Voice processing method and device, electronic device and vehicle

Abstract

The present application discloses a voice processing method and device and an electronic device. The method comprises: obtaining a voice mode instruction for a call, wherein the voice mode instruction indicates a method for generating a call voice; obtaining a plurality of call voice data, wherein the plurality of call voice data are collected by voice collection modules respectively arranged at different positions of the vehicle; and processing the plurality of call voice data according to the generation method indicated by the voice mode instruction to generate output voice data. The embodiment of the present application can generate output voice data that is more suitable for the voice requirements required for the call, avoiding the problem of poor collection effect caused by only a single voice collection method in the prior art.

Description

Technical Field

[0001] The present application relates to the technical field of audio data processing, and in particular to a speech processing method and device, electronic equipment, and a vehicle. Background Art

[0002] As vehicles become more and more important in people's lives, people spend more and more time in their cars. Therefore, more and more users need to communicate with the outside world in their cars, such as by phone. Therefore, it has been proposed in the prior art to set a microphone on the vehicle to collect the user's voice, so that the user can make a call in the car without wearing a headset.

[0003] In the prior art, usually only the need for voice collection on the driver's side is considered, so a microphone is usually only set on the driver's side. For example, in existing vehicles, a microphone is usually set on the top of the driver's position, so that the microphone can be close to the driver's head and can easily collect the driver's voice. However, today, the role of vehicles in people's lives is becoming more and more important. In many cases, multiple people, such as a family or friends, travel in a vehicle at the same time, and calls are often joint calls initiated by multiple people in the car, such as family phone chats, etc. Therefore, in this case, the prior art only considers the driver's voice collection, and the voices of people in other positions in the car cannot be clearly heard by the other party, and the need for voice collection from multiple people in the car cannot be met. Summary of the invention

[0004] The embodiments of the present application provide a speech processing method and device and an electric vehicle to solve the defect of poor speech collection effect inside the vehicle in the prior art.

[0005] To achieve the above object, the present application provides a speech processing method, which is characterized by comprising:

[0006] Acquire a voice mode instruction for a call, wherein the voice mode instruction indicates a method for generating a call voice;

[0007] Acquire a plurality of call voice data, wherein the plurality of call voice data are collected by voice collection modules respectively arranged at different positions of the vehicle;

[0008] The plurality of call voice data are processed according to the generation method indicated by the voice mode instruction to generate output voice data.

[0009] The present application also provides a speech processing device, which includes:

[0010] A first acquisition module, configured to acquire a voice mode instruction for a call, wherein the voice mode instruction indicates a method for generating a call voice;

[0011] A second acquisition module is used to acquire a plurality of call voice data, wherein the plurality of call voice data are collected by voice acquisition modules respectively arranged at different positions of the vehicle;

[0012] A generating module is used to process the plurality of call voice data according to the generating method indicated by the voice mode instruction to generate output voice data.

[0013] An embodiment of the present application also provides an electronic device, comprising: a memory for storing a program; and a processor for running the program stored in the memory to execute a speech processing method as provided in an embodiment of the present application.

[0014] An embodiment of the present application also provides a vehicle, characterized in that it includes: a controller and multiple microphones, wherein the controller controls the multiple microphones to execute the voice processing method provided according to the embodiment of the present application.

[0015] The voice processing method and device, electronic device and vehicle provided in the embodiments of the present application process call voice data collected by collection modules arranged at different positions of the vehicle according to the acquired voice mode instructions indicating the call voice generation method, so that the collected voice can be processed according to the mode indicated by the voice call instruction. When all the people in the car need to talk, the requirements of multi-person voice collection in the car can be met, and the voices collected at multiple positions in the car can be output clearly, avoiding the problem of poor collection effect caused by the single voice collection method in the prior art.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0018] Figure 1 A schematic diagram of an application scenario of a speech processing method according to an embodiment of the present application;

[0019] Figure 2 A flowchart of an embodiment of a speech processing method provided in an embodiment of the present application;

[0020] Figure 3 A flowchart of another embodiment of the speech processing method provided in the embodiment of the present application;

[0021] Figure 4 A schematic diagram of the structure of an embodiment of a speech processing device provided by the present application;

[0022] Figure 5 A schematic diagram of the structure of an electronic device embodiment provided by the present application; DETAILED DESCRIPTION

[0023] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0024] In some of the processes described in the specification, claims and drawings of this application, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0025] 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 those skilled in the art without creative work are within the scope of protection of this application.

