Voice masking method, apparatus, and system, and vehicle
Patent Information
- Application Number
- MYPI2025006353
- Authority / Receiving Office
- MY · MY
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-14
- Publication Date
- 2024-10-14
AI Technical Summary
In smart vehicle cockpits, passengers' voice communication content is easily known by other passengers or drivers, leading to privacy leakage issues.
By determining the voice source position and the target masking position, receiving the voice signal and detecting whether there is a voice signal, generating a masking sound based on the detection results, and outputting it to the speech source position and the target masking position through the speaker to ensure that passengers at the target masking position cannot hear it. Understand or hear the voice content clearly, while avoiding interference with the location of the voice source when there is no voice input.
It realizes private voice communication in the vehicle cockpit, protects the privacy of passengers, avoids information leakage, and improves information security.
Smart Images

Figure PI2025006353_DRAWING_001 
Figure PI2025006353_DRAWING_002 
Figure PI2025006353_DRAWING_003
Abstract
Description
Voice masking method, device, system and vehicle Technical Field
[0001] The present application relates to the field of smart cars, and in particular to a cockpit voice masking method, device, system and vehicle. Background Art
[0002] With the development of intelligent vehicles, the smart cockpit, as an independent space, has created a need for privacy protection for voice communications within the cockpit, both for the driver and passengers. For example, in a business scenario, two parties may be conversing in the back seat of the cockpit, but they don't want the driver or passengers in the front seat to know their conversation. Alternatively, a driver may be talking to someone but may not want other passengers to know the conversation. In these scenarios, preventing privacy or information leakage caused by passengers' voices has become a problem that needs to be solved.
[0003] Summary of the Invention
[0004] The present application provides a voice masking method, device, system and vehicle to meet the needs of passengers for private voice communication in the vehicle cabin space and improve information security.
[0005] In a first aspect, the present application provides a speech masking method for use in a vehicle. The method comprises:
[0006] Determine a speech source position and a target masking position; receive a sound signal from the speech source position, detect whether a speech signal exists in the sound signal, and generate a detection result; if the detection result is that a speech signal exists in the sound signal, generate a masking sound for the speech signal, and output the masking sound to a first speaker at the speech source position and a second speaker at the target masking position; if the detection result is that no speech signal exists in the sound signal, do not generate a masking sound.
[0007] Based on this solution, when masking a speech signal is needed, the masking sound can be output to the speaker at the target masking location, preventing passengers at the target masking location from understanding or clearly hearing the speech originating from the speech source, thereby protecting the privacy of passengers at the speech source location. Furthermore, this solution detects the sound signal originating from the speech source location and controls the generation of the masking sound based on the detection results. This effectively prevents the masking sound from causing continuous interference to passengers at the target masking location when there is no speech input from the speech source location.
[0008] In one possible implementation, a voice masking activation command is first received. The voice source location is then determined based on the source location of the activation command, and the target masking location is determined based on passenger information acquired by sensors within the vehicle. The command source location allows for more accurate determination of the voice source location, while captured passenger images intelligently identify the distribution of passengers within the vehicle, thereby determining the target masking location and avoiding sending masking sound to irrelevant locations.
[0009] In one possible implementation, the speech source location and target masking location are determined based on passenger input within the vehicle. This dynamic determination of the speech source location and target masking location based on passenger input can provide a better passenger experience and be applicable to various scenarios, such as when a passenger does not wish to be captured by a vehicle camera.
[0010] In one possible implementation, the sound signal at the speech source location can be enhanced to provide a clearer sound signal for subsequent speech detection, thereby improving the accuracy of speech detection. Optionally, the speech enhancement process includes echo cancellation and / or speech adaptive noise reduction.
[0011] In a possible implementation, a speech signal is subjected to time-domain inversion processing to generate a masking sound.
[0012] In one possible implementation, noise data is obtained from a noise database and used to generate the masking sound, or the masking sound is generated using the voice signal and the noise data. Optionally, the noise data in the noise database is preset. Specifically, the speech features of the voice signal can be analyzed to obtain noise data corresponding to the speech features from the noise database.
[0013] This application provides multiple masking sound generation methods, which are more flexible.
[0014] In one possible implementation, the masking sound may be automatically gain-controlled to ensure that the volume of the masking sound falls within a set range, thereby preventing the masking sound from fluctuating or leaking, thereby ensuring the masking effect at the target masking position.
[0015] In one possible implementation, a masking sound is subjected to sound field control processing based on a speech source position and a target masking position to output a first masking sound and a second masking sound, wherein the sound field control processing includes adjusting the phase and amplitude of each frequency signal in the masking sound; and then the first masking sound is output to a first speaker at the speech source position, and the second masking sound is output to a second speaker at the target masking position.
[0016] This application performs sound field control on the masking sound, causing the first speaker at the speech source location and the second speaker at the target masking location to play different masking sounds. This ensures that the masking sound at the target masking location meets the masking requirements, while also canceling out the masking sound played by the speaker at the speech source location with the masking sound at other locations, thereby preventing the masking sound from other locations from interfering with passengers at the speech source location. Specifically, the masking sound can be sound field controlled based on the speech source location and the target masking location to output N channels of masking sound, including a first masking sound and a second masking sound, where N is the number of speakers in the cabin. The volume of the masking sound from the first speaker at the speech source location is lower than the volume of the masking sound from the second speaker at the target masking location.
[0017] Through the sound field control processing, multiple speakers in the cockpit are coordinated to play masking sounds. On the one hand, a dark area of the sound field can be formed at the voice source position (to avoid the interference of the masking sound on the voice source position), and a bright area of the sound field can be formed at the target masking position (to ensure the masking effect on the target masking position). On the other hand, it can meet the demands of various private voice communications in the cockpit, such as the rear passengers wanting to mask the voices of the front passengers while communicating with each other, or the rear passengers masking the voices of the main driver's seat when communicating with the passenger in the front passenger seat. Furthermore, when the target masking position includes the main driver's seat, the second speaker includes a speaker located at the headrest of the main driver's seat. By playing the masking sound through the speaker on the headrest of the target masked seat, the masking sound has stronger directionality and better masking effect.
[0018] In a possible implementation, when the target masking position includes the main driver's seat, the volume of the vehicle safety warning sound of the main driver's seat is increased. By increasing the volume of the vehicle safety warning sound, it is possible to ensure that the driver can hear the safety warning sound.
[0019] Furthermore, the system can also capture external sounds, identify specific sounds within them, and then output these specific sounds to a speaker near the driver's seat. These specific sounds can include ambient warning sounds, such as sirens. Collecting and identifying specific external sounds and playing them inside the vehicle ensures the driver is responsive to the external environment, improving driving safety.
[0020] In a possible implementation, a voice masking closing instruction may be received, and the reception of the sound signal at the voice source location may be stopped according to the closing instruction.
