Voice processing method, device, storage medium and electronic device

Abstract

The disclosed embodiments disclose a voice processing method, device, storage medium and electronic device. The voice processing method is applied to a cloud server, including: receiving a vehicle identification and multiple groups of sound data containing interaction request instructions sent by a vehicle processor; calling the corresponding recorded voiceprint data in a voiceprint database based on the vehicle identification, and comparing the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores the recorded voiceprint data of multiple users; processing the sound data with successful voiceprint comparison to obtain a processing result; and sending the processing result to the vehicle processor. Through the above technical solution, the sound data is processed on the cloud server, which reduces the calculation amount of the vehicle processor, solves the problem of vehicle system jamming, and through voiceprint comparison, the sound data of non-recorded voiceprints can be filtered, thereby solving the problem of false triggering of the voice system.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of data processing technology, and in particular to a speech processing method, device, storage medium, and electronic device. Background Art

[0002] As car computers are equipped with more and more functions and their systems become more and more complex, voice systems are widely used in car computers. They can help drivers reduce their dependence on the operation of in-car equipment and increase driving safety.

[0003] With the development of technology, the single-tone zone interaction solution of the car voice system is relatively mature. However, when multiple people in the car speak at the same time, the car system will be stuck, resulting in voice recognition errors or no response; in addition, sound sources such as driving noise, car multimedia sound, and conversations between drivers and passengers will cause the voice system to be mistakenly awakened and commands to be mistakenly triggered. Summary of the invention

[0004] The embodiments of the present disclosure provide a voice processing method, device, storage medium and electronic device to solve the problems of vehicle system freezing and voice system false triggering.

[0005] In a first aspect, an embodiment of the present disclosure provides a voice processing method, which is applied to a cloud server, comprising:

[0006] Receiving a vehicle identification and multiple groups of voice data containing interaction request instructions sent by a vehicle processor;

[0007] Based on the vehicle identification, calling corresponding recorded voiceprint data in a voiceprint database, and comparing the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores recorded voiceprint data of multiple users;

[0008] Process the voice data that has successfully matched the voiceprint to obtain a processing result;

[0009] The processing result is sent to the vehicle computer processor.

[0010] In a second aspect, the embodiment of the present disclosure further provides a voice processing method, which is applied to a vehicle processor, comprising:

[0011] Acquire multiple groups of sound data, and if the sound data includes an interaction request instruction, send the vehicle identification and the sound data including the interaction request instruction to a cloud server;

[0012] The cloud server is used to call the corresponding recorded voiceprint data in the voiceprint database based on the vehicle identification, compare the voiceprint data corresponding to the voice data containing the interactive request instruction with the recorded voiceprint data, process the voice data with successful voiceprint comparison, and obtain a processing result. The voiceprint database pre-stores the recorded voiceprint data of multiple users;

[0013] Receive the processing result sent by the cloud server.

[0014] In a third aspect, the present disclosure also provides a speech processing device, which is applied to a cloud server, including:

[0015] A data receiving module, used for receiving a vehicle identification and multiple groups of sound data containing interaction request instructions sent by the vehicle processor;

[0016] a voiceprint comparison module, configured to call corresponding recorded voiceprint data in a voiceprint database based on the vehicle identification, and compare the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores recorded voiceprint data of multiple users;

[0017] A data processing module is used to process the voice data that has been successfully matched with the voiceprint to obtain a processing result;

[0018] The result sending module is used to send the processing result to the vehicle computer processor.

[0019] In a fourth aspect, the present disclosure also provides a speech processing device, which is applied to a vehicle processor, including:

[0020] A data sending module, used for acquiring multiple groups of sound data, and sending the vehicle identification and the sound data containing the interaction request instruction to the cloud server when the sound data contains the interaction request instruction;

[0021] The cloud server is used to call the corresponding recorded voiceprint data in the voiceprint database based on the vehicle identification, compare the voiceprint data corresponding to the voice data containing the interactive request instruction with the recorded voiceprint data, process the voice data with successful voiceprint comparison, and obtain a processing result. The voiceprint database pre-stores the recorded voiceprint data of multiple users;

[0022] The result receiving module is used to receive the processing result sent by the cloud server.