[0026] As vehicles become more and more important in people's lives, people spend more and more time in their cars. Therefore, more and more users need to communicate with the outside world in their cars, such as by phone. Therefore, it has been proposed in the prior art to set a microphone on the vehicle to collect the user's voice, so that the user can make a call in the car without wearing a headset.

[0027] In the prior art, usually only the demand for voice collection on the driver's side is considered, so usually only a microphone is set on the driver's side. For example, in existing vehicles, a microphone is usually set on the top of the driver's position, so that the microphone can be close to the driver's head and can easily collect the driver's voice. However, today, the role of vehicles in people's lives is becoming more and more important. In many cases, multiple people, such as a family or friends, travel in the vehicle at the same time, and calls are often joint calls initiated by multiple people in the vehicle, such as family phone chats, etc. Therefore, in this case, the prior art only considers the driver's voice collection and only sets a microphone on the top of the driver, which cannot meet the demand for voice collection in the vehicle.

[0028] In the prior art, a microphone is only provided on the driver's side (for example, the top) to collect the voice of the driver or even users sitting in other positions in the vehicle. On the one hand, such a voice collection scheme makes it inevitable that when the driver makes a call in the presence of other people in the vehicle, the microphone on the driver's side will collect the voices of other people in the vehicle. Since these voices are also voices and the sound frequencies are similar to those of the driver, the usual noise removal algorithm cannot remove the voices of these other people, thereby reducing the audio quality of the driver's call. In addition, when people in other positions in the vehicle initiate a call, they can only use the microphone on the top of the driver's head to collect voices. However, in this case, the microphone on the top of the driver's head is at a certain distance from other seating positions, so the voice collection effect cannot be guaranteed.

[0029] Therefore, the embodiment of the present application can provide a voice processing solution, which can be applied to, for example, a vehicle in which a voice collection module such as a microphone is arranged at at least two positions. Figure 1 As shown in Figure 1 is a schematic diagram showing an application scenario of a speech processing solution according to an embodiment of the present application. Figure 1 In the vehicle shown in , the prior art usually only sets one microphone on the top of the driver's head to collect the voices of the driver and other passengers in the car. As mentioned above, in such a single voice collection scheme, when there are multiple people in the car and the driver initiates a call at his own position, the microphone will not only collect the driver's voice, but also the voices of other passengers in the car. Although various noise reduction schemes have been proposed in the prior art, since the voices of other passengers in the car and the driver's voice are both human voices, and the space inside the vehicle is relatively narrow, the sound intensity and frequency of other people collected by the microphone set on the top of the driver's head in the prior art are very close to the intensity and frequency emitted by the driver. Therefore, even if noise reduction technology is applied, it is difficult to achieve a better voice collection effect.

[0030] In addition, when multiple people in the vehicle, such as a family or friends, want to talk together, the voice collection effect of other people will not be good because only one microphone is provided inside the vehicle and the position is far away from non-drivers.

[0031] In this regard, Figure 1 As shown in , a vehicle to which the voice processing solution according to an embodiment of the present application is applied can set multiple microphones as voice collection modules at different positions, such as the top. For example, a microphone can be set at a position corresponding to each seat on the top of the vehicle, and of course, a microphone can be set in the front row and a microphone can be set on the roof of the rear row. The embodiment of the present application has no restrictions on the setting position of the microphone, as long as multiple microphones are set at different positions inside the vehicle to collect voices at different positions.

[0032] exist Figure 1 In the vehicle scenario shown in , the driver or a passenger at another position in the vehicle can initiate a voice call request through a mobile terminal, for example, the mobile terminal is connected to the vehicle's audio system by Bluetooth or wired, and the vehicle's processing module can determine the voice output mode according to the call object of the voice call initiated by the driver or passenger. For example, when the call object of the voice call initiated by the driver or passenger is a predetermined target object, for example, when the driver or passenger initiates a voice call with family or friends, it can be determined that the call is a call that is expected to be made with the whole family or with friends, and it can be determined that the call is a call that is expected to be made with all passengers in the car. Therefore, it can be determined that the voice mode of this call is the whole car call mode, and therefore a voice mode instruction can be generated to indicate that the generation method of the output voice collected by this call is to use the voices collected by all microphones together as the output voice data of this call. In other words, the other party as the call object can hear the voices collected by the people sitting in each seat in the vehicle through the microphones corresponding to their positions in the terminal where the call is performed.