[0021] In a second aspect, the present application provides a speech masking device, comprising:
[0022] A position determination module is used to determine the speech source position and the target masking position; a speech detection module is used to receive a sound signal from the speech source position and detect whether a speech signal is present in the sound signal to generate a detection result; a masking sound generation module is used to generate a masking sound based on the detection result, specifically: if the detection result is that a speech signal is present in the sound signal, then a masking sound is generated for the speech signal; if the detection result is that no speech signal is present in the sound signal, then no masking sound is generated; and a masking sound post-processing module is used to output the masking sound to a first speaker at the speech source position and a second speaker at the target masking position.
[0023] In one possible implementation, the position determination module is specifically configured to: receive a voice masking activation instruction; determine a voice source location based on a source location of the activation instruction; and determine the target masking location based on passenger information acquired by sensors in the vehicle.
[0024] In a possible implementation, the position determination module is specifically configured to determine the speech source position and the target masking position according to the speech source position and the target masking position input by a passenger in the vehicle.
[0025] In a possible implementation, the voice detection module is further configured to perform enhancement processing on the voice signal after receiving the voice signal from the voice source location. The enhancement processing includes echo cancellation processing and / or voice adaptive noise reduction processing.
[0026] In a possible implementation, the masker sound generation module is specifically configured to generate the masker sound by performing time-domain inversion processing on the speech signal.
[0027] In one possible implementation, the masker generation module is specifically configured to obtain noise data from a noise database and generate the masker using the noise data, or to generate the masker using the voice signal and the noise data. Optionally, the noise data is preset. Specifically, the masker generation module is configured to analyze speech features of the voice signal, obtain noise data corresponding to the speech features from the noise database, and generate the masker using the noise data.
[0028] In one possible implementation, the masker post-processing module is further configured to perform automatic gain control on the masker before outputting the masker to the first speaker at the speech source position and the second speaker at the target masking position, so that the volume of the masker meets a set range.
[0029] In one possible implementation, the masking sound post-processing module is specifically configured to: perform sound field control processing on the masking sound according to the speech source position and the target masking position to output a first masking sound and a second masking sound, wherein the sound field control processing includes adjusting the phase and amplitude of each frequency signal in the masking sound; output the first masking sound to the first speaker at the speech source position, and output the second masking sound to the second speaker at the target masking position.
[0030] Specifically, performing sound field control processing on the masking sound based on the speech source location and the target masking location to output a first masking sound and a second masking sound includes: performing sound field control processing on the masking sound based on the speech source location and the target masking location to output N channels of masking sound, the N channels of masking sound including the first masking sound and the second masking sound, where N is the number of speakers in the cabin; and the volume of the masking sound received by the first speaker is less than the volume of the masking sound received by the second speaker. Furthermore, when the target masking location includes the main driver's seat, the second speaker includes a speaker located on the headrest of the main driver's seat.
[0031] In one possible implementation, when the target masking location includes the primary driver's seat, the masking sound post-processing module is further configured to increase the volume of the vehicle safety warning sound. Furthermore, the masking sound post-processing module is further configured to acquire external sounds, perform specific type recognition on the external sounds to identify specific sounds within the external sounds, and output the specific sounds to the speaker in the primary driver's seat.
[0032] In a possible implementation, the position determination module is further configured to receive a voice masking off instruction; and the voice detection module is further configured to stop receiving the sound signal from the voice source location according to the off instruction.
[0033] In a third aspect, the present application provides a speech masking device, comprising a processor and a memory, wherein the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the method as described in the first aspect or any one of the first aspects.
[0034] In a fourth aspect, the present application provides a voice shielding system for use in a vehicle, the voice shielding system comprising:
[0035] A voice masking switch device is used to control the voice masking function to be turned on and / or off; a microphone is deployed at the voice source location and is used to collect voice at the voice source location; a first speaker is deployed at the voice source location; a second speaker is deployed at the target masking location, and the first and second speakers are used to play masking sounds.
[0036] In a possible implementation, the voice masking system further includes a camera, which is used to capture images of passengers in the vehicle.
[0037] In a possible implementation, the voice masking system further includes the information input device, which is used for a passenger in the vehicle to input the voice source position and the target masking position.
[0038] In a possible implementation, the microphone further includes a microphone deployed outside the vehicle, and the microphone deployed outside the vehicle is used to collect sounds outside the vehicle.
[0039] In a fifth aspect, the present application provides a computer-readable storage medium, which is used to store a computer program. When the computer program is run on a computer, the computer executes the method as described in the first aspect or any one of the first aspects.
[0040] In a sixth aspect, the present application provides a vehicle, comprising any one of the device described in the second aspect, the device described in the third aspect, and the system described in the fourth aspect.
[0041] In a seventh aspect, the present application provides a chip comprising a processor for reading instructions to execute the method as described in the first aspect or any one of the first aspects.
[0042] In an eighth aspect, the present application provides a computer program product, comprising a computer program code, which, when executed on a computer, enables the computer to execute the method according to the first aspect or any one of the first aspects.
[0043] Regarding the technical effects of the second to eighth aspects or various possible implementations, reference may be made to the introduction to the technical effects of the first aspect or corresponding implementations. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solution of the present application, the drawings of the embodiments of the present application will be briefly introduced below.
[0045] FIG1 is a schematic diagram of seat distribution in a vehicle cabin provided by an embodiment of the present application;
[0046] FIG2 is a schematic diagram of a speech masking system for a vehicle provided in an embodiment of the present application;
[0047] FIG3 is a schematic diagram of the deployment positions of a microphone and a speaker of a vehicle provided by an embodiment of the present application;
[0048] FIG4 is a flow chart of a method for implementing voice masking according to an embodiment of the present application;
[0049] FIG5 is a schematic diagram of an input control interface for a voice source position and / or a target masking position provided by an embodiment of the present application;
[0050] FIG6 is a schematic diagram of a method for enhancing a sound signal provided by an embodiment of the present application;
[0051] FIG7A is a schematic diagram of a method for generating a masking sound provided by an embodiment of the present application;
[0052] FIG7B is a schematic diagram of another method for generating masking sound provided in an embodiment of the present application;
[0053] FIG7C is a schematic diagram of another method for generating masking sound provided in an embodiment of the present application;
[0054] FIG8 is a schematic diagram of a sound masking principle provided by an embodiment of the present application;
[0055] FIG9 is a schematic diagram of a sound wave cancellation principle provided by an embodiment of the present application;
[0056] FIG10 is a schematic diagram of a sound field control provided in an embodiment of the present application;
[0057] FIG11 is a schematic diagram of a voice masking device provided in an embodiment of the present application;
[0058] FIG12 is a schematic diagram of another voice masking device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0059] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.
[0060] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.
[0061] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on the quantity and execution order.
