External voice control device and automobile

Abstract

The invention relates to the technical field of human-vehicle interaction, and discloses an out-of-vehicle voice control device and an automobile, the device comprises an acquisition module, an identification module and a power supply module; the identification module is respectively connected with the acquisition module and the power supply module, and the identification module is also connected with equipment to be controlled through a digital key terminal controller of the automobile; the power supply module is used for supplying power to the acquisition module and the identification module; the acquisition module is used for transmitting an acquired external voice instruction to the recognition module; and the identification module is used for transmitting a generated control signal to the digital key terminal controller when the external voice instruction is a preset control instruction, so that the digital key terminal controller controls the corresponding to-be-controlled equipment. Compared with the prior art that simple voice control needs to be carried out after the vehicle machine is started, simple voice control can be completed without starting the vehicle machine, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of human-vehicle interaction technology, and in particular to an external vehicle voice control device and a vehicle. Background Art

[0002] At present, with the development of automobile intelligence, many vehicles have external voice control functions, that is, the voice commands issued by users outside the car will also be collected and transmitted to the car computer for complete audio algorithm processing and execution of corresponding operations.

[0003] However, when performing existing voice control outside the vehicle, whether it is a simple voice command (such as opening the trunk tailgate, etc.) or a complex voice command (such as turning on the air conditioner, etc.), it is necessary to use the vehicle computer to recognize the voice command when the vehicle computer is working. For some complex voice controls, the vehicle engine must be started.

[0004] For simple voice control that can be achieved without starting the engine, it must be done when the car computer is turned on. When the engine is off, the ignition should be turned on first and then the car computer is turned on, which is a cumbersome operation. Therefore, how to achieve simple voice control when the engine is off is an urgent problem to be solved. Summary of the invention

[0005] The main purpose of the present application is to provide an off-vehicle voice control device and a vehicle, aiming to solve the existing technical problem of how to achieve simple voice control when the engine is turned off.

[0006] To achieve the above-mentioned purpose, the present application provides an off-vehicle voice control device, the device comprising: a collection module, a recognition module and a power supply module;

[0007] The identification module is connected to the acquisition module and the power supply module respectively, and the identification module is also connected to the device to be controlled through the digital key terminal controller of the car;

[0008] The power supply module is used to supply power to the acquisition module and the identification module;

[0009] The acquisition module is used to transmit the collected external vehicle voice commands to the recognition module;

[0010] The recognition module is used to transmit the generated control signal to the digital key terminal controller when the external voice command is a preset control command, so that the digital key terminal controller controls the corresponding device to be controlled.

[0011] In one embodiment, the recognition module is further used to pre-process the external voice command, wherein the pre-processing includes at least one of pre-emphasis processing, frame processing, windowing processing, and noise reduction processing;

[0012] The recognition module is further used to perform voice enhancement on the pre-processed external vehicle voice command and to perform feature extraction on the voice-enhanced external vehicle voice command to obtain a target voice command;

[0013] The recognition module is also used to transmit the generated control signal to the digital key terminal controller when the target voice command is a preset control command.

[0014] In one embodiment, the identification module includes: a processing unit and a judgment unit;

[0015] The processing unit is connected to the power supply module, the acquisition module and the judgment unit respectively, and the judgment unit is also connected to the power supply module and the digital key terminal controller;

[0016] The processing unit is used to preprocess the external vehicle voice command, perform voice enhancement on the preprocessed external vehicle voice command, and perform feature extraction on the voice enhanced external vehicle voice command to obtain a target voice command;

[0017] The judgment unit is used to transmit the generated control signal to the digital key terminal controller when the target voice command is a preset control command.

[0018] In one embodiment, the processing unit includes: a first processing subunit and a second processing subunit;

[0019] The first processing subunit is connected to the power supply module, the acquisition module, the judgment unit and the second processing subunit respectively, and the second processing subunit is also connected to the power supply module and the judgment unit;

[0020] The first processing subunit is used to pre-process the external vehicle voice command and perform voice enhancement on the pre-processed external vehicle voice command;

[0021] The second processing subunit is used to extract features of the external vehicle voice command after voice enhancement to obtain the target voice command.

[0022] In one embodiment, the recognition module is further used to perform beamforming on the pre-processed external vehicle voice command to determine the collection angle of the external vehicle voice command;

[0023] The recognition module is also used to enhance the pre-processed external vehicle voice command when the collection angle is within a preset angle range.

[0024] In one embodiment, the identification module is further used to determine the number of occurrences of the preset interval range corresponding to the acquisition angle when the acquisition angle is not within the preset angle range;

[0025] The identification module is further configured to update the preset angle range when the number of occurrences reaches a preset number threshold corresponding to the preset interval range.