[0023] In a fifth aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0024] one or more processors;

[0025] a storage device for storing one or more programs,

[0026] When the one or more programs are executed by the one or more processors, the one or more processors implement the speech processing method as described in any one of the embodiments of the present disclosure.

[0027] In a sixth aspect, the embodiments of the present disclosure further provide a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a speech processing method as described in any one of the embodiments of the present disclosure.

[0028] According to the technical solution of the disclosed embodiment, the cloud server processes the sound data on the cloud server by receiving the vehicle identification and multiple groups of sound data containing interaction request instructions sent by the vehicle processor; further, based on the vehicle identification, the corresponding recorded voiceprint data is called in the voiceprint database, and the voiceprint data corresponding to the sound data is compared with the recorded voiceprint data, so that the sound data of non-recorded voiceprints can be filtered; the sound data with successful voiceprint comparison is processed to obtain a processing result, and the processing result of the cloud server is sent to the vehicle processor, thereby reducing the data processing amount of the vehicle processor, thereby solving the problem of vehicle system freeze. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0030] Figure 1 is a flowchart of a speech processing method provided by an embodiment of the present disclosure;

[0031] Figure 2 is a flowchart of a speech processing method provided by an embodiment of the present disclosure;

[0032] Figure 3 is a flowchart of a speech processing method provided by an embodiment of the present disclosure;

[0033] Figure 4 is a flowchart of a speech processing method provided by an embodiment of the present disclosure;

[0034] Figure 5 is a structural diagram of a speech processing system provided by an embodiment of the present disclosure;

[0035] Figure 6 is a structural schematic diagram of a speech processing device provided by an embodiment of the present disclosure;

[0036] Figure 7 is a structural schematic diagram of a speech processing device provided by an embodiment of the present disclosure;

[0037] Figure 8 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain 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 construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0039] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0040] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0041] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0042] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0043] Figure 1 This is a flow chart of a voice processing method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is suitable for the situation of multi-zone voice interaction in a locomotive. The method can be executed by a voice processing device provided by an embodiment of the present disclosure. The voice processing device can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a cloud server. Figure 1 , the method of this embodiment includes:

[0044] S110, receiving a vehicle identification and multiple groups of sound data containing interaction request instructions sent by a vehicle processor.

[0045] In this embodiment, the cloud server and the vehicle processor can be connected through wireless communication. The vehicle processor refers to a vehicle processing device installed in the vehicle terminal, which can be used to obtain the vehicle identification and multiple groups of sound data containing interaction request instructions, and send the vehicle identification and multiple groups of sound data containing interaction request instructions to the cloud server. Among them, the vehicle identification can be an identification representing the vehicle identity information, which is unique. Exemplarily, the vehicle identification can be the vehicle VIN (Vehicle Identification Number) code. Sound data refers to audio data collected by a microphone in the car, which can include but is not limited to driving noise, multimedia sound in the car, and conversations of drivers. Sound data containing interaction request instructions refers to sound data containing interaction request instructions for controlling the actions of in-vehicle devices. The interaction request instruction can be a wake-up instruction or a wake-up-free instruction. Exemplarily, the interaction request instruction can be "Hello, play music", "Navigate to location A", etc.

[0046] Furthermore, the cloud server can receive the vehicle identification and multiple groups of sound data containing interaction request instructions sent by the vehicle processor. It is understandable that the cloud server has stronger computing processing capabilities than the vehicle processor, and processing sound data through the cloud server can reduce the jamming of the vehicle.

[0047] S120. Call corresponding recorded voiceprint data in a voiceprint database based on the vehicle identification, and compare the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores recorded voiceprint data of multiple users.

[0048] The voiceprint database may pre-store recorded voiceprint data of multiple users, where the recorded voiceprint data refers to voiceprint data pre-recorded by the user.