[0062] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.
[0063] In addition, in order to better illustrate the present application, numerous specific details are provided in the following specific embodiments. Those skilled in the art should understand that the present application can also be implemented without certain specific details.
[0064] The method provided in the embodiment of the present application can be applied to scenarios where passengers in the cabin are communicating with each other or their voices need to be masked when they are talking, and is particularly applicable to scenarios where the front-seat driver needs to be shielded from the voices of rear-seat passengers when they are speaking.
[0065] FIG1 is a schematic diagram of the seat layout within a vehicle cabin provided in the present application. As shown in FIG1 , the vehicle 100 is equipped with front and rear rows of seats, including a driver's seat 101, a passenger seat 102, a rear left seat 103, a rear middle seat 104, and a rear right seat 105. For example, when the passengers in the rear left seat 103 and the rear right seat 105 are talking, if the conversation involves private or business matters, the conversation would be heard by the passengers in the front driver's seat 101 and the passenger seat 102, which is undesirable for the rear passengers. For another example, when the passenger in the driver's seat 101 (i.e., the driver) is making a phone call, the conversation would be heard by the passenger in the passenger seat 102 and the rear passengers. If the conversation involves personal privacy, this would be undesirable for the passenger in the driver's seat 101.
[0066] In response to the above problems, the present application provides a solution. First, the voice source position and the target masking position are determined. Then, the sound signal at the voice source position is received, and whether there is a voice signal in the sound signal is detected. A masking sound is generated based on the detection result, and the masking sound is played through a first speaker at the voice source position and a second speaker at the target masking position, so that the passengers at the target masking position cannot understand or hear clearly what the passengers at the voice source position are saying.
[0067] The solution provided by the embodiment of the present application can be implemented by the voice masking system 200 shown in Figure 2. As shown in Figure 2, the voice masking system 200 includes but is not limited to: a control device 210, a microphone device 220, and a speaker device 230. The control device 210 can be connected to the microphone device 220 and the speaker device 230. The control device 210 can be a platform with processing capabilities, including hardware, software, or a combination of hardware and software. For example, it can be implemented as an on-board computing platform and / or a cockpit domain control platform, which is not limited in this application. The speaker device 230 may include one or more speakers deployed in different locations.
[0068] The speech masking system 200 may also include an interaction device 240, which may include a sensor device 241. The sensor device 241 may include, but is not limited to, some or all of an image sensor 241-1, a radar 241-2, and a seat sensor 241-3. The image sensor 241-1 may be a camera, which can be used to capture images within the vehicle cabin. This application does not specifically limit the number and deployment location of the image sensors 241-1. The radar 241-2 may include one or more of an ultrasonic radar, a millimeter-wave radar, etc., for detecting passengers within the vehicle cabin. The seat sensor 241-3 is used to detect whether a passenger is on a vehicle seat. The seat sensor 241-3 may be a gravity sensor. The control device 210 can obtain information about the passenger's position within the cabin through the sensor device 241.
[0069] The interactive device 240 may also include a display device 242, which may include a mobile terminal or a display in the cabin, for interacting with passengers and receiving passenger input. The interactive device 240 may also include a function switch device 243 in the cabin, which may include a physical key switch, etc.
[0070] With the development of smart cars and the increasing demand for in-cabin interaction and audio quality, the number of microphones and speakers in vehicles is increasing. Speaker placement is becoming more and more scientific to achieve a superior sound field and sound experience, while microphones are also placed as close as possible to passengers in the cabin to facilitate the collection of their voice signals.
[0071] Figure 3 is a schematic diagram illustrating the deployment of microphones and speakers in a vehicle according to an embodiment of the present application. As shown in Figure 3, the vehicle's speaker assembly 230 may include speakers 230-1 through 230-8. The speakers may be arranged in a surround configuration around the cabin or in the headrests of seats within the cabin. For example, speaker 230-4 is arranged in the headrest of the driver's seat. By properly configuring the speaker deployment and orientation, a superior sound field can be created within the cabin. The vehicle's microphone assembly 220 may include in-cabin microphones 220-1 through 220-4. The in-cabin microphones are positioned above or to the sides of the passenger seats, as close as possible to the passenger's head. Additionally, the vehicle's microphone assembly may include an external microphone 220-5, which is primarily used to collect sounds outside the vehicle. It should be understood that the above-described speaker and microphone deployment locations and quantities are illustrative only and do not represent all deployment methods. This application does not specifically limit the deployment locations and quantities of the speakers and microphones. However, it should be understood that all deployment methods that meet the requirements of this application are within the scope of protection of this application.
[0072] It should be understood that the following description is for ease of understanding and explanation only, and that the method provided in the embodiments of the present application is described using a control device in a vehicle as the executing entity. This control device can be, for example, the control device 210 in FIG. 2 . The control device can be a component in the vehicle, such as a chip, a chip system, or other functional module capable of calling and executing programs. However, it should be understood that this does not constitute any limitation on the executing entity of the method provided in the present application. In the present application, the control device 210 can also be referred to as a voice masking device.
[0073] Figure 4 is a flow chart of a method for implementing voice masking provided by an embodiment of the present application. As shown in Figure 4, the method may include steps S410 to S430.
[0074] S410: Determine the voice source position and the target masking position.
[0075] Optionally, S410 may be implemented in any of the following ways, and the specific way to be adopted may depend on the implementation of the equipment and control device in the vehicle cabin.
[0076] In one embodiment, before the method in step S410, the method further includes receiving a voice masking activation instruction. Determining the voice source location and the target masking location includes: determining the voice source location based on the source location of the activation instruction; and determining the target masking location based on passenger information obtained by a sensor device within the vehicle. The sensor device may include the aforementioned sensor device 241. The activation instruction may be triggered by a function switch device at the voice source location within the cabin. The function switch device may be the aforementioned function switch device 243. The activation instruction may be used to locate the function switch device, thereby determining the source location of the instruction.
[0077] For example, an image sensor device (such as a camera) in the cabin may be used to obtain images of passengers in the cabin, and the position distribution of passengers in the cabin may be determined from the images of passengers, thereby determining the target masking position.
[0078] For example, passengers in the cabin may be detected by using a radar in the cabin (such as a millimeter wave radar) to determine the position distribution of the passengers in the cabin, thereby determining the target masking position.
[0079] For example, the pressure sensors of the seats in the cabin may be used to detect whether there are passengers on the seats in the vehicle, and the position distribution of the passengers in the cabin may be determined, thereby determining the target masking position.
[0080] For example, a combination of multiple sensors, such as a pressure sensor and an image sensor, can be used to more accurately determine the position distribution of passengers in the cabin, thereby more accurately determining the target masking position.