[0026] In one embodiment, the identification module is further configured to determine a corresponding range update strategy based on the preset interval range when the number of occurrences reaches a preset number threshold corresponding to the preset interval range;

[0027] The identification module is further used to update the preset angle range according to the corresponding range update strategy.

[0028] In one embodiment, the acquisition module is further used to transmit the collected external vehicle audio to the recognition module;

[0029] The recognition module is further configured to switch the current working mode from the low power consumption mode to the normal working mode when a preset voiceprint exists in the external audio of the vehicle;

[0030] The identification module is further used to determine whether the external vehicle voice command is a preset control command when the current working mode is the normal working mode;

[0031] The identification module shown is also used to transmit the generated control signal to the digital key terminal controller when the external voice command is a preset control command.

[0032] In one embodiment, the device further comprises: a transmission module;

[0033] The transmission module is connected to the identification module and the digital key terminal controller respectively;

[0034] The transmission module is used to transmit the control signal to the digital key terminal controller when receiving the control signal.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a car, wherein the device includes the off-vehicle voice control device as described above.

[0036] The present application provides an external vehicle voice control device and a vehicle, the device comprising: an acquisition module, an identification module and a power supply module; the identification module is connected to the acquisition module and the power supply module respectively, and the identification module is also connected to a device to be controlled through a digital key terminal controller of the vehicle; the power supply module is used to power the acquisition module and the identification module; the acquisition module is used to transmit the collected external vehicle voice instructions to the identification module; the identification module is used to transmit the generated control signal to the digital key terminal controller when the external vehicle voice instruction is a preset control instruction, so that the digital key terminal controller controls the corresponding device to be controlled.

[0037] Since the present application can be provided with a collection module, a recognition module and a power supply module; the collection module and the recognition module are powered by the sharing module, the collection module can transmit the collected voice commands outside the vehicle to the recognition module for recognition, and the recognition module can transmit the generated control signal to the digital key terminal controller when the voice command outside the vehicle is a preset control command, and then the digital key terminal controller controls the corresponding device to be controlled. Compared with the existing simple voice control that requires starting the vehicle computer, the present application can complete simple voice control without starting the vehicle computer, which improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0040] Figure 1 This is a schematic structural diagram of a first embodiment of the vehicle exterior voice control device of the present application;

[0041] Figure 2 This is a schematic diagram of the current working mode switching in the first embodiment of the vehicle exterior voice control device of the present application;

[0042] Figure 3 This is a schematic structural diagram of a second embodiment of the vehicle exterior voice control device of the present application;

[0043] Figure 4 This is a schematic diagram of the voice processing flow in the second embodiment of the off-vehicle voice control device of the present application;

[0044] Figure 5This is a specific structural diagram of the second embodiment of the vehicle exterior voice control device of the present application;

[0045] Figure 6 This is a schematic diagram of beamforming in the third embodiment of the external vehicle voice control device of the present application.

[0046] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0050] In addition, the descriptions of "first", "second", etc. in this application are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0051] It is understandable that at present, with the development of automobile intelligence, many vehicles have external voice control functions, that is, the voice commands issued by users outside the car will also be collected and transmitted to the car computer for complete audio algorithm processing and execution of corresponding operations.

[0052] However, when performing existing voice control outside the vehicle, whether it is a simple voice command (such as opening the trunk tailgate, etc.) or a complex voice command (such as turning on the air conditioner, etc.), it is necessary to use the vehicle computer to recognize the voice command when the vehicle computer is working. For some complex voice controls, the vehicle engine must be started.

[0053] For simple voice control that can be achieved without starting the engine, it must be carried out when the car computer is turned on, that is, the car computer can recognize voice commands to generate corresponding control signals and transmit them to the car's digital key terminal controller (Bluetooth Network Controller Module, BNCM), and control the corresponding device actions through the digital key terminal controller.

[0054] When the engine is off, the ignition should be turned on first and then the car computer is turned on, which is a cumbersome operation. Therefore, how to achieve simple voice control when the engine is off is an urgent problem to be solved.

[0055] Therefore, in order to solve the above defects, this embodiment provides an off-vehicle voice control device, which can be provided with a collection module, a recognition module and a power supply module; the collection module and the recognition module are powered by the sharing module, and the collection module can transmit the collected off-vehicle voice commands to the recognition module for recognition, and the recognition module can transmit the generated control signal to the digital key terminal controller when the off-vehicle voice command is a preset control command, and then the digital key terminal controller controls the corresponding device to be controlled. Compared with the existing simple voice control that requires starting the car computer, this embodiment can complete simple voice control without starting the car computer, which improves the user experience.