[0049] Specifically, the recorded voiceprint data and the vehicle identification can be associated and stored in the voiceprint database, and the vehicle identification can be matched with the same vehicle identification in the voiceprint database to obtain one or more recorded voiceprint data corresponding to the vehicle identification. The voiceprint data corresponding to the multiple sound data are compared with the recorded voiceprint data. If the voiceprint data corresponding to the sound data is the same as the voiceprint of the recorded voiceprint data, it indicates that the interaction request instruction is issued by the vehicle user and is a valid interaction instruction. Among them, the vehicle user may refer to the user who has recorded the voiceprint data in advance, such as the car owner, the car owner's family, etc. If the voiceprint data corresponding to the sound data is different from the voiceprint of the recorded voiceprint data, it indicates that the interaction request instruction is not issued by the vehicle user and is an invalid interaction instruction, then the voice processing is stopped. In this embodiment, the voiceprint comparison can effectively avoid the occurrence of temporary passengers accidentally waking up or triggering the voice system.

[0050] S130: Process the voice data with successful voiceprint matching to obtain a processing result.

[0051] In the case where the voiceprint comparison is successful, that is, when the voiceprint data corresponding to the voice data is the same as the voiceprint of the recorded voiceprint data, the successfully compared voice data can be further processed to complete the processing of the voice data. Exemplarily, the successfully compared voice data can be subjected to natural language processing operations such as feature extraction, semantic recognition, and noise reduction processing to obtain the user's control intention, and the user's control intention can be judged and analyzed to obtain the corresponding processing result. The processing result can include a variety of judgment results, such as sending an execution instruction, sending a failure reason, etc.

[0052] S140: Send the processing result to the vehicle computer processor.

[0053] In the disclosed embodiment, the cloud server may send the processing result to the vehicle processor, and the vehicle processor may receive the processing result and control the equipment in the vehicle to perform corresponding actions according to the processing result.

[0054] According to the technical solution of the disclosed embodiment, the cloud server processes the sound data on the cloud server by receiving the vehicle identification and multiple groups of sound data containing interaction request instructions sent by the vehicle processor; further, based on the vehicle identification, the corresponding recorded voiceprint data is called in the voiceprint database, and the voiceprint data corresponding to the sound data is compared with the recorded voiceprint data, so that the sound data of non-recorded voiceprints can be filtered; the sound data with successful voiceprint comparison is processed to obtain a processing result, and the processing result of the cloud server is sent to the vehicle processor, thereby reducing the data processing amount of the vehicle processor, thereby solving the problem of vehicle system freeze.

[0055] refer to Figure 2 , Figure 2The flowchart of the voice processing method provided in the embodiment of the present disclosure is as follows. The method of this embodiment can be combined with the various optional schemes in the voice processing method provided in the above embodiment. The voice processing method provided in this embodiment is further optimized. Optionally, the processing of the sound data with successful voiceprint matching to obtain the processing result includes: performing semantic recognition on the sound data with successful voiceprint matching to obtain user intention information; determining the user intention information to obtain the processing result.

[0056] like Figure 2 , the method of this embodiment includes:

[0057] S210: Receive a vehicle identification and multiple groups of sound data containing interaction request instructions sent by a vehicle processor.

[0058] S220: based on the vehicle identification, call the corresponding recorded voiceprint data in the voiceprint database, and compare the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores the recorded voiceprint data of multiple users.

[0059] S230: Perform semantic recognition on the voice data that has been successfully matched with the voiceprint to obtain user intention information.

[0060] S240: Determine the user intention information and obtain a processing result.

[0061] S250: Send the processing result to the vehicle computer processor.

[0062] In this embodiment, the method of semantically recognizing the sound data may include but is not limited to a rule method based on a dictionary and a template, and a method of discriminating the user's intention based on a classification model. Specifically, the sound data may be converted into text information containing the user's intention through semantic recognition, that is, the user's intention information may be text information. The user's intention information may be information that the user is interested in, and according to the user's intention information, the device in the vehicle may be controlled to perform an action corresponding to the user's intention information.

[0063] For example, the interactive request instruction in the sound data may be "play Jay Chou's "Rice Fragrance". Through semantic recognition, key information such as the singer "Jay Chou" and the song title "Rice Fragrance" in the interactive request instruction can be identified, and the key information can be used as user intent information.