[0081] In one embodiment, the speech source location and / or target masking location are input by a passenger in the vehicle. For example, the passenger may input the speech source location and / or target masking location via a display device, which may include the aforementioned display device 242. The display device may be located in a center console, behind a seat headrest, or in a rear center console, among other locations.
[0082] Figure 5 shows an input control interface 500 for a speech source location and / or target masking location provided by an embodiment of the present application. In the input control interface shown in Figure 5 , the microphone icon represents the speech source location, and the mute icon represents the target masking location. As shown in Figure 5 , seat 501 is the speech source location, and seats 502, 503, 504, and 505 are the target masking locations. Passengers can switch their corresponding seat locations to the speech source location or target masking location by clicking an icon. For example, a passenger can click the mute icon for seat 502 in the input control interface to switch seat 502 to the speech source location. In this case, both seats 501 and 502 are speech source locations. The passenger in seat 502 can understand the speech from the passenger in seat 501, while the speech from the passengers in seats 501 and 502 will not be heard or understood by the passengers in seats 503, 504, and 505.
[0083] By providing an input control interface, passengers can dynamically control and adjust the location where voice masking is required, allowing for more flexible adaptation to various in-cabin scenarios and enhancing the passenger experience. For example, when rear-seat passengers are talking or chatting, the content of their conversation needs to be masked from the front seat. Another example is when rear-seat passengers are chatting and the passenger in the front passenger seat needs to join in. Both of these can be flexibly adjusted through the input interface. It should be understood that the input control interface provided in this embodiment is merely illustrative; the voice source location and target masking location can also be represented using other icons. Furthermore, the input control interface can also indicate the current passenger location in the vehicle cabin, which can be identified by various in-cabin sensors. Furthermore, the input control interface can also be a switch for selecting the voice source location and / or target masking location, or a voice receiving device. This embodiment of the application does not specifically limit the input control interface, input control methods, or methods for adjusting the voice source location and / or target masking location.
[0084] In one embodiment, the voice source location can be determined based on the source location of a voice masking activation command, and the target masking location can be determined based on input from a passenger in the vehicle. For example, a voice masking switch device can be positioned above or to the side of a passenger seat. When a passenger in the cabin triggers the voice masking switch, the control device determines the physical location of the voice masking switch device based on the received voice masking activation command, and then uses the seat position corresponding to the physical location of the voice masking switch device as the voice source location.
[0085] The above-mentioned methods for determining the voice source position and the target masking position can be combined, for example, by determining the voice source position by combining the image sensor and the instruction source position. It should be understood that the combined position determination method should also be within the scope of protection of this application.
[0086] S420: Receive a sound signal from the voice source location, and detect whether there is a voice signal in the sound signal to generate a detection result.
[0087] In one embodiment, after receiving the sound signal from the voice source location, step S420 further includes performing enhancement processing on the sound signal.
[0088] That is, step S420 specifically includes the following steps as shown in FIG6 :
[0089] 601, receiving a sound signal from the voice source location;
[0090] 602, performing enhancement processing on the sound signal to generate an enhanced sound signal;
[0091] 603 : Detect whether there is a speech signal in the enhanced sound signal to generate a detection result.
[0092] In one embodiment, the enhancement processing may include echo cancellation processing and / or speech adaptive noise reduction processing.
[0093] By performing enhancement processing on the sound signal, the noise in the sound signal can be reduced, making the sound signal clearer, and helping to improve the accuracy of the detection result of whether a speech signal exists in the sound signal.
[0094] In one embodiment, the sound signal may be detected by voice activity detection (VAD) to generate a detection result of whether a speech signal exists in the sound signal.
[0095] S430, if the detection result is that a speech signal exists in the sound signal, a masking sound is generated for the speech signal, and the masking sound is output to a first speaker at the speech source position and a second speaker at the target masking position; if the detection result is that no speech signal exists in the sound signal, no masking sound is generated.
[0096] Controlling the generation of masking sounds based on the presence of voice signals in the detection results can prevent the masking sounds from disturbing the target masking location when there is no voice signal. For example, when a passenger in the driver's seat is talking on a phone, the other party may be speaking for a long period of time while the driver is listening. In this case, since no voice signal is detected, there is no need to generate masking sounds, thus preventing the masking sounds from disturbing other passengers in the cabin.
[0097] In one embodiment, by setting up a voice signal caching mechanism, the cached voice signal is used to generate a masking sound in the gap (for example, 2 seconds) when the passenger at the voice source position pauses in speaking, thereby ensuring the continuity of the masking effect. For example, the cache size can be set to 500ms of voice signal content. It should be understood that this application does not specifically limit the method and size of the cache setting. In addition, the cached voice signal content can be updated according to whether there is a voice signal. When a voice signal is detected, the cached voice signal content is updated according to the voice signal; when no voice signal is detected, the cached voice signal content is not updated.
[0098] Similarly, the generated masking sound can also be cached. By caching the masking sound mechanism, the purpose of ensuring the continuity of the masking effect during the pauses of passengers speaking at the voice source location can be achieved. The mechanism is consistent with the above-mentioned cached voice signal.
[0099] In one embodiment, as shown in FIG7A , the masker sound is generated by performing time-domain inversion processing on the speech signal.
[0100] In one embodiment, as shown in FIG7B , noise data from a noise database is obtained and used to generate the masking sound. The noise data in the noise database may include one or more of white noise, narrowband noise, speech noise, etc. The noise data may be pre-set in the system or downloaded from the cloud and updated in real time. This application does not specifically limit the noise data in the noise database or its source.
[0101] In one embodiment, noise data from a noise database is obtained, and a masking sound is generated using the noise data and a speech signal. For example, a speech signal may be subjected to time-domain inversion processing to obtain a processed speech signal, and the processed speech signal is fused with the noise data obtained from the noise database to generate a masking sound.
[0102] In one embodiment, as shown in FIG7C , the speech features of the speech signal are analyzed to obtain noise data corresponding to the speech features from a noise database, and then the masking sound is generated using this noise data. By matching the noise data in the noise database with the speech features, the obtained noise data can be more closely matched to the speech signal, making the masking sound more comfortable for passengers at the target masking location and achieving a better masking effect. Furthermore, the speech features of the speech signal can be analyzed to generate the masking sound using a neural network model.
[0103] It should be understood that the above embodiments of generating masking sounds can be combined with each other to generate masking sounds. There are other ways to generate masking sounds, which are not specifically limited in this application.
[0104] In one embodiment, automatic gain control (AGC) can be applied to the generated masking sound to ensure that its volume falls within a set range. By controlling the volume of the masking sound to maintain it within the set range, the masking sound volume can be minimized to avoid discomfort to passengers at the target masking location. Furthermore, the masking sound volume can be kept relatively stable, preventing fluctuations or sound leakage, thereby ensuring effective masking.