[0033] Therefore, after the call mode is determined, multiple call voice data can be collected separately during the call between people in the vehicle through the microphones arranged at different positions inside the vehicle. In an embodiment of the present application, for example, the microphones arranged corresponding to the seats of the vehicle can collect the voices of people in the corresponding seats respectively, so that the data collected by the microphones arranged at various positions of the vehicle can be output as output voices to the other party of the call according to the voice mode determined above, that is, the output voice generation method. Therefore, by generating output voice data according to the collected voice according to the voice output method determined in the above manner, all microphones can be opened to collect the voices of people in corresponding positions respectively in the scenario where all people in the vehicle need to talk, thereby ensuring the voice collection effect of the call.

[0034] Similarly, for example, it is possible to determine whether the caller is a family member through the information of the matched call partner in the address book stored in the terminal of the user initiating the call, and when the call partner of the voice call initiated by the user is not the target partner such as family or friends, only the voice data collected by the microphone at the driver's position, such as the top of the driver's head, can be enhanced, and the voice data collected by other microphones can be suppressed, thereby ensuring that the driver's voice is the strongest in the final generated output voice data, so that the other party of the call can clearly hear the driver's call voice.

[0035] In particular, in the embodiment of the present application, as the call object initiated by the driver or the passenger, the target object can be family members, friends, colleagues with close cooperation, and other closely connected people, and in the embodiment of the present application, it can be determined whether to adopt the whole car call mode according to whether the call object is such a target object, so as to allow all passengers in the car to participate in the call together. On the contrary, when the call object is not the above target object, it can be indicated that the call is a private call initiated by the driver, so it can be determined to use the driver call mode.

[0036] Therefore, according to the voice processing scheme of the embodiment of the present application, the call voice data collected by the collection modules arranged at different positions of the vehicle are processed according to the acquired voice mode instructions indicating the call voice generation method, so that the collected voice can be processed according to the mode indicated by the voice call instructions. When all the people in the car need to talk, the requirements of multi-person voice collection in the car can be met, and the voices collected at multiple positions in the car can be output as clear voice data, avoiding the problem of poor collection effect caused by the single voice collection method in the prior art.

[0037] Figure 2 This is a flow chart of an embodiment of the speech processing method provided in the present application. Figure 2 As shown, the speech processing method according to the embodiment of the present application may include:

[0038] S201, obtaining a voice mode instruction for a call.

[0039] In step S201, a voice mode instruction for a call may be obtained. In an embodiment of the present application, the voice mode instruction may indicate a method for generating a call voice. For example, in Figure 1In the scenario shown in , since multiple microphones are set at different positions in the vehicle to collect voice data, how to use the collected voice data for the final output of the voice data for the call needs to be carried out in the manner indicated by the voice mode instruction in step S201. In the embodiment of the present application, the voice mode instruction can be determined by the call object that initiates the voice call, and of course, the voice mode instruction can also be obtained by, for example, the user pressing a switch or inputting the instruction through human-computer interaction.

[0040] S202, obtaining a plurality of call voice data.

[0041] S203, processing the plurality of call voice data according to the generation method indicated by the voice mode instruction to generate output voice data.

[0042] In step S202, multiple voice collection modules arranged at different positions inside the vehicle can be used to collect multiple call voice data. The call voice data obtained in step S202 are processed according to the voice generation method indicated by the voice mode instruction obtained in step S201. For example, when the output voice generation mode indicated by the voice mode instruction obtained in step S201 only requires voice data collected at a specific position, the voice data can be enhanced and other voice data can be suppressed when the collected data of all microphones collected in step S202 are processed in step S203. For example, various existing voice enhancement algorithms or voice enhancement models can be used to enhance the voice data corresponding to a specific position in the call voice data obtained in step S202 and / or suppress the voice data at other positions and finally generate the output voice call data, so that the voice data at the position in the output voice call data will be particularly clear, greatly improving the call effect.

[0043] For example, the voice data collected by microphones corresponding to other positions can be input into a voice enhancement algorithm or model as background data together with the voice data collected by the microphone at the position to be enhanced, such as the main driver's seat. In this way, the data with the voice characteristics of the background data can be removed from the voice data collected by the microphone at the main driver's seat, thereby retaining the driver's voice as much as possible to achieve an enhancement effect on the voice data at the main driver's seat.

[0044] Therefore, according to the voice processing scheme of the embodiment of the present application, the call voice data collected by the collection modules arranged at different positions of the vehicle are processed according to the acquired voice mode instructions indicating the call voice generation method, so that the collected voice can be processed according to the mode indicated by the voice call instructions. When all the people in the car need to talk, the requirements of multi-person voice collection in the car can be met, and the voices collected at multiple positions in the car can be output as clear voice data, avoiding the problem of poor collection effect caused by the single voice collection method in the prior art.