[0056] For ease of understanding, the following combination Figures 1 to 6 The external vehicle voice control device provided in the embodiment of the present application is specifically introduced.

[0057] Reference Figure 1 , Figure 1 The first embodiment of the vehicle exterior voice control device of the present application is shown in FIG. Figure 1 As shown, in this embodiment, the vehicle external voice control device includes: a collection module, a recognition module and a power supply module;

[0058] The identification module is connected to the acquisition module and the power supply module respectively, and the identification module is also connected to the device to be controlled through the digital key terminal controller of the car.

[0059] It should be understood that the external vehicle voice control device provided in this embodiment can be used in the scenario of external vehicle voice control of the car, and of course can also be used in other scenarios of voice control. This embodiment uses the scenario of external vehicle voice control of the car for illustration.

[0060] It should also be understood that the acquisition module can be any module for collecting audio, such as a microphone. Of course, in order to improve the quality of the collected audio, the acquisition module in this embodiment can be implemented by a microphone array (Microphone Array, MIC Array). The MIC Array in this embodiment can be composed of two or more microphone units, which can be arranged vertically, that is, arranged in a "line", or arranged in a ring. Of course, they can also be arranged in other shapes, which is not limited in this embodiment. And the acquisition module in this embodiment can be set at any position on the car that is convenient for collecting audio outside the car, which is not limited in this embodiment.

[0061] It should be emphasized that since multiple microphone units are used in this embodiment, in order to make the microphone units work in coordination, the microphone units in this embodiment can have higher performance consistency or further achieve high matching between microphone units through an external electrically erasable programmable read-only memory.

[0062] It should be noted that the above recognition module can be any module with an audio recognition function. In this embodiment, it can be implemented by a micro control unit (MCU). Of course, it can also be implemented by other devices, and this embodiment does not limit this. Therefore, in this embodiment, a voice command recognition program can be configured in the MCU, and the voice command recognition program can perform voice recognition.

[0063] It should also be noted that the power supply module may be any module that can supply power, such as a lithium battery, etc., and of course, may also be other batteries, which is not limited in this embodiment.

[0064] The digital key terminal controller may be a module provided in the vehicle for controlling some of the devices to be controlled. The devices to be controlled may be any device on the vehicle, such as a window, a trunk tailgate, etc., which is not limited in this embodiment.

[0065] In existing vehicles, the above-mentioned digital key terminal controller can be provided, and connected to the vehicle computer and the device to be controlled respectively. After receiving the user's voice command, the vehicle computer can identify it, and when it identifies that the device to be controlled that the digital key terminal controller is responsible for needs to be controlled, it can generate a corresponding control signal and transmit it to the digital key terminal controller. After receiving the control signal, the digital key terminal controller can control the corresponding device to be controlled. The equipment that the above-mentioned digital key terminal controller is responsible for generally includes but is not limited to car windows, trunk tailgate, etc., which do not require the car engine to be started. The specific settings can be made according to the actual situation, and this embodiment does not limit this. And the above-mentioned digital key terminal controller can work all the time, so there is no need to consider whether to start the engine.

[0066] Continue as Figure 1 As shown, in this embodiment, the power supply module is used to supply power to the acquisition module and the identification module;

[0067] The acquisition module is used to transmit the collected external vehicle voice commands to the recognition module;

[0068] The recognition module is used to transmit the generated control signal to the digital key terminal controller when the external voice command is a preset control command, so that the digital key terminal controller controls the corresponding device to be controlled.

[0069] It is understandable that the above-mentioned voice command outside the vehicle can be a voice command corresponding to the audio issued by the user. The above-mentioned preset control command can be a command corresponding to the device that the digital key terminal controller is responsible for, such as opening the trunk tailgate, opening the window, etc. These commands do not need to be implemented under the car engine starting, and this embodiment does not limit this.

[0070] In actual use, when the acquisition module collects the audio outside the car sent by the user, the audio outside the car may contain the voice command outside the car, and then the audio outside the car can be transmitted to the recognition module, and the recognition module can determine whether the voice command outside the car is a preset control command; if not, it can be explained that the voice command outside the car is noise or cannot be completed when the engine is turned off, so no control signal is generated; if so, it can be explained that the voice command outside the car can be completed through the digital key terminal controller, and then the corresponding control signal can be generated and transmitted to the digital key terminal controller, and the digital key terminal controller can control the corresponding device to be controlled according to the control signal to complete the action. Compared with the existing simple voice control that requires starting the car computer, this embodiment can complete simple voice control without starting the car computer, which improves the user experience.