[0105] In one embodiment, the masking sound is subjected to sound field control processing according to the speech source position and the target masking position to output a first masking sound and a second masking sound. The sound field control processing includes adjusting the phase and amplitude of each frequency signal in the masking sound, outputting the first masking sound to a first speaker at the speech source position, and outputting the second masking sound to a second speaker at the target masking position.
[0106] The speaker used to play the masking sound is determined based on the location information of the speech source and the target masking location. Sound field control coordinates the first speaker at the speech source location and the second speaker at the target masking location to play different masking sounds, creating a bright area at the target masking location and a dark area at the speech source location. This prevents passengers at the target masking location from understanding or clearly hearing the speech of passengers at the speech source location, while also preventing the masking sound played at the target masking location from interfering with passengers at the speech source location.
[0107] The following is a brief explanation of sound field control based on the principles of sound masking and noise reduction.
[0108] The phenomenon in which the auditory perception of a weaker sound (the masked sound) is affected by a stronger sound (the masking sound) is called the masking effect of the human ear. Generally speaking, the closer the frequencies of two sounds are, the greater the amount of masking they cause. In addition, high-frequency sounds are easily masked by low-frequency sounds, while low-frequency sounds are less likely to be masked by high-frequency sounds. For example, in a concert setting, the sound pressure level of a bass drum may not be high, but people can still clearly hear the sound of the bass drum from the concert music, while the sound of a violin is more easily masked by other low-frequency instruments.
[0109] Based on the above principles, the embodiment of the present application plays a masking sound through a speaker near the target masking position, masking the speech from the speech source position at the human ear position of the passenger at the target masking position, so that the passenger at the target masking position cannot understand or cannot hear the speech content at the speech source position clearly.
[0110] As shown in Figure 8, due to the distance between the passenger at the speech source location and the target masking location, the passenger's voice at the speech source location propagates through the air to the ear of the target masking location (direct sound wave). Simultaneously, a microphone near the speech source location captures the passenger's voice signal (direct sound wave) and detects the voice signal from the sound signal. A masking sound generator then generates a masking sound, which is then output to a speaker near the target masking location. Finally, the speaker near the target masking location plays the masking sound. At this point, at the target masking location's ear, the masking sound interferes with the voice from the passenger at the speech source location, achieving the goal of voice masking.
[0111] When the masking sound is played at the target masking location, the masking sound at the target masking location will also propagate to the voice source location, potentially disturbing passengers at the voice source location. Therefore, the present application can also perform noise reduction processing at the voice source location. For example, an active noise cancellation solution can be used. The principle is that all sounds are composed of a certain frequency spectrum. By finding an active noise whose frequency spectrum is the same as the noise to be cancelled, but with a phase difference of 180 degrees, the noise to be cancelled can be canceled.
[0112] FIG9 is a schematic diagram of a sound wave cancellation principle provided by an embodiment of the present application. As shown in FIG9 , a first sound wave 901 and a second sound wave 902 have the same frequency spectrum but are in opposite phases (180 degrees apart). The intersection of the first and second sound waves is precisely controlled based on calculations, for example, at the human ear. After the two sound waves intersect and cancel each other out, a third sound wave 903 is generated. The amplitude of the third sound wave 903 is very small, thereby achieving the goal of making the noise essentially inaudible to the human ear at the intersection.
[0113] Based on the above principles, the goal of forming a dark area at the speech source position and a bright area at the target masking position can be achieved through sound field control.
[0114] Figure 10 shows a schematic diagram of a sound field control provided by an embodiment of the present application. As shown in Figure 10, after the masking sound generating device generates the masking sound, the masking sound is output to the first filter and the second filter, and the first masking sound and the second masking sound are generated by controlling the parameters of the first filter and the second filter, and then the first masking sound is output to the first speaker, and the second masking sound is output to the second speaker. By controlling the parameters of the first filter and the second filter, the phase and amplitude of each frequency signal in the masking sound are adjusted, so that the first masking sound and the second masking sound have different phases and amplitudes. The first speaker can be a speaker near the voice source position, such as a speaker on the side of the voice source position. The second speaker can be a speaker near the target masking position, such as a speaker on the side of the target masking position.
[0115] In one embodiment, the volume of the first masking sound received by the first speaker is smaller than the volume of the second masking sound received by the second speaker.
[0116] In one embodiment, the masking sound can also be output to a third filter to generate a third masking sound, and the third masking sound is output to a third speaker at the voice source position. By the first speaker and the third speaker at the voice source position working simultaneously, the noise reduction effect at the voice source position is improved.
[0117] In one embodiment, the masking sound can also be output to a fourth filter to generate a fourth masking sound, and the fourth masking sound is output to a fourth speaker at the target masking position. The second speaker and the fourth speaker at the target masking position work simultaneously to improve the speech masking effect.
[0118] In one embodiment, the masking sound can also be output to N filters (the first filter to the Nth filter) to generate N channels of masking sound (the first masking sound to the Nth masking sound), where N is the number of speakers in the vehicle cabin. The N masking sounds are output to N speakers (the first speaker to the Nth speaker), and the sound field of the entire cabin is controlled by all speakers in the vehicle cabin, so that the speech masking at the target masking position has no sound leakage and low interference, and the noise at the speech source position is even smaller.
[0119] In one embodiment, the system can also identify the location of the human ear at the speech source and / or target masking location, dynamically adjusting the direction of one or more speakers in the vehicle cabin to achieve better noise reduction and speech masking. This recognition method can be an in-cabin camera sensor or millimeter-wave radar, and this application does not specify the specific recognition method.
[0120] In one embodiment, when the target masking position is the main driver's seat and the main driver's seat is equipped with a headrest speaker, playing the masking sound through the headrest speaker can achieve a better voice masking effect because the headrest speaker is closer to the human ear and has stronger directionality.
[0121] Similarly, when the driver's seat, co-driver's seat, and rear seats are equipped with headrest speakers, the masking sound can be played through the driver's seat, co-driver's seat, and rear seat headrest speakers to achieve a better voice masking effect.
[0122] In one embodiment, the target masking position can be dynamically adjusted and the sound field can be adaptively controlled based on changes in passenger status within the cabin (including changes in passenger position, number of passengers, etc.). For example, if a new passenger boards the vehicle, the sound field can be dynamically controlled after the new passenger's position is detected, and voice masking can be performed at the new passenger's location. In one embodiment, when a passenger alights or a passenger's position changes, the passenger at the voice source location can be prompted through a display or voice message to adjust the voice source location or target masking position.
[0123] In one embodiment, the sound field control may be implemented using a variable span trade-off (VAST) algorithm.
[0124] In one embodiment, when the target masking location includes the main driver's seat, the volume of vehicle prompts can be increased. Vehicle prompts can include safety warnings, such as battery and fuel level warnings. They can also include fault warnings and safety alerts, such as obstacle avoidance warnings and tire pressure warnings. Vehicles can also include function prompts, such as navigation prompts. By increasing the volume of vehicle prompts, voice masking can be achieved while ensuring that the driver recognizes the warnings in a timely manner, thereby ensuring driving safety.