[0045] Figure 3 A flowchart of another embodiment of the speech processing method provided in the embodiment of the present application.

[0046] like Figure 3 As shown in , the speech processing method according to the embodiment of the present application may include:

[0047] S301, obtaining object data of the call object.

[0048] S302: Generate a voice mode instruction according to the object data.

[0049] In step S301, the object data of the call object can be obtained when the user initiates a voice call, for example, by matching the object in the address book of the mobile terminal used by the user to initiate the call to obtain the object information of the call object. For example, the call object can be searched in the address book of the mobile terminal used by the user to initiate the call and the grouping information of the call object can be used to determine whether it is a family member, or it can be determined by keywords in the user conversation. Then, in step S302, a voice mode instruction for the call can be generated based on the object data. In an embodiment of the present application, the voice mode instruction can indicate the method of generating the call voice. For example, in Figure 1 In the scenario shown in , since multiple microphones are set at different positions in the vehicle to collect voice data, how to use the collected voice data to finally output the voice data for the call needs to be done in the manner indicated by the voice mode instruction in step S301.

[0050] S303, receiving a voice mode instruction input by a user.

[0051] In addition to determining the voice mode instruction according to the object data of the call object in steps S301-S302, a voice mode instruction input by the user may also be received in step S303. For example, the user may manually switch the voice mode instruction by pressing a mode switching switch, or may also input the voice mode instruction through a human-computer interaction interface provided by the center console of the vehicle.

[0052] S304, obtaining a plurality of call voice data.

[0053] In step S304, a plurality of call voice data may be collected by using a plurality of voice collection modules disposed at different locations inside the vehicle.

[0054] S305 , performing enhancement processing on the first voice data collected from the voice collection module at the driver's position to generate first processed voice data.

[0055] S306, suppressing the second voice data collected from the voice collection module at the non-driver position to generate second processed voice data.

[0056] S307: Generate output voice data according to the first processed voice data and the second processed voice data.

[0057] When the voice mode instruction obtained in step S301-S302 or S303 is a driver mode instruction, for example, when it is determined that the call object is not a family member through the information matched in the address book stored in the terminal of the user who initiated the call in step S301, the driver mode instruction can be generated in step S302, or the driver can directly switch to the driver call mode by pressing a button in step S303. Therefore, in step S305, the first voice data collected by the microphone at the driver's position, such as the top of the driver's head, can be enhanced, and in step S306, the second voice data collected by other microphones can be suppressed, and in step S307, the driver's voice data collected at the driver's position after such enhancement and the voice data of the passenger collected at other positions after suppression are used to generate output voice data, thereby ensuring that the driver's voice is the strongest in the output voice data finally generated, so that the other party can clearly hear the driver's call voice.

[0058] S308: Perform noise reduction processing on the first voice data collected from the voice collection module at the driver's position to generate first processed voice data.

[0059] S309: Perform noise reduction processing on the second voice data collected from the voice collection module at the non-driver position to generate second processed voice data.

[0060] S310, generating output voice data according to the first processed voice data and the second processed voice data.

[0061] When the voice mode instruction obtained in steps S301-S302 or S303 is a full-vehicle mode instruction, or when the user switches the mode to the full-vehicle call mode by directly pressing a button in step S303, noise reduction processing can be performed on both the voice data collected from the driver's position and the voice data collected from the non-driver's position in steps S308 and S309.

[0062] For example, when the user initiates a voice call request to a family member, it can be determined that the call is intended for the whole family to make together. Therefore, in steps S308 and S309, the voice data collected by all microphones can be subjected to noise reduction processing, and in step S310, the multiple voice data subjected to such noise reduction processing are integrated into the output voice data, so that the other party can clearly hear the voice of each person at different positions in the car.

[0063] Therefore, according to the voice processing method of the embodiment of the present application, the call voice data collected by the collection modules arranged at different positions of the vehicle are processed according to the acquired voice mode instructions indicating the call voice generation method, so that the collected voice can be processed according to the mode indicated by the voice call instructions. When all the people in the car need to talk, the requirements of multi-person voice collection in the car can be met, and the voices collected at multiple positions in the car can be output as clear voice data, avoiding the problem of poor collection effect caused by only a single voice collection method in the prior art.