[0071] It should be emphasized that the simple voice control described in this embodiment can be the control that can be completed by the digital key terminal control.

[0072] Furthermore, considering that the power supply mode of the above device is battery powered, in order to reduce power consumption, continue as follows Figure 1 As shown, in this embodiment, the acquisition module is also used to transmit the collected external vehicle audio to the recognition module;

[0073] The recognition module is further configured to switch the current working mode from the low power consumption mode to the normal working mode when a preset voiceprint exists in the external audio of the vehicle;

[0074] The identification module is further used to determine whether the external vehicle voice command is a preset control command when the current working mode is the normal working mode;

[0075] The identification module shown is also used to transmit the generated control signal to the digital key terminal controller when the external voice command is a preset control command.

[0076] It should be noted that the recognition module in this embodiment can be set to have two working modes, namely, low power consumption mode and normal working mode. When no voice command outside the vehicle is detected, the recognition module can generally be in low power consumption mode to reduce power consumption; when a voice command outside the vehicle is detected, it can be switched to normal working mode for recognition.

[0077] It is understandable that the above-mentioned preset voiceprint can be the voiceprint of a user with permission to use, such as the owner of the car. Figure 2 To explain, Figure 2 This is a schematic diagram of the current working mode switching in the first embodiment of the vehicle exterior voice control device of the present application;

[0078] like Figure 2 As shown, in general, the current working mode of the recognition module is low power consumption mode (i.e. Figure 2 Low and medium power consumption modes), and continue to monitor, and can monitor at preset time intervals (i.e. Figure 2 The specific preset time interval can be set according to the actual situation, and this embodiment does not limit this.

[0079] When the recognition module receives the audio outside the car, it can first determine whether the voiceprint in the audio outside the car is a preset voiceprint (i.e. Figure 2 If not, it can be indicated that the person is not the owner of the vehicle, and the low power consumption mode can be maintained; if yes, it can be indicated that the person is the owner of the vehicle, and the current working mode can be switched to the normal working mode and the subsequent external voice command recognition can be performed (i.e. Figure 2 Normal working mode audio analysis transmission).

[0080] After the identification module transmits the control signal to the digital key terminal controller, it can be determined whether the control signal transmission is completed (i.e. Figure 2 If the command transmission is not finished, the normal working mode is maintained for identification and transmission; if it is finished, the low power consumption mode is switched back to the low power consumption mode.

[0081] Furthermore, in order to reduce external noise interference, after the above-mentioned recognition module switches to a normal working state, before determining whether the voice command outside the vehicle is a preset control command, the recognition module can also perform wake-up word detection. Specifically, the recognition module can first determine whether there is a preset wake-up command in the audio outside the vehicle; the preset wake-up command can be any command for waking up the recognition module, and this embodiment does not limit this.

[0082] If it does not exist, it means that the user has no intention to issue commands, and no subsequent recognition will be performed; if it exists, it means that the user has the intention to issue commands, and the above-mentioned outside-vehicle voice control commands can be identified and extracted from the outside-vehicle audio, and the corresponding control signals can be generated and transmitted to the digital key terminal controller.

[0083] Further, in order to transmit the control signal generated by the identification module to the digital key terminal controller, continue as follows Figure 1 As shown, in this embodiment, the device further includes: a transmission module;

[0084] The transmission module is connected to the identification module and the digital key terminal controller respectively;

[0085] The transmission module is used to transmit the control signal to the digital key terminal controller when receiving the control signal.

[0086] It is understandable that the above-mentioned transmission module can be any module for signal transmission. In this embodiment, the above-mentioned transmission module can adopt a wired transmission method or a wireless transmission method. When the wired transmission method is adopted, the transmission module can be connected to the digital key terminal controller by means of a local interconnect network (Local Interconnect Network, LIN), and then the transmission module can adopt a module with LIN transmission function, which can be set according to actual conditions, and this embodiment does not limit this. When the wireless transmission method is adopted, the transmission module can be connected to the digital key terminal controller by means of Bluetooth, and then the transmission module can adopt Bluetooth Low Energy (Bluetooth Low Energy, BLE), of course, other devices that can be wirelessly connected can also be used, and this embodiment does not limit this.

[0087] In actual use, after the identification module generates a control signal, it can be transmitted to the transmission module, and the transmission module then transmits the received control signal to the digital key terminal controller for control.

