Sound pickup system, sound pickup method and vehicle

Abstract

The present disclosure provides a sound pickup system, a sound pickup method, and a vehicle. The sound pickup system includes: a sound collection group and a processor, and the sound collection group includes at least one sound collection device; the sound collection group is configured to use at least one sound collection device to receive a first audio signal in the vehicle interior space and send the first audio signal to the processor; the processor is configured to perform sound zone division processing on the vehicle interior space according to the relative positions between the vehicle seats and at least one sound collection device, divide the vehicle interior space into at least two sound zones, perform filtering processing on the first audio signal to obtain target audio signals corresponding to the sound zones of at least one sound collection device; wherein any one of the at least two sound zones is the sound zone corresponding to the rear seats. The voices of the rear passengers in the vehicle are recognized through the sound collection devices corresponding to the rear seat sound zones, ensuring that the voices of all passengers in all positions in the vehicle can be recognized. The filtering processing can improve the anti-interference ability of voice control and enhance the experience of the people in the vehicle.

Description

Technical Field

[0001] The present disclosure relates to the field of sound pickup technology, and particularly to a sound pickup system, a sound pickup method and a vehicle. Background Art

[0002] When setting up the vehicle's sound pickup device, usually no sound zone division is performed or only the driver's and front passenger's sound zones in the front row are distinguished. When no sound zone division is performed, after a person in the vehicle wakes up the sound pickup device by voice, the voices of other people can also interfere with the sound pickup device; when only the driver's and front passenger's sound zones in the front row are distinguished, the voices of the passengers sitting in the back row of the vehicle cannot be recognized. The above two situations will affect the experience of the people in the vehicle. Summary of the Invention

[0003] In view of this, the purpose of the present disclosure is to provide a sound pickup system, a sound pickup method and a vehicle to solve the problems in the prior art that the voices of the passengers sitting in the back row of the vehicle cannot be recognized, and the anti-interference ability of voice control is low, affecting the experience of the people in the vehicle.

[0004] Based on the above purpose, the first aspect of the present disclosure provides a sound pickup system, which includes: a sound pickup group and a processor, and the sound pickup group includes at least one sound pickup device;

[0005] The sound pickup group is configured to use the at least one sound pickup device to receive the first audio signal in the vehicle interior space and send the first audio signal to the processor;

[0006] The processor is configured to perform sound zone division processing on the vehicle interior space according to the relative positions between the vehicle seats and the at least one sound pickup device, divide the vehicle interior space into at least two sound zones, and perform filtering processing on the first audio signal to obtain the target audio signal of the sound zone corresponding to the at least one sound pickup device;

[0007] Wherein, any one of the at least two sound zones is the sound zone corresponding to the back row seat.

[0008] In some embodiments, the sound pickup group includes: two sound pickup devices respectively arranged in the front row area and the back row area of the vehicle interior;

[0009] The processor is configured to divide the vehicle interior space into a front row sound zone and a back row sound zone according to the relative positions between the vehicle seats and the two respectively arranged sound pickup devices.

[0010] In some embodiments,

[0011] The sound pickup group includes: a front row sound pickup device arranged at the front position of the middle line of the vehicle interior ceiling, and a back row sound pickup device arranged at the back position of the middle line of the vehicle interior ceiling;

[0012] Alternatively,

[0013] The sound collection group includes: a front-row sound collection device arranged at the front row position of the middle line of the vehicle ceiling, and a rear-row sound collection device arranged at the rear side position of the middle armrest box in the vehicle.

[0014] In some embodiments,

[0015] The sound collection group includes: a front-row sound collection device arranged in front of the front row position of the middle line of the vehicle ceiling, and a rear-row sound collection device arranged behind the rear row position of the middle line of the vehicle ceiling;

[0016] Or,

[0017] The sound collection group includes: a front-row sound collection device arranged in front of the front row position of the middle line of the vehicle ceiling, and a rear-row sound collection device arranged at the rear side position of the middle armrest box in the vehicle;

[0018] Or,

[0019] The sound collection group includes: a front-row sound collection device arranged behind the front row position of the middle line of the vehicle ceiling, and a rear-row sound collection device arranged in front of the rear row position of the middle line of the vehicle ceiling.

[0020] In some embodiments, the sound collection group includes: two sound collection devices arranged in parallel in front of the middle line of the vehicle ceiling;

[0021] The processor is configured to divide the vehicle interior space into a driver's seat sound zone, a passenger seat sound zone, and a rear row sound zone according to the relative positions between the vehicle seats and the two sound collection devices arranged in parallel.

[0022] Based on the same inventive concept, a second aspect of the present disclosure provides a sound collection method applied to the sound collection system described in the first aspect, including:

[0023] The sound collection group uses the at least one sound collection device to receive a first audio signal in the vehicle interior space and sends the first audio signal to the processor;

[0024] The processor performs sound zone division processing on the vehicle interior space according to the relative positions between the vehicle seats and the at least one sound collection device, divides the vehicle interior space into at least two sound zones, and performs filtering processing on the first audio signal to obtain a target audio signal corresponding to the sound zone of the at least one sound collection device;

[0025] Wherein, the at least two sound zones include the sound zone corresponding to the rear row seats.