[0064] Figure 4 This is a schematic diagram of the structure of an embodiment of the speech processing device provided by the present application. Figure 4 As shown in , the speech processing device according to the embodiment of the present application may include: a first acquisition module 41, a second acquisition module 42, and a generation module 43.

[0065] The first acquisition module 41 may be used to acquire a voice mode instruction for a call.

[0066] The first acquisition module 41 can acquire a voice mode instruction for a call. In an embodiment of the present application, the voice mode instruction can indicate a method for generating a call voice. For example, in Figure 1In the scenario shown in , since multiple microphones are set at different positions in the vehicle to collect voice data, how to use the collected voice data for the final output of the voice data for the call needs to be carried out according to the method indicated by the voice mode instruction obtained by the first acquisition module 41. In an embodiment of the present application, the first acquisition module 41 can obtain the object data of the call object when the user initiates a voice call, for example, by matching the object in the address book of the mobile terminal used by the user to initiate the call to obtain the object information of the call object. For example, the call object can be found in the address book of the mobile terminal where the user initiates the call and whether it is a family member can be determined based on the group information of the call object. After that, a voice mode instruction for the call can be generated according to the object data in step S302. Or the voice mode instruction input by the user can be directly received. For example, the user can manually input the switching voice mode instruction to the first acquisition module 41 by pressing, or the voice mode instruction can be input through the human-computer interaction interface provided by the center console of the vehicle.

[0067] The second acquisition module 42 can be used to acquire a plurality of call voice data.

[0068] The generating module 43 may be configured to process a plurality of call voice data according to a generating method indicated by the voice mode instruction to generate output voice data.

[0069] The second acquisition module 42 can collect multiple call voice data through multiple voice collection modules set at different positions inside the vehicle. And the acquired call voice data is processed according to the voice generation method indicated by the voice mode instruction acquired by the first acquisition module 41. For example, when the voice mode instruction acquired by the first acquisition module 41 is a driver mode instruction, a driver mode instruction can be generated, or the driver can input the driver call mode instruction by pressing a button. Therefore, the generation module 43 can enhance the first voice data collected by the microphone at the driver's position, such as the top of the driver's head, and suppress the second voice data collected by other microphones, and generate output voice data with the driver's voice data collected at the driver's position after enhancement and the passenger's voice data collected at other positions after suppression, so as to ensure that the driver's voice is the strongest in the final generated output voice data, so that the other party can clearly hear the driver's call voice.

[0070] In addition, when the voice mode instruction acquired by the first acquisition module 41 is a full-vehicle mode instruction, the generation module 43 can perform noise reduction processing on both the voice data collected from the driver's position and the voice data collected from the non-driver's position. For example, when the caller of the voice call initiated by the user is a family member, it can be determined that the call is a call that the whole family wants to make together. Therefore, the generation module 43 can perform noise reduction processing on the voice data collected by all microphones, and integrate the multiple voice data enhanced in this way into the output voice data, so that the other party can clearly hear the call voice of each person at different positions in the car.

[0071] Therefore, according to the voice processing device of the embodiment of the present application, the call voice data collected by the collection modules arranged at different positions of the vehicle are processed according to the acquired voice mode instructions indicating the call voice generation method, so that the collected voice can be processed according to the mode indicated by the voice call instructions. When all the people in the car need to talk, the requirements of multi-person voice collection in the car can be met, and the voices collected at multiple positions in the car can be output as clear voice data, avoiding the problem of poor collection effect caused by only a single voice collection method in the prior art.

[0072] The internal functions and structure of the speech processing device are described above. The device can be implemented as an electronic device. Figure 5 This is a schematic diagram of the structure of an electronic device embodiment provided by this application. Figure 5 As shown, the electronic device includes a memory 51 and a processor 52 .

[0073] The memory 51 is used to store programs. In addition to the above programs, the memory 51 can also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phone book data, messages, pictures, videos, etc.

[0074] The memory 51 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0075] The processor 52 is not limited to a central processing unit (CPU), but may also be a processing chip such as a graphics processing unit (GPU), a field programmable gate array (FPGA), an embedded neural network processor (NPU) or an artificial intelligence (AI) chip. The processor 52 is coupled to the memory 51 and executes a program stored in the memory 51. When the program is executed, the speech processing method in the above embodiment is executed.

[0076] Further, if Figure 5 As shown, the electronic device may also include: a communication component 53, a power component 54, an audio component 55, a display 56 and other components. Figure 5 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 5 Components shown.