[0088] This embodiment can be provided with a collection module, a recognition module and a power supply module; the collection module and the recognition module are powered by the sharing module, the collection module can transmit the collected voice commands outside the vehicle to the recognition module for recognition, and the recognition module can transmit the generated control signal to the digital key terminal controller when the voice command outside the vehicle is a preset control command, and then the digital key terminal controller controls the corresponding device to be controlled. Compared with the existing simple voice control that requires starting the vehicle computer, this embodiment can complete simple voice control without starting the vehicle computer, which improves the user experience.

[0089] Reference Figure 3 , Figure 3 This is a structural schematic diagram of the second embodiment of the external vehicle voice control device of the present application. Based on the above-mentioned first embodiment, the second embodiment of the external vehicle voice control device of the present application is proposed.

[0090] Considering that there may be a lot of noise in the collected external voice control commands, in order to facilitate subsequent recognition, Figure 3 As shown, in this embodiment, the recognition module is also used to pre-process the external voice command, and the pre-processing includes at least one of pre-emphasis processing, frame processing, windowing processing and noise reduction processing.

[0091] It should be noted that the above-mentioned pre-emphasis processing can be a processing to improve the signal-to-noise ratio of the high-frequency part of the external voice command. Since the energy of the high-frequency part in the external audio is usually weak and easily interfered by noise, the recognition module in this embodiment can increase the signal-to-noise ratio of the high-frequency part of the received external voice command, thereby completing the pre-emphasis processing.

[0092] The above-mentioned frame division processing can be a processing for segmenting the voice commands outside the vehicle. Since the collected audio outside the vehicle is continuous, the recognition module can segment the voice commands outside the vehicle, thereby completing the frame division processing.

[0093] The above-mentioned windowing process can be to multiply the external audio by a window function so as to facilitate Fourier transform processing in the subsequent noise reduction. Since directly performing Fourier transform on the external audio will cause leakage in the frequency domain, in this embodiment, the recognition module can multiply the external voice command by a window function (such as Hamming window, Hanning window, etc.) to reduce leakage. And Fourier transform can be performed after windowing.

[0094] The above-mentioned noise reduction processing can be any processing for reducing the noise of the audio. In this embodiment, the noise reduction can be achieved by using Fast Fourier Transform (FFT). Then, the recognition module can perform FFT on the voice command outside the vehicle to complete the noise reduction processing.

[0095] For ease of understanding, refer to Figure 4 , Figure 4 This is a schematic diagram of the voice processing flow in the second embodiment of the vehicle exterior voice control device of the present application. Figure 4 As shown, the acquisition module collects the voice commands outside the vehicle (i.e. Figure 4 After the microphone collects the input, it is transmitted to the recognition module, which can pre-process it (i.e. Figure 4 pre-emphasis, framing, windowing, FFT).

[0096] After preprocessing, the recognition module is further used to perform voice enhancement on the preprocessed external vehicle voice instructions, and perform feature extraction on the voice enhanced external vehicle voice instructions to obtain target voice instructions.

[0097] It is understandable that the above-mentioned voice enhancement can be to enhance the signal strength of the audio. In this embodiment, spectral subtraction, adaptive beamforming, deep neural network and other methods can be used to achieve this. The specific method can be selected according to the actual situation, and this embodiment does not limit this. Therefore, in actual use, the recognition module can perform voice enhancement (i.e., Figure 4 Medium signal enhancement);

[0098] After the speech enhancement, the feature extraction of the enhanced vehicle external voice command can be performed (i.e. Figure 4 The target voice command can be a command for controlling the audio outside the vehicle. The feature extraction in the voice command outside the vehicle can be achieved by linear prediction coding, short-time Fourier transform, etc., and of course, it can also be achieved by other methods, which are not limited in this embodiment.

[0099] After obtaining the target voice command, the recognition module is further used to transmit the generated control signal to the digital key terminal controller when the target voice command is a preset control command.

[0100] In this embodiment, a command library may be provided, and the command library may store various preset control commands that can be used for control. Then, when the recognition module obtains the target voice command, the target voice command may be compared with the preset control command in the command library (i.e. Figure 4 and confirm whether it is a preset control command; and if it is a preset control command, generate a corresponding control signal and transmit it to the digital key terminal controller (i.e. Figure 4 If it is not in the control signal transmission, the external audio can be continuously monitored (i.e. Figure 4 continuous monitoring).