[0026] In some embodiments, the processor performs sound zone division processing on the vehicle interior space according to the relative positions between the vehicle seats and the at least one sound collection device, and divides the vehicle interior space into at least two sound zones, including:

[0027] The processor executes the following process:

[0028] In response to confirming that two sound collection devices are respectively arranged in the front row area and the rear row area of the vehicle;

[0029] Determine the line segment connecting between the front row seats of the vehicle as the first line segment;

[0030] Determine the line segment connecting between the front row seat of the vehicle and the front row sound collection device as the second line segment;

[0031] Obtain the included angle between the first line segment and the second line segment as the target included angle α;

[0032] In response to confirming that the target included angle α is less than the first included angle threshold of 180°, the sound zone where the seat is located is the front row sound zone;

[0033] Determine the line segment connecting between the rear row seats of the vehicle as the third line segment;

[0034] Determine the line segment connecting between the rear row seat of the vehicle and the rear row sound collection device as the fourth line segment;

[0035] Obtain the included angle between the third line segment and the fourth line segment as the target included angle β;

[0036] In response to confirming that the target included angle β is less than the second included angle threshold of 180°, the sound zone where the seat is located is the rear row sound zone.

[0037] In some embodiments, the processor performs sound zone division processing on the interior space of the vehicle according to the relative positions between the vehicle seats and the at least one sound collection device, and divides the interior space of the vehicle into at least two sound zones, including:

[0038] The processor executes the following process:

[0039] In response to confirming that two sound collection devices are arranged side by side in front of the center line of the vehicle roof;

[0040] Determine the line segment connecting between the two side-by-side arranged sound collection devices as the fifth line segment;

[0041] Determine the line segment connecting between the vehicle seat and the two side-by-side arranged sound collection devices as the sixth line segment;

[0042] Obtain the included angle between the fifth line segment and the sixth line segment as the target included angle θ;

[0043] In response to confirming that the target included angle θ is less than the preset third included angle threshold θ 1 , the sound zone where the seat is located is the driver's seat sound zone;

[0044] In response to confirming that the target angle θ is greater than or equal to a preset fourth angle threshold θ 2 , the sound zone where the seat is located is the co-pilot sound zone;

[0045] In response to confirming that the target angle θ is greater than or equal to the third angle threshold θ 1 and less than the fourth angle threshold θ 2 , the sound zone where the seat is located is the rear row sound zone.

[0046] In some embodiments, it is characterized in that the filtering process of the first audio signal to obtain the target audio signal of the target sound zone where the sound collection group is located includes:

[0047] The processor executes the following process:

[0048] Performing echo cancellation processing on the first audio signal through a neural network algorithm to obtain a second audio signal;

[0049] Performing signal recognition processing on the second audio signal through a combination of beamforming and blind source separation to determine a third audio signal in the target sound zone where the first audio signal is located;

[0050] Performing noise suppression processing on the third audio signal through Wiener filtering, and waking up the third audio signal after noise suppression processing through a wake-up function to obtain the target audio signal of the target sound zone where the sound collection group is located.

[0051] Based on the same inventive concept, a third aspect of the present disclosure provides a vehicle, including the sound pickup system of the first aspect.

[0052] As can be seen from the above, a sound pickup system, a sound pickup method and a vehicle provided by the present disclosure, the sound collection group sends the received first audio signal to the processor; the processor divides the in-vehicle space into sound zones according to the relative position between the vehicle seat and the sound pickup device, divides the in-vehicle space into at least two sound zones, and at least two divided sound zones include the sound zone corresponding to the rear seat. Therefore, the voices of the rear row passengers in the vehicle can be recognized through the sound pickup device corresponding to the rear seat sound zone, ensuring that the voices of all passengers in all positions on the vehicle can be recognized, and improving the experience of the passengers on the vehicle. Filtering the first audio signal to obtain the target audio signal of the sound zone corresponding to at least one sound pickup device. When the sound pickup device receives audio signals from multiple sound zones, through filtering processing, the intensity of the audio signal of the sound zone corresponding to this sound pickup device is increased, and the intensity of the audio signals of other sound zones is suppressed, which can improve the anti-interference ability of voice control and improve the experience of the passengers on the vehicle. Description of the Drawings

[0053] To more clearly illustrate the technical solutions in the present disclosure or related technologies, the following will briefly introduce the drawings required for use in the embodiments or descriptions of related technologies. Obviously, the drawings in the following description are only the embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0054] Figure 1 Structural schematic diagram of a sound pickup system in the related technology of the embodiments of the present disclosure;

[0055] Figure 2 Structural schematic diagram of the sound pickup system of the embodiments of the present disclosure;

[0056] Figure 3 Structural schematic diagram of the first sound pickup system of the embodiments of the present disclosure;

[0057] Figure 4 Structural schematic diagram of the second sound pickup system of the embodiments of the present disclosure;

[0058] Figure 5 Structural schematic diagram of the third sound pickup system of the embodiments of the present disclosure;

[0059] Figure 6 Structural schematic diagram of the fourth sound pickup system of the embodiments of the present disclosure;

[0060] Figure 7 Flowchart of the sound pickup method of the embodiments of the present disclosure;

[0061] Figure 8 Schematic diagram of beamforming of the embodiments of the present disclosure;

[0062] Figure 9 Flowchart of the audio signal processing method of the embodiments of the present disclosure.