[0125] In one embodiment, when the target masking position includes the main driver's seat, it is also possible to obtain a sound signal outside the vehicle, perform specific type recognition on the sound signal outside the vehicle to identify a specific sound in the sound outside the vehicle, and output the specific sound to the speaker of the main driver's seat. The sound outside the vehicle can be collected by an external microphone, and the specific type of the sound outside the vehicle can be recognized to identify the specific sound, and then the specific sound can be played through the speaker of the main driver's seat. For example, when the vehicle is driving, the rear vehicle honks to overtake, and the sound outside the vehicle is recognized to identify the horn of the rear vehicle, and then the horn sound is played through the speaker near the main driver's seat, which can remind the driver to pay attention and take corresponding safe driving actions. Specific types of sounds may include whistles, alarms, sound signals in specific directions, sound signals of emergencies, etc.
[0126] It should be understood that only a part of the vehicle prompt sounds, vehicle warning sounds and specific types of sounds are shown here. More scenes and corresponding prompt sounds and specific types of sounds can also be included. This application does not make specific limitations here.
[0127] In one embodiment, a voice masking off command may be received, and the reception of the sound signal from the voice source location may be stopped according to the off command. For example, the off command may be triggered by a passenger at the voice source location turning off the voice masking function switch device.
[0128] In one embodiment, a voice masking closing instruction may be automatically triggered when a passenger is detected getting off the bus at the voice source location.
[0129] In one embodiment, a timeout mechanism may be set, for example, a timeout mechanism of 2 minutes. When no voice signal is detected in the sound signal collected from the voice source location for 2 minutes, a voice masking shutdown instruction may be automatically triggered.
[0130] In one embodiment, when it is detected that a passenger gets off the bus at the target masking position, a voice masking closing instruction may be automatically triggered.
[0131] The various embodiments described herein may be independent solutions or may be combined according to internal logic, and all of these solutions fall within the scope of protection of this application.
[0132] It can be understood that, in the above-mentioned various method embodiments, the methods and operations implemented by the control device can also be implemented by components (such as chips or circuits) that can be used in the control device.
[0133] The speech masking device provided in the embodiment of the present application is described in detail below with reference to Figures 11 and 12. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment, so that for matters not described in detail, reference can be made to the above method embodiment.
[0134] As shown in Figure 11 , an embodiment of the present application further provides a speech masking device 1100 for implementing the functions of the control device in the above-described method. This device can be adapted to perform the functions of the above-described method embodiments in the flowcharts shown in Figures 4 , 6 , 7A , 7B , 7C , and 10 . For example, the device can be a software module or a chip system. In the embodiment of the present application, the chip system can be composed of a chip or can include a chip and other devices. The speech masking device 1100 can be the control device 210 shown in Figure 2 .
[0135] In one embodiment, the voice masking device 1100 is used in a vehicle, and includes:
[0136] Position determination module 1101, for determining the voice source position and target masking position;
[0137] a speech detection module 1102 for receiving a sound signal from the speech source location and detecting whether a speech signal exists in the sound signal to generate a detection result;
[0138] a masker generating module 1103 configured to generate a masker according to the detection result, wherein the masker generating module 1103 is specifically configured to: generate a masker for the voice signal if the detection result indicates that a voice signal exists in the sound signal; and not generate a masker if the detection result indicates that no voice signal exists in the sound signal.
[0139] The masker sound post-processing module 1104 is configured to output the masker sound to the first speaker at the speech source position and the second speaker at the target masking position.
[0140] In one embodiment, the position determination module 1101 is further configured to receive an instruction to activate a voice masking function, determine the voice source location based on the source location of the activation instruction, and determine the target masking location based on passenger information acquired by sensors in the vehicle.
[0141] In one embodiment, the sensor includes one or more of an image sensor, a radar sensor, and a seat sensor. The image sensor may include a camera. The radar sensor may include one or more of an ultrasonic radar, a millimeter-wave radar, etc. The seat sensor may include one or more of a gravity sensor, a pressure sensor, etc.
[0142] In one embodiment, the position determination module 1101 is further used to receive input from a passenger in the vehicle, and to determine the speech source position and / or target masking position based on the passenger input, wherein the passenger input includes the speech source position and / or target masking position input by the passenger.
[0143] In one embodiment, the voice detection module 1102 is further configured to perform enhancement processing on the sound signal after receiving the sound signal from the voice source location.
[0144] In one embodiment, the enhancement processing includes echo cancellation processing and / or speech adaptive noise reduction processing.
[0145] In one embodiment, the masker sound generating module 1103 is specifically configured to perform time domain inversion processing on the speech signal to generate a masker sound.
[0146] In one embodiment, the masker sound generation module 1103 is specifically configured to obtain noise data from a noise database and generate the masker sound using the noise data, or generate the masker sound using the voice signal and the noise data. The noise data in the noise database may be preset.
[0147] In one embodiment, the masker sound generation module 1103 is used to obtain noise data from a noise database, specifically to: analyze speech features of the speech signal, and obtain the noise data corresponding to the speech features from the noise database.
[0148] In one embodiment, the masker post-processing module 1104 is further configured to perform automatic gain control adjustment on the masker before outputting the masker to the first speaker at the speech source location and the second speaker at the target masking location, so that the volume of the masker meets a set range.
[0149] In one embodiment, the masker sound post-processing module 1104 is specifically configured to:
[0150] performing sound field control processing on the masking sound according to the speech source position and the target masking position to output a first masking sound and a second masking sound, wherein the sound field control processing includes adjusting the phase and amplitude of each frequency signal in the masking sound;
[0151] The first masking sound is output to the first speaker at the speech source position, and the second masking sound is output to the second speaker at the target masking position.
[0152] In one embodiment, performing sound field control processing on the masking sound according to the speech source position and the target masking position to output the first masking sound and the second masking sound includes:
[0153] The masking sound is subjected to sound field control processing according to the speech source position and the target masking position to output N channels of masking sound, where the N channels of masking sound include the first masking sound and the second masking sound, and N is the number of speakers in the cabin.
[0154] In one embodiment, the masking sound received by the first speaker at the speech source position is smaller than the masking sound received by the second speaker at the masking position.
[0155] In one embodiment, when the target masking position is a main driving seat, the second speaker includes a speaker located at a headrest of the main driving seat.
[0156] In one embodiment, when the target masking position includes the main driver's seat, the masking sound post-processing module 1104 is further configured to increase the volume of the vehicle safety warning sound.