[0101] It should be emphasized that when the above recognition module is an MCU, the above preprocessing, speech enhancement, feature extraction and comparison operations can all be completed by the MCU. However, in order to reduce the amount of MCU calculation, Figure 3 As shown, in this embodiment, the identification module includes: a processing unit and a judgment unit;

[0102] The processing unit is connected to the power supply module, the acquisition module and the judgment unit respectively, and the judgment unit is also connected to the power supply module and the digital key terminal controller;

[0103] The processing unit is used to preprocess the external vehicle voice command, perform voice enhancement on the preprocessed external vehicle voice command, and perform feature extraction on the voice enhanced external vehicle voice command to obtain a target voice command;

[0104] The judgment unit is used to transmit the generated control signal to the digital key terminal controller when the target voice command is a preset control command.

[0105] It should be noted that the processing unit can be any unit that implements the preprocessing, voice enhancement and feature extraction. In this embodiment, the processing unit can be implemented by a digital signal processor (DSP). Furthermore, the judgment unit can be an MCU, that is, a DSP and an MCU can be provided. In actual use, the DSP can be used to preprocess, enhance and extract features of the external voice command to obtain the target voice command, and then transmit the target voice command to the MCU for recognition.

[0106] Furthermore, considering that the computing power of a DSP may not be sufficient, in this embodiment, the processing unit includes: a first processing sub-unit and a second processing sub-unit;

[0107] The first processing subunit is connected to the power supply module, the acquisition module, the judgment unit and the second processing subunit respectively, and the second processing subunit is also connected to the power supply module and the judgment unit;

[0108] The first processing subunit is used to pre-process the external vehicle voice command and perform voice enhancement on the pre-processed external vehicle voice command;

[0109] The second processing subunit is used to extract features of the external vehicle voice command after voice enhancement to obtain the target voice command.

[0110] It should be noted that, in this embodiment, the above-mentioned first processing subunit can be implemented by a DSP, which is recorded as the first DSP for the convenience of subsequent description; the above-mentioned second processing subunit can be implemented by another DSP, which is recorded as the second DSP for the convenience of subsequent description.

[0111] For ease of understanding, refer to Figure 5 , Figure 5 This is a specific structural diagram of the second embodiment of the vehicle exterior voice control device of the present application, such as Figure 5 As shown, the battery in the power supply module (i.e. Figure 5Li Battery Optional / 12VBattery) can provide electrical energy. Since different devices require different electrical energy, a conversion module can also be provided in the power supply module. The conversion module is connected to the battery. The conversion module can be a power management integrated circuit (Power Management Integrated Circuit, PMIC) (i.e. Figure 5 The conversion module can convert the electric energy provided by the battery.

[0112] At the same time, the conversion module can also be connected to the first processing sub-unit (i.e. the above-mentioned first DSP), the second processing sub-unit (i.e. the above-mentioned second DSP), the judgment unit (i.e. the above-mentioned MCU) and the transmission module respectively; wherein the electric energy can be converted into a 3.3V voltage and transmitted to the first processing sub-unit and the second processing sub-unit for power supply, and the electric energy can be converted into a 3.3V or 5V voltage and transmitted to the judgment unit for power supply.

[0113] Acquisition module (i.e. Figure 5 The MIC Array in the middle can transmit the collected voice commands outside the vehicle to the first DSP (i.e. Figure 5 In DSP1), when powered, the first DSP can pre-process and enhance the voice commands outside the vehicle, and transmit the enhanced voice commands outside the vehicle to the second DSP, which can extract features from the commands under power supply, obtain target voice commands, and transmit them to the MCU;

[0114] The MCU can determine whether it is a preset control instruction under the power supply. If so, it will transmit the command to the transmission module (i.e. Figure 5 LIN and BLE Optional) to the digital key terminal controller (i.e. Figure 5 BNCM), so that the digital key terminal controller controls the device to be controlled (i.e. Figure 5 mid and rear tailgate motors, etc.).

[0115] It should be emphasized that when the wake-up word wake-up function is provided in this embodiment, it can be specifically implemented by the above-mentioned first DSP to determine whether there is a preset wake-up word in the audio outside the vehicle, and it can also be implemented by the second DSP, and it can also be implemented by the MCU. It can be set according to the actual situation, and this embodiment does not limit this.

[0116] Continue based on Figure 3 , a third embodiment of the external vehicle voice control device of the present application is proposed.

[0117] In order to achieve voice enhancement, in this embodiment, the recognition module is also used to perform beamforming on the pre-processed external vehicle voice command to determine the collection angle of the external vehicle voice command;

[0118] The recognition module is also used to enhance the pre-processed external vehicle voice command when the collection angle is within a preset angle range.