[0063] Explanation of reference numerals:

[0064] 1. Sound collection group, 11. Sound collection device, 12. Sound collection device;

[0065] 2. Processor;

[0066] 3. Sound area, 31. Front row sound area, 311. Driver's seat sound area, 312. Passenger seat sound area, 32. Rear row sound area;

[0067] 4. Suppression area. Detailed implementation manners

[0068] To make the objectives, technical solutions, and advantages of the present disclosure clearer and more understandable, the following further elaborates on the present disclosure in detail with reference to specific embodiments and the accompanying drawings.

[0069] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meanings understood by those of ordinary skill in the art to which the present disclosure pertains. The "first", "second" and similar terms used in the embodiments of the present disclosure do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right", etc. are only used to indicate relative position relationships, and when the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0070] As Figure 1 shown, Figure 1 is a schematic structural diagram of a sound pickup system in the related art. Figure 1 It includes a sound collection group, a sound zone, and a rear row suppression zone. Among them, the sound collection group includes a first sound collection device and a second sound collection device arranged in parallel in the middle area between the driver's seat and the passenger seat in the front row of the vehicle; the sound zone includes a driver's seat sound zone and a passenger seat sound zone. The processor divides the vehicle interior space into a driver's seat sound zone and a passenger seat sound zone by partitioning the sound zone of the vehicle interior space. The first sound collection device recognizes the voices of the people in the driver's seat sound zone space; the second sound collection device recognizes the voices of the people in the passenger seat sound zone space. However, neither the first sound collection device nor the second sound collection device can recognize the voices of the people in the rear row suppression zone position. Since the people in the rear row cannot control the vehicle through voice, it affects the experience of the rear row people.

[0071] In addition, the related art also includes not partitioning the sound zone of the vehicle interior space. When the sound zone of the vehicle interior space is not partitioned, after a person in the vehicle wakes up the sound collection device, the voices of other people in the vehicle will also be recognized by the awakened sound collection device. The anti-interference ability of voice control is poor, and the misrecognition rate is high, which affects the experience of the people in the vehicle.

[0072] As described above, how to achieve voice recognition for the entire cockpit at a relatively low cost, improve the anti-interference ability of voice control, and improve the experience of the people in the vehicle has become an important research issue.

[0073] As Figure 2 shown, Figure 2 is a schematic structural diagram of a sound pickup system. An embodiment of the present disclosure provides a sound pickup system, the sound pickup system includes: a sound collection group 1 and a processor 2, the sound collection group 1 includes at least one sound collection device (such as Figure 3 , Figure 4 , Figure 5and Figure 6 as shown, the sound receiving device 11 or the sound receiving device 12);

[0074] such as Figure 3 , Figure 4 , Figure 5 and Figure 6 as shown, the sound receiving group 1 is configured to receive a first audio signal in the vehicle interior space by using the at least one sound receiving device (the sound receiving device 11 or the sound receiving device 12), and send the first audio signal to the processor 2; the processor 2 is configured to perform sound zone division processing on the vehicle interior space according to the relative position between the vehicle seat and the at least one sound receiving device (the sound receiving device 11 or the sound receiving device 12), divide the vehicle interior space into at least two sound zones (the front row sound zone 31 and the rear row sound zone 32), perform filtering processing on the first audio signal, and obtain a target audio signal of the sound zone (the front row sound zone 31 or the rear row sound zone 32) corresponding to the at least one sound receiving device; wherein, any one of the at least two sound zones is a sound zone (the rear row sound zone 32) corresponding to the rear seat.

[0075] In the above solution, as Figure 3 , Figure 4 , Figure 5 and Figure 6 as shown, the sound receiving group 1 includes the sound receiving device 11 and the sound receiving device 12; the sound zone 3 includes the front row sound zone 31 and the rear row sound zone 32, wherein, Figure 6 the front row sound zone 31 further includes a driver's seat sound zone 311 and a passenger seat sound zone 312. Wherein, the sound receiving device may be a microphone.

[0076] During the sound pickup process, the sound receiving device 11 or the sound receiving device 12 will receive a first audio signal in the vehicle interior space. The processor 2 will perform sound zone division processing on the vehicle interior space according to the relative position between the vehicle seat and the sound receiving device 11 or the sound receiving device 12, and divide the vehicle interior space into at least two sound zones (for example, the front row sound zone 31 and the rear row sound zone 32). Wherein, the processor 2 can divide the vehicle interior space into sound zones by constructing a target included angle, or can also be divided according to the relative distance between the vehicle seat and the sound receiving device 11 or the sound receiving device 12.

[0077] Perform filtering processing on the first audio signal to obtain a target audio signal of the sound zone corresponding to the at least one sound receiving device. Wherein, the first audio signal includes an audio signal of the front row sound zone 31 and an audio signal of the rear row sound zone 32.

[0078] For example, when the sound receiving device 11 or the sound receiving device 12 corresponding to the rear sound zone 32 simultaneously receives the audio signal of the front sound zone 31 and the audio signal of the rear sound zone 32, the sound receiving device 11 or the sound receiving device 12 will filter the received first audio signal, filter out the audio signal of the front sound zone 31, and obtain the audio signal of the rear sound zone 32. The audio signal processing process of the sound receiving device 11 or 12 corresponding to the front sound zone is similar to the above process and will not be repeated here.

