2. The adaptive adjustment method for a sound-generating device based on sound field direction recognition as described in claim 1, characterized in that, The sound field feature data includes relative setting state data. The method further includes processing the target sound source data using a preset sound source feature parsing algorithm to determine the sound source feature data. By using a preset acoustic model, acoustic matching processing is performed on the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device to obtain the acoustic matching result. Based on the acoustic matching results, the relative setting status data of the microphone matrix corresponding to the target sound source is determined; Based on the relative setting status data, the wearing status of the first device is determined.

3. An adaptive adjustment device for a sound-generating device based on sound field direction recognition, characterized in that, The method for adaptive adjustment of a sound-generating device based on sound field direction recognition as described in claim 1 includes: The acquisition module is used to acquire the target sound source data received by the preset microphone matrix sequence of the current first device; The processing module is used to process the target sound source data through a preset sound source feature parsing algorithm to determine sound source feature data, wherein the sound source feature data includes sound field feature data; The allocation module is used to allocate at least one channel of the current first device based on the sound source feature data; The processing module is further configured to: determine the sound source feature parameters of a preset microphone matrix sequence of the first device, wherein the sound source feature parameters include position parameters, direction parameters, and / or phase parameters; determine the sound source feature rules corresponding to the current preset microphone matrix sequence of the first device based on the position parameters, direction parameters, and / or phase parameters; parse and process the target sound source data received by each microphone unit in the preset microphone matrix sequence of the first device using a preset sound source feature parsing algorithm to determine the sound field difference data of the target sound source corresponding to each microphone unit; determine the sound source feature rules corresponding to the current preset microphone matrix sequence of the first device; match the sound source feature data based on the sound source feature rules to determine the channel allocation strategy of the first device; and determine the channel allocation strategy of at least the second device according to the channel allocation strategy of the first device. The allocation module is also used to determine the sound field direction data of each microphone unit in the preset microphone matrix sequence within the first device when acquiring target sound source data, as well as the order data of acquiring target sound source data. The sound field direction data and sequence data of each microphone unit are matched with the preset sound field direction data and sequence data in the sound source feature rules to determine the sound field difference data of each microphone unit.

4. An adaptive adjustment system for a sound-generating device based on sound field direction recognition, characterized in that, The sound-generating device adaptive adjustment system based on sound field direction recognition includes: a sound-generating device adaptive adjustment device based on sound field direction recognition; The adaptive adjustment device for a sound-generating device based on sound field direction recognition is determined by the adaptive adjustment method for a sound-generating device based on sound field direction recognition as shown in claim 1 or 2.

5. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the adaptive adjustment method for a sound-generating device based on sound field direction recognition as described in any one of claims 1 or 2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the adaptive adjustment method for a sound-generating device based on sound field direction recognition as described in any one of claims 1 or 2.

Images