[0119] It should be noted that this embodiment can be implemented by adaptive beamforming when performing voice enhancement. The above-mentioned acquisition angle can be the angle of the user who issues the voice command outside the car relative to the acquisition module. The above-mentioned preset angle range can be the range of acquisition angles that allow the execution of commands, which can be set according to actual conditions. For example, the range near the main driver's door of the car can be used as the above-mentioned preset angle range.

[0120] In actual use, the first processing sub-unit can be used to perform beamforming on the outside-vehicle voice commands. Since the acquisition module in this embodiment can be implemented using a microphone array, the angle of the outside-vehicle voice commands relative to the acquisition module can be determined by the time difference, phase difference and amplitude of the outside-vehicle voice commands received by each microphone, as the above-mentioned acquisition angle.

[0121] For ease of understanding, refer to Figure 6 , Figure 6 This is a schematic diagram of beamforming in the third embodiment of the vehicle exterior voice control device of this application. Figure 6 As shown, after obtaining the acquisition angle, it can be determined whether the acquisition angle is within the preset angle range (i.e. Figure 6 The first processing sub-unit can enhance the voice command outside the vehicle and suppress the audio outside the vehicle that is outside the preset angle range (i.e., Figure 6 The noise is suppressed and muted), thus reducing noise interference.

[0122] Furthermore, considering that the car owner may not always issue outside-car voice commands within the preset angle range, in this embodiment, the recognition module is also used to determine the number of occurrences of the preset interval range corresponding to the collection angle when the collection angle is not within the preset angle range.

[0123] It should be noted that the above-mentioned preset interval range can be a range for dividing the area around the car. In this embodiment, the area around the car other than the above-mentioned preset angle range can be divided; for example, the preset angle range is the range corresponding to the main driver's door of the car, and then the area other than the range corresponding to the main driver's door of the car can be divided. Specifically, the division can be performed according to different directions. For example, if the main driver's door of the car is the left front door, the area corresponding to the left rear door of the car, the area corresponding to the right front door of the car, the area corresponding to the right rear door of the car, the area corresponding to the front of the car, and the area corresponding to the rear tailgate of the car can be respectively used as a preset interval range.

[0124] Furthermore, when the first processing subunit determines that the collection angle is not within the preset angle range, that is, not within the range of the left front door of the car, it can first determine which preset interval range it is in based on the collection angle, and obtain the number of occurrences of the preset interval range within a certain period of time, for example, the number of occurrences within a month.

[0125] The identification module is further configured to update the preset angle range when the number of occurrences reaches a preset number threshold corresponding to the preset interval range.

[0126] It is understandable that in this embodiment, different preset times thresholds can be set for different preset intervals, and can be set specifically according to the probability of the car owner issuing a command. For example, the preset times threshold corresponding to the range of the left rear door of the car, the preset times threshold corresponding to the range of the right front door of the car, the preset times threshold corresponding to the range of the right rear door of the car, and the preset times threshold corresponding to the range in front of the car can all be set to 10 times, because the probability of the car owner issuing a command within these ranges is low, so the preset times threshold is set higher; the preset times threshold corresponding to the range of the rear door of the car can be set to 5 times, because the probability of the car owner issuing a command within this range is high.

[0127] Furthermore, in actual use, the first processing sub-unit can determine whether the number of occurrences reaches the preset number threshold corresponding to the preset interval range; if not, it can be said that the car owner has no need to issue instructions within the range, and the preset angle range will not be updated; if reached, it can be said that the car owner may have a need to issue instructions within the range, for example, there is a need to issue instructions within the range of the car's tailgate, and the preset angle range can be updated so that the preset angle range can include the preset interval range, that is, including the range of the car's tailgate.

[0128] Furthermore, considering that the needs of the car owners in different preset ranges may be different, when the preset angle range is updated, the identification module is further used to determine the corresponding range update strategy based on the preset range when the number of occurrences reaches the preset number threshold corresponding to the preset range;

[0129] The identification module is further used to update the preset angle range according to the corresponding range update strategy.

[0130] It should be understood that in this embodiment, different range update strategies may be set for different preset interval ranges, and the range update strategy may be a strategy for determining the range update size according to different ranges.