[0079] Through the above scheme, the processor 2 performs sound zone division processing on the interior space of the vehicle according to the relative position between the vehicle seat and the at least one sound receiving device (sound receiving device 11 or sound receiving device 12), and the at least two sound zones obtained by dividing the interior space of the vehicle include the rear sound zone 32. Therefore, the sound receiving device (sound receiving device 11 or sound receiving device 12) corresponding to the rear sound zone can recognize the voice of the rear-seat passengers in the vehicle, so that the rear-seat passengers can control the vehicle through voice, thereby improving the experience of the rear-seat passengers in the vehicle. In addition, the processor 2 obtains the target audio signal of the sound zone corresponding to the sound receiving device by filtering the first audio signal, and filters out the audio signals of other sound zones, thereby reducing the interference of the audio signals of other sound zones, improving the anti-interference ability of voice control, and improving the experience of the passengers in the vehicle.

[0080] In some embodiments, the sound receiving group 1 includes: two sound receiving devices (such as Figure 3 , Figure 4 and Figure 5 As shown, the sound receiving device 11 and the sound receiving device 12); the processor 2 is configured to receive the sound from the vehicle seat and the two separately arranged sound receiving devices (such as Figure 3 , Figure 4 and Figure 5 As shown, the relative positions of the sound receiving devices 11 and 12 divide the interior space of the vehicle into the front sound zone 31 (such as Figure 3 , Figure 4 and Figure 5 ) and the rear sound zone 32 (as shown Figure 3 , Figure 4 and Figure 5 shown).

[0081] In the above scheme, if Figure 3 , Figure 4 and Figure 5 As shown, the sound receiving group 1 includes a sound receiving device 11 and a sound receiving device 12; the sound zone 3 includes a front row sound zone 31 and a rear row sound zone 32. The sound receiving device 11 can also be called a front row sound receiving device 11, which is arranged in the front row area of ​​the vehicle; the sound receiving device 12 can also be called a rear row sound receiving device 12, which is arranged in the rear row area of ​​the vehicle.

[0082] The first audio signal received by the front row sound collection device 11 is mainly the audio signal in the front row sound area 31. When the front row sound collection device 11 simultaneously receives the audio signals in the front row sound area 31 and the rear row sound area 32, the processor 2 filters out the audio signal in the rear row sound area 32 through filtering processing to obtain the audio signal in the front row sound area 31. Therefore, the front row sound collection device 11 can improve the intensity of the audio signal in the front row sound area 31 and enhance the anti-interference ability of voice control. Correspondingly, the processing process of the rear row sound collection device 21 for the first audio signal is similar to the above process and will not be elaborated here.

[0083] Through the above solution, the sound collection device corresponding to the rear row sound area (sound collection device 12) can recognize the voices of the rear row passengers in the vehicle, enabling the rear row passengers to control the vehicle through voice and enhancing the experience of the rear row passengers in the vehicle.

[0084] In some embodiments,

[0085] The sound collection group 1 includes: a front row sound collection device 11 (such as shown in Figure 3 、 Figure 4 and Figure 5 ) arranged at the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device 12 (such as shown in Figure 3 and Figure 5 ) arranged at the rear position of the middle line of the vehicle interior ceiling; or, the sound collection group 1 includes: a front row sound collection device 11 (such as shown in Figure 3 、 Figure 4 and Figure 5 ) arranged at the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device 12 (such as shown in Figure 4 ) arranged at the rear side position of the middle armrest box inside the vehicle.

[0086] In the above solution, as shown in Figure 3 、 Figure 4 and Figure 5 , the sound collection group 1 includes a sound collection device 11 and a sound collection device 12; the sound area 3 includes a front row sound area 31 and a rear row sound area 32. Among them, the sound collection device 11 can also be referred to as the front row sound collection device 11 and is arranged at the front position of the middle line of the vehicle interior ceiling; the sound collection device 12 can also be referred to as the rear row sound collection device 12 and is arranged at the rear position of the middle line of the vehicle interior ceiling or the rear side position of the middle armrest box inside the vehicle.

[0087] The first audio signal received by the front-row sound collection device 11 is mainly the audio signal in the front-row sound area 31. When the front-row sound collection device 11 simultaneously receives the audio signals in the front-row sound area 31 and the rear-row sound area 32, the processor 2 filters out the audio signal in the rear-row sound area 32 through filtering processing to obtain the audio signal in the front-row sound area 31. Therefore, the front-row sound collection device 11 can improve the intensity of the audio signal in the front-row sound area 31 and enhance the anti-interference ability of voice control. Correspondingly, the processing process of the rear-row sound collection device 12 for the first audio signal is similar to the above process and will not be elaborated here.

[0088] Through the above solution, the positions of the sound collection device 11 and the sound collection device 12 are further determined. Each sound collection device identifies the voice in the corresponding sound area. The sound collection device 11 corresponding to the front-row sound area 31 can identify the voices of the front-row passengers in the vehicle, and the sound collection device 12 corresponding to the rear-row sound area 32 can identify the voices of the rear-row passengers in the vehicle. The rear-row passengers in the vehicle can also control the vehicle through voice, improving the experience of the rear-row passengers in the vehicle.