[0077] The communication component 53 is configured to facilitate wired or wireless communication between the electronic device and other devices. The electronic device can access a wireless network based on a communication standard, such as WiFi, 3G, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component 53 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 53 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0078] The power supply component 54 provides power to various components of the electronic device. The power supply component 54 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device.

[0079] The audio component 55 is configured to output and / or input audio signals. For example, the audio component 55 includes a microphone (MIC), and when the electronic device is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 51 or sent via the communication component 53. In some embodiments, the audio component 55 also includes a speaker for outputting audio signals.

[0080] The display 56 includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0081] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0082] The present application also provides a vehicle, including: a controller and a plurality of microphones, wherein the controller controls the plurality of microphones to execute the voice processing method described in the aforementioned embodiment. The vehicle controller may be an electronic control unit or the processor 52 in the aforementioned embodiment, and the plurality of microphones may be the audio component 55 in the aforementioned embodiment.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A speech processing method, characterized in that: include: Acquire a voice mode instruction for a call, wherein the voice mode instruction indicates a method for generating a call voice, and the voice mode instruction includes at least a driver mode instruction and a vehicle mode instruction; Acquire a plurality of call voice data, wherein the plurality of call voice data are collected by voice collection modules respectively arranged at different positions of the vehicle; Processing the plurality of call voice data according to the generation method indicated by the voice mode instruction to generate output voice data; Among them, the generation method includes: processing the first call voice data collected from the voice collection module at the driver's position to generate first processed voice data; processing the second call voice data collected from the voice collection module at the non-driver position to generate second processed voice data; generating the output voice data according to the first processed voice data and the second processed voice data.

2. The speech processing method according to claim 1, characterized in that: The step of obtaining a voice mode instruction for a call includes: Get the object data of the call object; The speech mode instruction is generated based on the object data.

3. The speech processing method according to claim 1, characterized in that: The obtaining of the voice mode instruction for the call includes: receiving the voice mode instruction input by the user.

4. The speech processing method according to claim 2, characterized in that: Generating the voice mode instruction according to the object data comprises: determining the identity of the call object according to the object data; The voice mode instruction is generated according to the identity of the call object.

5. The speech processing method according to claim 4, characterized in that: The generating the voice mode instruction according to the identity of the call object comprises: When the identity of the communication object is the target object, generating a voice mode instruction indicating a full-vehicle communication mode; When the identity of the communication object is a non-target object, a voice mode instruction indicating a main driving mode is generated.

6. The speech processing method according to claim 1, characterized in that: When the voice mode instruction is a driver mode instruction, the processing of the plurality of call voice data according to the generation method indicated by the voice mode instruction to generate output voice data includes: Performing enhancement processing on the first call voice data collected from the voice collection module at the driver's position to generate first processed voice data; performing suppression processing on the second call voice data collected from the voice collection module at the non-driver position to generate second processed voice data; The first processed voice data and the second processed voice data are fused to generate output voice data.

7. The speech processing method according to claim 1, characterized in that: When the voice mode instruction is a full vehicle mode instruction, the processing of the plurality of call voice data according to the generation method indicated by the voice mode instruction to generate output voice data includes: Performing noise reduction processing on the first call voice data collected from the voice collection module at the driver's position to generate first processed voice data; Performing noise reduction processing on the second call voice data collected from the voice collection module at the non-driver position to generate second processed voice data; The first processed voice data and the second processed voice data are fused to generate output voice data.

8. A speech processing device, characterized in that: include: A first acquisition module, configured to acquire a voice mode instruction for a call, wherein the voice mode instruction indicates a method of generating a call voice, and the voice mode instruction includes at least a driver mode instruction and a vehicle mode instruction; A second acquisition module is used to acquire a plurality of call voice data, wherein the plurality of call voice data are collected by voice acquisition modules respectively arranged at different positions of the vehicle; A generating module, configured to process the plurality of call voice data according to the generating method indicated by the voice mode instruction to generate output voice data; Among them, the generation method includes: processing the first call voice data collected from the voice collection module at the driver's position to generate first processed voice data; processing the second call voice data collected from the voice collection module at the non-driver position to generate second processed voice data; generating the output voice data according to the first processed voice data and the second processed voice data.

9. An electronic device, comprising: Memory, used to store programs; A processor, configured to run the program stored in the memory to execute the speech processing method as claimed in any one of claims 1 to 6.

10. A vehicle, characterized in that: include: A controller and a plurality of microphones, wherein the controller controls the plurality of microphones to execute the speech processing method according to any one of claims 1 to 7.

Images