[0157] In one embodiment, when the target masking position includes the main driver's seat, the masking sound post-processing module 1104 is further used to obtain external sounds, perform specific type recognition on the external sounds to identify specific sounds in the external sounds, and output the specific sounds to the speaker of the main driver's seat.
[0158] In one embodiment, the position determination module 1101 may also receive a voice masking off instruction and transmit the off instruction to the voice detection module 1102. The voice detection module 1102 is further configured to stop receiving sound signals originating from the voice source location according to the off instruction.
[0159] In one embodiment, the location determination module 1101 may further directly control the voice detection module according to the shutdown instruction, so that the voice detection module stops receiving the sound signal of the voice source location.
[0160] In one embodiment, the voice detection module may be configured to directly receive a voice masking off instruction, and stop receiving the sound signal at the voice source location according to the off instruction.
[0161] It should be understood that in the several embodiments provided in this application, the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units, components or modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple units, components or modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0162] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0164] An embodiment of the present application further provides another speech masking device 1200. The speech masking device 1200 shown in FIG12 may be a hardware circuit implementation of the device shown in FIG11 and may be adapted to perform the functions of the above-described method embodiments in the flowcharts shown in FIG4 , FIG6 , FIG7A , FIG7B , FIG7C , and FIG10 .
[0165] As shown in FIG12 , the speech masking device 1200 includes at least one processor 1201. The at least one processor 1201 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, configured to execute relevant programs to implement the speech masking method of the embodiment of the present invention.
[0166] The processor 1201 may also be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the voice masking method of the present application may be completed by hardware logic circuits in the processor 1201 or software instructions.
[0167] The speech masking device 1200 may further include at least one memory 1202, wherein the memory 1202 is configured to store instructions and / or data. The processor 1201 may be configured to execute instructions stored in the memory 1202. The memory 1202 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). By way of example but not limitation, the RAM can be in various forms, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM). It should be understood that the memory in the embodiments of the present application can be volatile memory or non-volatile memory, or can include both volatile and non-volatile memory. It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0168] It should be noted that although the above-mentioned voice masking device 1200 only shows a memory and a processor, in the specific implementation process, those skilled in the art should understand that the voice masking device 1200 may also include other components necessary for normal operation, such as a power supply, a communication port, input and output devices, etc.
[0169] The present application also provides a speech masking system 200, which may include a control device 210, a microphone device 220, and a speaker device 230 as shown in FIG2 . The control device 210 may be the speech masking device 1100 or 1200 described in the above-described embodiments. The microphone device 220 may include a microphone positioned at a speech source location, configured to collect sound signals at the speech source location. The speaker device 230 may include a first speaker positioned at the speech source location and a second speaker positioned at the target masking location, configured to play a masking sound.
[0170] In one embodiment, the voice masking system 200 may further include an interaction device 240 as shown in FIG2 , which may include a function switch device 243. The function switch device 243 may include a voice masking function switch device for controlling the on and / or off of the voice masking function.
[0171] In one embodiment, the interaction device 240 may further include a sensor device 241 as shown in FIG2 . The sensor device 241 may include one or more of an image sensor, a radar sensor, and a seat sensor to collect information about passengers in the vehicle. For example, the image sensor may include a camera, which captures images of passengers in the vehicle and transmits them to the control device 210. The control device 210 then identifies the speech source location and / or target masking location based on the images.
[0172] In one embodiment, the interaction device 240 further includes an information input device, which is used by vehicle passengers to input the voice source location and / or target masking location. The information input device can be a display device 242 as shown in Figure 2, a physical key input device, or a terminal device. The terminal device can be a mobile phone, tablet, watch, etc. The terminal device can interact directly or indirectly with the control device 210 via Wi-Fi, Bluetooth, mobile network, etc. It should be understood that this application does not specifically limit the terminal device, nor does it specifically limit the interaction method between the terminal device and the control device 210.
[0173] In one embodiment, the microphone device 220 may further include one or more microphones disposed outside the vehicle, and the microphones are used to collect sound signals outside the vehicle.
[0174] The embodiment of the present application further provides a computer-readable storage medium for storing a computer program. When the computer program is executed on a computer, the computer is caused to execute the above-mentioned voice masking method.
[0175] An embodiment of the present application further provides a computer program product, including computer program code. When the computer program code is executed on a computer, the computer is enabled to perform the above-mentioned voice masking method.
[0176] An embodiment of the present application further provides a vehicle, which includes any one of the above-mentioned voice masking device 1100 and voice masking device 1200 or the above-mentioned voice masking system 200.
[0177] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0178] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0179] It should be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0180] It should be understood that determining B based on A does not mean determining B based solely on A. B can also be determined based on A and / or other information.
[0181] As used in this specification, the terms "component," "module," "system," and the like are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and a computing device can be a component. One or more components can reside in a process and / or an execution thread, and a component can be located on a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).
[0182] The relevant parts of the various method embodiments of this application can be referenced to each other; the device provided by each device embodiment is used to execute the method provided by the corresponding method embodiment, so each device embodiment can be understood by referring to the relevant parts of the relevant method embodiments.
[0183] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. A method for implementing speech masking, characterized in that: Applied to vehicles, including: Determine the speech source location and target masker location; Receiving a sound signal from the voice source location; Detecting whether there is a voice signal in the sound signal to generate a detection result; If the detection result is that there is a speech signal in the sound signal, a masking sound is generated for the speech signal, and the masking sound is output to the first speaker at the speech source position and the second speaker at the target masking position; if the detection result is that there is no speech signal in the sound signal, no masking sound is generated.
2. The method according to claim 1, characterized in that Before determining the voice source position and the target masking position, the method further includes receiving a voice masking start instruction; Determining the speech source position and the target masking position includes: Determining the voice source location according to the source location of the start instruction; as well as The target masking position is determined according to passenger information acquired by a sensor in the vehicle.
3. The method according to claim 1, characterized in that The speech source position and the target masking position are the speech source position and the target masking position input by the passengers in the vehicle.
4. The method according to any one of claims 1 to 3, characterized in that: After receiving the sound signal from the voice source location, the method further includes performing enhancement processing on the sound signal.
5. The method according to claim 4, characterized in that The enhancement processing includes echo cancellation processing and / or speech adaptive noise reduction processing.
6. The method according to any one of claims 1 to 5, characterized in that: The generating a masker sound for the speech signal includes generating the masker sound by performing a time domain inversion process on the speech signal.
7. The method according to claims 1 to 6, characterized in that The method of outputting the masking sound to the first speaker at the speech source position and the second speaker at the target masking position comprises: Performing sound field control processing on the masking sound according to the speech source position and the target masking position to output a first masking sound and a second masking sound, wherein the sound field control processing includes adjusting the phase and amplitude of each frequency signal in the masking sound; The first masking sound is output to the first speaker at the speech source position, and the second masking sound is output to the second speaker at the target masking position.