[0089] In some embodiments,

[0090] The sound collection group 1 includes: a front-row sound collection device 11 (as shown in Figure 3 ), which is arranged at the front of the middle line of the vehicle ceiling in the front row, and a rear-row sound collection device 12 (as shown in Figure 3 ), which is arranged at the rear of the middle line of the vehicle ceiling in the rear row; or, the sound collection group 1 includes: a front-row sound collection device 11 (as shown in Figure 4 ), which is arranged at the front of the middle line of the vehicle ceiling in the front row, and a rear-row sound collection device 12 (as shown in Figure 4 ), which is arranged at the rear side of the middle armrest box in the vehicle; or, the sound collection group 1 includes: a front-row sound collection device 11 (as shown in Figure 5 ), which is arranged at the rear of the middle line of the vehicle ceiling in the front row, and a rear-row sound collection device 12 (as shown in Figure 5 ), which is arranged at the front of the middle line of the vehicle ceiling in the rear row.

[0091] In the above solution, as shown in Figure 3 , the sound collection group 1 includes the sound collection device 11 and the sound collection device 12; the sound area 3 includes the front-row sound area 31 and the rear-row sound area 32. Among them, the sound collection device 11 can also be called the front-row sound collection device 11 and is arranged at the front of the middle line of the vehicle ceiling in the front row; the sound collection device 12 can also be called the rear-row sound collection device 12 and is arranged at the rear of the middle line of the vehicle ceiling in the rear row.

[0092] As shown in Figure 4As shown in the figure, the radio group 1 includes a radio device 11 and a radio device 12; the sound area 3 includes a front row sound area 31 and a rear row sound area 32. Among them, the radio device 11 can also be called the front row radio device 11 and is set at the front position in front of the middle line of the vehicle ceiling; the radio device 12 can also be called the rear row radio device 12 and is set at the rear position of the middle armrest box in the vehicle.

[0093] As Figure 5 shown in the figure, the radio group 1 includes a radio device 11 and a radio device 12; the sound area 3 includes a front row sound area 31 and a rear row sound area 32. Among them, the radio device 11 can also be called the front row radio device 11 and is set at the rear position in front of the middle line of the vehicle ceiling; the radio device 12 can also be called the rear row radio device 12 and is set at the front position in the rear row of the vehicle ceiling middle line.

[0094] The first audio signal received by the front row radio device 11 is mainly the audio signal in the front row sound area 31. When the front row radio device 11 simultaneously receives the audio signals in the front row sound area 31 and the rear row sound area 32, the processor 2 filters out the audio signal in the rear row sound area 32 through filtering processing to obtain the audio signal in the front row sound area 31. Therefore, the front row radio device 11 can improve the intensity of the audio signal in the front row sound area 31 and improve the anti-interference ability of voice control. Correspondingly, the processing process of the rear row radio device 12 for the first audio signal is similar to the above process and will not be elaborated here.

[0095] Through the above solution, the positions of the radio device 11 and the radio device 12 are further determined. Each radio device identifies the voice of the corresponding sound area. The radio device 11 corresponding to the front row sound area 31 can identify the voices of the front row passengers in the vehicle, and the radio device 12 corresponding to the rear row sound area 32 can identify the voices of the rear row passengers in the vehicle. The rear row passengers in the vehicle can also control the vehicle through voice, improving the experience of the rear row passengers in the vehicle.

[0096] In some embodiments, the radio group 1 includes: two radio devices arranged in parallel in front of the middle line of the vehicle ceiling (as Figure 6 shown, the radio device 11 and the radio device 12); the processor 2 is configured to divide the vehicle interior space into a driver's seat sound area 311 (as Figure 6 shown), a co-driver's seat sound area 312 (as Figure 6 shown) and a rear row sound area 32 (as Figure 6 shown) according to the relative positions between the vehicle seats and the two radio devices arranged in parallel (as Figure 6 shown, the radio device 11 and the radio device 12).

[0097] In the above solution, as Figure 6As shown in the figure, the radio group 1 includes a radio device 11 and a radio device 12; the sound area 3 includes a front-row sound area 31 and a rear-row sound area 32, and the front-row sound area 31 includes a driver's sound area 311 and a co-driver's sound area 312. Among them, the radio device 11 and the radio device 12 are arranged in parallel in front of the midline of the vehicle ceiling.

[0098] The processor 2 can construct a target angle with the two radio devices arranged in parallel (radio device 11 and radio device 12) through the vehicle seat, compare the target angle with a preset angle threshold, and divide the vehicle interior space into a driver's sound area 311, a co-driver's sound area 312, and a rear-row sound area 32.

[0099] The first audio signal received by the radio device 11 is mainly the audio signal in the driver's sound area 311. When the radio device 11 receives the audio signals in both the driver's sound area 311 and the co-driver's sound area 312 at the same time, the processor 2 filters out the audio signal in the co-driver's sound area 312 through filtering processing to obtain the audio signal in the driver's sound area 311. Therefore, the radio device 11 can improve the intensity of the audio signal in the driver's sound area 311 and enhance the anti-interference ability of voice control. Correspondingly, the processing process of the radio device 21 for the first audio signal is similar to the above process and will not be elaborated here.

[0100] Both the radio device 11 and the radio device 12 can identify the audio signal in the rear-row sound area 32 and obtain the target audio signal in the rear-row sound area 32 through filtering processing.

[0101] Through the above solution, the vehicle interior space is divided into a driver's sound area 311, a co-driver's sound area 312, and a rear-row sound area 32, making the sound area division more refined. At the same time, the anti-interference ability of voice control is further improved, enhancing the experience of the people in the vehicle.