[0131] For example, the range update strategies corresponding to the range of the left rear door of the car, the range of the right front door of the car, the range of the right rear door of the car, and the range in front of the car can all be set to partial range update, and the range update strategy corresponding to the range of the rear tail door of the car can be set to full range update. That is, in actual use, when the number of occurrences corresponding to the range of the right front door of the car reaches the corresponding preset number threshold, it can be explained that the owner has the need to issue instructions within the range of the right front door of the car, and then the part of the range in the preset range interval (i.e., the range of the right front door of the car) (specifically, it can be in accordance with a certain preset proportion, etc.) as the above-mentioned preset angle range, and the size of the specific preset proportion can be set according to the actual situation, and this embodiment does not limit this. When the number of occurrences corresponding to the range of the rear tail door of the car reaches the corresponding preset number threshold, it can be explained that the owner needs to issue instructions within the range of the rear tail door of the car, and then the entire range of the rear tail door of the car (i.e., the entire proportion) can be used as the above-mentioned preset angle range, so that the next time the current angle is detected to be at the rear tail door of the car, it can also be recognized, thereby improving the user experience.

[0132] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further provides a car, which includes the external voice control device as described above.

[0133] Other embodiments or specific implementation methods of the electronic device of the present application can refer to the embodiments of the above-mentioned external vehicle voice control devices, which will not be repeated here.

[0134] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An external vehicle voice control device, characterized in that: The device comprises: a collection module, an identification module and a power supply module; The identification module is connected to the acquisition module and the power supply module respectively, and the identification module is also connected to the device to be controlled through the digital key terminal controller of the car; The power supply module is used to supply power to the acquisition module and the identification module; The acquisition module is used to transmit the collected external vehicle voice commands to the recognition module; The recognition module is used to transmit the generated control signal to the digital key terminal controller when the external voice command is a preset control command, so that the digital key terminal controller controls the corresponding device to be controlled.

2. The device according to claim 1, characterized in that The recognition module is further used to pre-process the external voice command, wherein the pre-processing includes at least one of pre-emphasis processing, frame processing, windowing processing and noise reduction processing; The recognition module is further used to perform voice enhancement on the pre-processed external vehicle voice command and to perform feature extraction on the voice-enhanced external vehicle voice command to obtain a target voice command; The recognition module is also used to transmit the generated control signal to the digital key terminal controller when the target voice command is a preset control command.

3. The device according to claim 2, characterized in that The identification module includes: a processing unit and a judgment unit; The processing unit is connected to the power supply module, the acquisition module and the judgment unit respectively, and the judgment unit is also connected to the power supply module and the digital key terminal controller; The processing unit is used to preprocess the external vehicle voice command, perform voice enhancement on the preprocessed external vehicle voice command, and perform feature extraction on the voice enhanced external vehicle voice command to obtain a target voice command; The judgment unit is used to transmit the generated control signal to the digital key terminal controller when the target voice command is a preset control command.

4. The device according to claim 3, characterized in that The processing unit comprises: a first processing subunit and a second processing subunit; The first processing subunit is connected to the power supply module, the acquisition module, the judgment unit and the second processing subunit respectively, and the second processing subunit is also connected to the power supply module and the judgment unit; The first processing subunit is used to pre-process the external vehicle voice command and perform voice enhancement on the pre-processed external vehicle voice command; The second processing subunit is used to extract features of the external vehicle voice command after voice enhancement to obtain the target voice command.

5. The device according to claim 2, characterized in that The recognition module is further used to perform beamforming on the pre-processed external vehicle voice command to determine the collection angle of the external vehicle voice command; The recognition module is also used to enhance the pre-processed external vehicle voice command when the collection angle is within a preset angle range.

6. The device according to claim 5, characterized in that The identification module is further configured to determine the number of occurrences of the preset interval range corresponding to the acquisition angle when the acquisition angle is not within the preset angle range; The identification module is further configured to update the preset angle range when the number of occurrences reaches a preset number threshold corresponding to the preset interval range.

7. The device according to claim 6, characterized in that The identification module is further configured to determine a corresponding range update strategy based on the preset interval range when the number of occurrences reaches a preset number threshold corresponding to the preset interval range; The identification module is further used to update the preset angle range according to the corresponding range update strategy.

8. The device according to claim 1, characterized in that The acquisition module is further used to transmit the collected external audio to the recognition module; The recognition module is further configured to switch the current working mode from the low power consumption mode to the normal working mode when a preset voiceprint exists in the external audio of the vehicle; The identification module is further used to determine whether the external vehicle voice command is a preset control command when the current working mode is the normal working mode; The identification module shown is also used to transmit the generated control signal to the digital key terminal controller when the external voice command is a preset control command.

9. The device according to claim 1, characterized in that The device further comprises: a transmission module; The transmission module is connected to the identification module and the digital key terminal controller respectively; The transmission module is used to transmit the control signal to the digital key terminal controller when receiving the control signal.

10. An automobile, characterized in that: The automobile comprises the exterior vehicle voice control device according to any one of claims 1 to 9.

Images