8. The method according to claim 7, characterized in that The performing sound field control processing on the masking sound according to the speech source position and the target masking position to output the first masking sound and the second masking sound comprises: performing sound field control processing on the masking sound according to the speech source position and the target masking position to output masking sounds of N channels, wherein the masking sounds of the N channels include the first masking sound and the second masking sound, and N is the number of speakers in the cabin; The volume of the masking sound received by the first speaker is smaller than the volume of the masking sound received by the second speaker.
9. The method according to claim 7, characterized in that When the target masking position includes a main driving seat, the second speaker includes a speaker located at a headrest of the main driving seat.
10. The method according to any one of claims 1 to 9, characterized in that: Generating a masking sound for the speech signal comprises: Obtain noise data from a noise database; The masker is generated by using the noise data, or the masker is generated by using the speech signal and the noise data.
11. The method according to claim 10, characterized in that The acquiring the noise data from the noise database includes: analyzing the speech features of the speech signal, and acquiring the noise data corresponding to the speech features from the noise database.
12. The method according to any one of claims 1 to 11, characterized in that: Before outputting the masking sound to the first speaker at the speech source position and the second speaker at the target masking position, the method further includes performing automatic gain control adjustment on the masking sound so that the volume of the masking sound meets a set range.
13. The method according to any one of claims 1 to 12, characterized in that: When the target masking position includes the main driving seat, the method further includes: increasing the volume of the vehicle safety warning sound.
14. The method according to claim 13, characterized in that Also includes, Acquire the sound outside the vehicle, perform specific type recognition on the sound outside the vehicle to identify a specific sound among the sounds outside the vehicle, and output the specific sound to the speaker of the main driving seat.
15. The method according to any one of claims 2 to 14, characterized in that: Also includes: receiving a voice masking closing instruction; Stop receiving the sound signal from the voice source location according to the closing instruction.
16. A speech masking device, characterized in that: include: A position determination module, used to determine the voice source position and the target masking position; A voice detection module, used for receiving a sound signal from the voice source position, and detecting whether there is a voice signal in the sound signal to generate a detection result; A masking sound generating module, used to generate a masking sound according to the detection result, specifically used to: if the detection result is that there is a speech signal in the sound signal, then generate a masking sound for the speech signal; if the detection result is that there is no speech signal in the sound signal, then do not generate a masking sound; The masking sound post-processing module is used to output the masking sound to the first speaker at the speech source position and the second speaker at the target masking position.
17. The device according to claim 16, characterized in that The location determination module is specifically used for: receiving a voice masking activation instruction; The voice source position is determined according to the source position of the opening instruction, and the target masking position is determined according to the passenger information acquired by the sensor in the vehicle.
18. The device according to claim 16, characterized in that The position determination module is specifically used to determine the speech source position and the target masking position according to the speech source position and the target masking position input by the passengers in the vehicle.
19. The device according to any one of claims 16 to 18, characterized in that The voice detection module is also used to enhance the sound signal after receiving the sound signal from the voice source position.
20. The device according to claim 19, characterized in that The enhancement processing includes echo cancellation processing and / or speech adaptive noise reduction processing.
21. The device according to any one of claims 16 to 20, characterized in that The masker sound generation module is specifically configured to generate a masker sound by performing time domain inversion processing on the speech signal.
22. The device according to any one of claims 16 to 21, characterized in that The masking sound post-processing module outputs the masking sound to the first speaker at the speech source position and the second speaker at the target masking position specifically for: Performing sound field control processing on the masking sound according to the speech source position and the target masking position to output a first masking sound and a second masking sound, wherein the sound field control processing includes adjusting the phase and amplitude of each frequency signal in the masking sound; The first masking sound is output to the first speaker at the speech source position, and the second masking sound is output to the second speaker at the target masking position.
23. The device according to claim 22, characterized in that When the masking sound is subjected to sound field control processing according to the speech source position and the target masking position to output a first masking sound and a second masking sound, the masking sound post-processing module is specifically used to: performing sound field control processing on the masking sound according to the speech source position and the target masking position to output masking sounds of N channels, wherein the masking sounds of the N channels include the first masking sound and the second masking sound, and N is the number of speakers in the cabin; The volume of the masking sound received by the first speaker is smaller than the volume of the masking sound received by the second speaker.
24. The device according to claim 22, characterized in that When the target masking position is a main driving seat, the second speaker includes a speaker located at a headrest of the main driving seat.
25. The device according to any one of claims 16 to 24, characterized in that The masking sound generation module is specifically used for: Obtain noise data from a noise database; The masker sound is generated using the noise data, or the voice signal and the noise data are used to generate the masker sound.
26. The device according to claim 25, characterized in that When acquiring the noise data from the noise database, the masker sound generation module is specifically used to: analyze the speech features of the speech signal, and acquire the noise data corresponding to the speech features from the noise database.
27. The device according to any one of claims 16 to 26, characterized in that Before outputting the masking sound to the first speaker at the speech source position and the second speaker at the target masking position, the masking sound post-processing module is further used to perform automatic gain control adjustment on the masking sound so that the volume of the masking sound meets a set range.
28. The device according to any one of claims 16 to 27, characterized in that When the target masking position includes the main driving seat, the masking sound post-processing module is further used to increase the volume of the vehicle safety warning sound.
29. The device according to claim 28, characterized in that The masking sound post-processing module is also used for: Acquire the sound outside the vehicle, perform specific type recognition on the sound outside the vehicle to identify a specific sound among the sounds outside the vehicle, and output the specific sound to the speaker of the main driving seat.
30. The device according to any one of claims 17 to 29, characterized in that include: The position determination module is also used to receive a voice masking closing instruction; The voice detection module is also used to stop receiving the sound signal from the voice source location according to the closing instruction.
31. A speech masking device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the method according to any one of claims 1 to 15.
32. A voice masking system, used in a vehicle, characterized in that: include: A voice masking switch device, used to control the voice masking function to be turned on and / or off; The device according to any one of claims 16 to 31; A microphone is deployed at the voice source location and is used to collect sound signals at the voice source location; A first speaker, deployed at the location of the voice source; The second speaker is deployed at the target masking position; The first loudspeaker and the second loudspeaker are used to play the masking sound.
33. The system of claim 32, wherein: It also includes a sensor device, which is used to collect information about passengers in the vehicle.
34. The system of claim 32, wherein: The vehicle also includes the information input device, which is used for passengers in the vehicle to input the voice source position and the target masking position.
35. The system according to any one of claims 32 to 34, characterized in that The microphone also includes a third microphone deployed outside the vehicle, and the third microphone deployed outside the vehicle is used to collect sounds outside the vehicle.
36. A vehicle, characterized in that: Comprising the apparatus as claimed in any one of claims 16 to 31 or the system as claimed in any one of claims 32 to 35.