[0102] Through the above embodiments, the radio group sends the received first audio signal to the processor; the processor divides the vehicle interior space into sound areas according to the relative position between the vehicle seat and the radio device, dividing the vehicle interior space into at least two sound areas, and at least two of the divided sound areas include the sound area corresponding to the rear seat. Therefore, the voice of the rear passengers in the vehicle can be recognized through the radio device corresponding to the rear seat sound area, ensuring that the voices of all passengers in the vehicle can be recognized and enhancing the experience of the people in the vehicle. Filter the first audio signal to obtain the target audio signal of the sound area corresponding to at least one radio device. When the radio device receives the audio signals of multiple sound areas, through filtering processing, the intensity of the audio signal of the sound area corresponding to the radio device is increased, and the intensity of the audio signals of other sound areas is suppressed, which can improve the anti-interference ability of voice control and enhance the experience of the people in the vehicle.

[0103] Based on the same inventive concept, an embodiment of the present disclosure provides a sound pickup method applied to the sound pickup systems described in the above respective embodiments.

[0104] As Figure 7 shown, the steps performed by the method include:

[0105] Step 101, the sound collection group uses the at least one sound pickup device to receive a first audio signal in the vehicle interior space, and sends the first audio signal to the processor.

[0106] Step 102, the processor performs sound zone division processing on the vehicle interior space according to the relative positions between the vehicle seats and the at least one sound pickup device, divides the vehicle interior space into at least two sound zones, and performs filtering processing on the first audio signal to obtain target audio signals corresponding to the sound zones of the at least one sound pickup device.

[0107] Among them, the at least two sound zones include the sound zone corresponding to the rear seats.

[0108] In specific implementation, the processor performs sound zone division processing on the vehicle interior space to divide it into at least two sound zones. The processor receives the first audio signal sent by the sound pickup device, and performs filtering processing on the first audio signal to obtain the target audio signal corresponding to the sound zone of this sound pickup device.

[0109] Through the above solution, among the at least two sound zones divided by the processor, there is a rear sound zone. Therefore, the voices of the rear passengers in the vehicle can also be recognized by the sound pickup device, and the rear passengers can control the vehicle through voice, providing a good experience for the rear passengers in the vehicle. At the same time, the processor performs filtering processing on the first audio signal sent by the sound pickup device, which can enhance the target audio signal corresponding to the sound zone of this sound pickup device, filter out the audio signals of other sound zones, improve the anti-interference ability of voice control, and improve the experience of the people in the vehicle.

[0110] In some embodiments, step 102 includes:

[0111] The processor performs the following process:

[0112] Step 1021, in response to confirming that two sound pickup devices are respectively arranged in the front area and the rear area of the vehicle interior.

[0113] Step 1022, determine the line segment connecting the front seats of the vehicle as the first line segment.

[0114] Step 1023, determine the line segment connecting the front seats of the vehicle and the front sound pickup device as the second line segment.

[0115] Step 1024, obtain the included angle between the first line segment and the second line segment as the target included angle α.

[0116] Step 1025, in response to confirming that the target angle α is less than the first angle threshold of 180°, the sound zone where the seat is located is the front-row sound zone.

[0117] Step 1026, determine the line segment connecting the rear seats of the vehicle as the third line segment.

[0118] Step 1027, determine the line segment connecting the rear seats of the vehicle and the rear audio collection device as the fourth line segment.

[0119] Step 1028, obtain the angle between the third line segment and the fourth line segment as the target angle β.

[0120] Step 1029, in response to confirming that the target angle β is less than the second angle threshold of 180°, the sound zone where the seat is located is the rear-row sound zone.

[0121] In specific implementation, when the in-vehicle audio collection device is set as Figure 3 and Figure 4 , Figure 5 as shown, the process of dividing the in-vehicle space into sound zones is as follows:

[0122] Construct the target angle between the front-row audio collection device and the front seats of the vehicle. The line segment between the front-row audio collection device and the front seats and the line segment between the front seats form the target angle α. When the target angle α is less than the first angle threshold of 180°, the sound zone where the seat is located is the front-row sound zone. Similarly, the process of dividing the rear-row sound zone is similar to that of the front-row sound zone and will not be elaborated here.

[0123] Through the above solution, when the two audio collection devices are respectively set in the front-row area and the rear-row area of the vehicle, the in-vehicle space is divided by constructing the target angle, making the sound zone division more accurate, so that the audio collection device can accurately obtain the audio signals of the corresponding sound zones.

[0124] In some embodiments, step 102 includes:

[0125] The processor executes the following process:

[0126] Step 102A, in response to confirming that the two audio collection devices are arranged side by side in front of the midline of the vehicle roof.

[0127] Step 102B, determine the line segment connecting the two side-by-side arranged audio collection devices as the fifth line segment.

[0128] Step 102C, determine the line segment connecting the vehicle seats and the two side-by-side arranged audio collection devices as the sixth line segment.

[0129] Step 102D, obtain the angle between the fifth line segment and the sixth line segment as the target angle θ.

[0130] Step 102E, in response to confirming that the target angle θ is less than a preset third angle threshold θ 1 , the sound zone where the seat is located is the driver's sound zone.

[0131] Step 102F, in response to confirming that the target angle θ is greater than or equal to a preset fourth angle threshold θ 2 , the sound zone where the seat is located is the passenger's sound zone.

[0132] Step 102G, in response to confirming that the target angle θ is greater than or equal to the third angle threshold θ 1 and less than the fourth angle threshold θ 2 , the sound zone where the seat is located is the rear row sound zone.

[0133] In specific implementation, when the in-vehicle sound collection device is set as Figure 6 shown, the process of dividing the in-vehicle space into sound zones is as follows:

[0134] As Figure 8 shown, a target angle θ between the sound collection device and the vehicle seat is constructed. Figure 8 Among them, the target angle θ is the angle formed by the line segment between the sound collection device and the vehicle seat and the line segments of the two sound collection devices. When the target angle θ is less than the third angle threshold θ 1 , the sound zone where the seat is located is the driver's sound zone; when the target angle θ is greater than or equal to the fourth angle threshold θ 2 , the sound zone where the seat is located is the passenger's sound zone; when the target angle θ is greater than or equal to the third angle threshold θ 1 and less than the fourth angle threshold θ 2 , the sound zone where the seat is located is the rear row sound zone.

[0135] Through the above solution, when the two sound collection devices are arranged in parallel in front of the midline of the in-vehicle ceiling, the in-vehicle space is divided by constructing the target angle, making the sound zone division more accurate, so that the sound collection device can accurately obtain the audio signals of the corresponding sound zones.

[0136] In some embodiments, Step 102 includes:

[0137] The processor executes the following process:

[0138] Step 102a, perform echo cancellation processing on the first audio signal through a neural network algorithm to obtain a second audio signal.

[0139] Step 102b, perform signal recognition processing on the second audio signal through a combination of beamforming and blind source separation to determine a third audio signal in the target sound zone where the first audio signal is located.

[0140] Step 102c, perform noise suppression processing on the third audio signal through Wiener filtering, and perform wake-up processing on the third audio signal after noise suppression processing through a wake-up function to obtain the target audio signal of the target sound area where the sound collection group is located.

[0141] During specific implementation, as Figure 9 shown, after the sound collection device receives the first audio signal, it sends the first audio signal to the processor. The processor performs echo suppression processing on the received first audio signal through a neural network-based echo cancellation method (Neural Network-Acoustic Echo Cancelation, abbreviated as NN-AEC) to obtain a second audio signal; performs signal recognition processing on the second audio signal through beamforming (Beam Form, abbreviated as BF) and blind source separation (Blind Signal Separation, abbreviated as BSS), determines the target sound area where the sound collection device is located through beamforming, and identifies and separates the third audio signal in the target sound area from the second audio signal through blind source separation; performs noise suppression processing on the third audio signal through Wiener filtering in noise suppression (Noise Suppression, abbreviated as NS), and performs wake-up processing on the third audio signal after noise suppression processing through a wake-up function (Wake Up World, abbreviated as WUW) to obtain the target audio signal of the target sound area where the sound collection group is located.

[0142] Through the above solution, for the neural network-based echo cancellation method, by combining the neural network-based echo cancellation method, since the neural network can continuously improve the echo cancellation method according to the echo cancellation effect, the effect of eliminating echoes from audio signals can be improved. By combining beamforming and blind source separation, the accuracy of separating audio signals in different sound areas is improved, and the audio signal of the corresponding target sound area is accurately obtained. Through further processing of the audio signal by noise suppression and wake-up function, the intensity of the target sound area audio signal is higher than that of the audio signals in other sound areas.

[0143] Through the above embodiments, the sound collection group sends the received first audio signal to the processor; the processor divides the in-vehicle space into sound zones according to the relative position between the vehicle seat and the sound collection device, divides the in-vehicle space into at least two sound zones, and at least two of the divided sound zones include the sound zone corresponding to the rear seat. Therefore, the voices of the rear passengers in the vehicle can be recognized through the sound collection device corresponding to the rear seat sound zone, ensuring that the voices of all passengers in all positions in the vehicle can be recognized and improving the experience of the passengers in the vehicle. The first audio signal is filtered to obtain the target audio signal of the sound zone corresponding to the at least one sound collection device. When the sound collection device receives the audio signals of multiple sound zones, through filtering, the intensity of the audio signal of the sound zone corresponding to the sound collection device is increased, and the intensity of the audio signals of other sound zones is suppressed, which can improve the anti-interference ability of voice control and improve the experience of the passengers in the vehicle.

[0144] It should be noted that the method of the embodiment of the present application can be executed by a single device, such as a mobile phone, a wearable device, a computer or a server, etc. The method of this embodiment can also be applied to a distributed scenario and completed by the cooperation of multiple devices. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiment of the present application, and these multiple devices will interact with each other to complete the described method.

[0145] It should be noted that some embodiments of the present application are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the above embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0146] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of brevity.

[0147] Additionally, for simplicity of explanation and discussion, and so as not to render the embodiments of the present disclosure difficult to understand, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid rendering the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that details regarding the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be fully within the understanding of those of ordinary skill in the art). In cases where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those of ordinary skill in the art that the embodiments of the present disclosure may be practiced without these specific details or with variations of these specific details. Accordingly, these descriptions are to be regarded as illustrative rather than restrictive.

[0148] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0149] Embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A sound pickup system, characterized in that, the sound pickup system includes: a sound collection group and a processor, and the sound collection group includes at least one sound collection device; the sound collection group is configured to use the at least one sound collection device to receive a first audio signal in the vehicle interior space and send the first audio signal to the processor; the processor is configured to perform sound zone division processing on the vehicle interior space according to the relative position between the vehicle seat and the at least one sound collection device, divide the vehicle interior space into at least two sound zones, and perform filtering processing on the first audio signal to obtain a target audio signal corresponding to the sound zone of the at least one sound collection device; wherein any one of the at least two sound zones is a sound zone corresponding to the rear seat.

2. The system according to claim 1, characterized in that, the sound collection group includes: two sound collection devices respectively arranged in the front row area and the rear row area of the vehicle interior; the processor is configured to divide the vehicle interior space into a front row sound zone and a rear row sound zone according to the relative position between the vehicle seat and the two respectively arranged sound collection devices.

3. The system according to claim 2, characterized in that, the sound collection group includes: a front row sound collection device arranged at the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device arranged at the rear position of the middle line of the vehicle interior ceiling; or, the sound collection group includes: a front row sound collection device arranged at the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device arranged at the rear side position of the vehicle interior middle armrest box.

4. The system according to claim 3, characterized in that, the sound collection group includes: a front row sound collection device arranged in front of the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device arranged behind the rear position of the middle line of the vehicle interior ceiling; or, the sound collection group includes: a front row sound collection device arranged in front of the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device arranged at the rear side position of the vehicle interior middle armrest box; or, the sound collection group includes: a front row sound collection device arranged behind the front position of the middle line of the vehicle interior ceiling, and a rear row sound collection device arranged in front of the rear position of the middle line of the vehicle interior ceiling.

5. The system according to claim 1, characterized in that, the sound collection group includes: two sound collection devices arranged in parallel in front of the middle line of the vehicle interior ceiling; the processor is configured to divide the vehicle interior space into a driver's seat sound zone, a passenger seat sound zone and a rear row sound zone according to the relative position between the vehicle seat and the two sound collection devices arranged in parallel.

6. A sound pickup method, characterized in that, the method is applied to the sound pickup system according to any one of claims 1-5, and the method includes: the sound collection group uses the at least one sound collection device to receive a first audio signal in the vehicle interior space and sends the first audio signal to the processor; the processor performs sound zone division processing on the vehicle interior space according to the relative position between the vehicle seat and the at least one sound collection device, divides the vehicle interior space into at least two sound zones, and performs filtering processing on the first audio signal to obtain a target audio signal corresponding to the sound zone of the at least one sound collection device; wherein the at least two sound zones include a sound zone corresponding to the rear seat.

7. The method according to claim 6, wherein, the processor performs sound zone division processing on the in-vehicle space according to the relative position between the vehicle seat and the at least one sound collection device, and divides the in-vehicle space into at least two sound zones, including: the processor executes the following process: in response to confirming that two sound collection devices are respectively arranged in the front row area and the rear row area of the vehicle; determining the line segment connecting the front row seats of the vehicle as the first line segment; determining the line segment connecting the front row seats of the vehicle and the front row sound collection device as the second line segment; obtaining the included angle between the first line segment and the second line segment as the target included angle α; in response to confirming that the target included angle α is less than the first included angle threshold of 180°, the sound zone where the seat is located is the front row sound zone; determining the line segment connecting the rear row seats of the vehicle as the third line segment; determining the line segment connecting the rear row seats of the vehicle and the rear row sound collection device as the fourth line segment; obtaining the included angle between the third line segment and the fourth line segment as the target included angle β; in response to confirming that the target included angle β is less than the second included angle threshold of 180°, the sound zone where the seat is located is the rear row sound zone.

8. The method according to claim 6, wherein, the processor performs sound zone division processing on the in-vehicle space according to the relative position between the vehicle seat and the at least one sound collection device, and divides the in-vehicle space into at least two sound zones, including: the processor executes the following process: in response to confirming that two sound collection devices are arranged side by side in front of the midline of the vehicle roof; determining the line segment connecting the two sound collection devices arranged side by side as the fifth line segment; determining the line segment connecting the vehicle seat and the two sound collection devices arranged side by side as the sixth line segment; obtaining the included angle between the fifth line segment and the sixth line segment as the target included angle θ; In response to confirming that the target included angle θ is less than a preset third included angle threshold θ 1 , the sound zone where the seat is located is the main driver sound zone; In response to confirming that the target included angle θ is greater than or equal to a preset fourth included angle threshold θ 2 , the sound zone where the seat is located is the co-pilot sound zone; in response to confirming that the target angle θ is greater than or equal to the third angle threshold θ 1 and less than the fourth angle threshold θ 2 , the sound zone where the seat is located is the rear sound zone.

9. The method according to claim 6, wherein, the filtering process of the first audio signal to obtain the target audio signal of the sound zone corresponding to the at least one sound collection device includes: the processor executes the following process: performing echo cancellation processing on the first audio signal through a neural network algorithm to obtain a second audio signal; performing signal recognition processing on the second audio signal through a combination of beamforming and blind source separation to determine the third audio signal in the target sound zone where the first audio signal is located; performing noise suppression processing on the third audio signal through Wiener filtering, and waking up the third audio signal after noise suppression processing through a wake-up function to obtain the target audio signal of the target sound zone where the sound collection group is located.

10. A vehicle, wherein, it includes the sound pickup system according to any one of claims 1-5.

Images