[0064] Furthermore, the cloud server can determine the user intention information and obtain the processing result.

[0065] It is understandable that the number of user intention information can be multiple, that is, when multiple users in the car issue different interaction request instructions, the cloud server can obtain multiple user intention information based on the multiple interaction request instructions. In order to ensure the rationality of the user intention information, it is necessary to judge the user intention information to obtain the corresponding processing results.

[0066] On the basis of the above embodiments, the processing result includes an execution instruction, and the user intention information is judged to obtain a processing result, including: if the user intention information is to control the vehicle system, then an execution instruction corresponding to the vehicle system is sent to the vehicle processor; wherein the vehicle processor is also used to control the vehicle system to perform corresponding actions based on the execution instruction corresponding to the vehicle system.

[0067] The execution instruction refers to an instruction that can control the equipment in the vehicle to perform corresponding actions. The vehicle system refers to the system controlled by the vehicle processing device. The functions of the vehicle system include but are not limited to navigation, playing music, playing videos, changing system settings, etc.

[0068] Exemplarily, if the user intention information is to play music, an instruction to play music is determined based on the user intention information, and the instruction to play music is sent to the vehicle computer processor; the vehicle computer processor can control the vehicle computer system to play music based on the instruction to play music.

[0069] Based on the above embodiments, the method also includes: if the user intention information is not to control the vehicle system, a secondary judgment is made on the user intention information; and if the user intention information obtained by the secondary judgment is to control the vehicle system, an execution instruction corresponding to the vehicle system is sent to the vehicle processor; wherein the vehicle processor is also used to send the execution instruction corresponding to the vehicle system to the controller, and the controller is used to control the vehicle system to perform corresponding actions.

[0070] Among them, the vehicle system refers to the overall control system of the vehicle, through which the windows, sunroof, air conditioning, trunk and other equipment can be controlled.

[0071] For example, if the user intention information is to open the main driver's window, the user intention information is not to control the vehicle system, but to control the vehicle system. Further, according to the user intention information, it is determined as an instruction to open the main driver's window, and the instruction to open the main driver's window is sent to the vehicle processor; the vehicle processor can send the instruction to open the main driver's window to the controller to control the main driver's window to open.

[0072] Based on the above embodiments, before obtaining the execution instruction corresponding to the vehicle system and sending it to the vehicle processor, the method also includes: obtaining vehicle configuration information corresponding to the vehicle identification based on the vehicle identification; and judging whether the user intention information meets the instruction execution conditions based on the vehicle configuration information corresponding to the vehicle identification.

[0073] The vehicle configuration information refers to the information of the equipment configured in the vehicle. It is understandable that the vehicle configuration can be divided into high-end, medium-end, low-end and other levels, and the number of equipment in vehicles of different configuration levels is also different. Optionally, if the vehicle configuration information contains the number of execution devices to be controlled in the user intention information, the instruction execution condition is met.

[0074] For example, a high-end car may include four car screens, namely the central control screen, the co-pilot screen, the left rear screen, and the right rear screen; a mid-end car may include two car screens, namely the central control screen and the co-pilot screen; and a low-end car may include one central control screen. When the user's intention information is "play Daoxiang" or "play Qilixiang", if the vehicle configuration information is a low-end car, the vehicle cannot play two songs at the same time and does not meet the command execution conditions; if the vehicle configuration information is a mid-end or high-end car, the vehicle can play two songs at the same time and meets the command execution conditions.

[0075] According to the technical solution of the disclosed embodiment, the cloud server obtains user intention information by performing semantic recognition on the sound data with successful voiceprint matching, and makes a judgment on the user intention information, thereby ensuring the rationality of the user intention information.

[0076] Figure 3 This is a flow chart of a voice processing method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is suitable for multi-zone voice interaction in a vehicle. The method can be executed by a voice processing device provided by an embodiment of the present disclosure. The voice processing device can be implemented in the form of software and / or hardware, and optionally, by a vehicle processor. Figure 3 , the method of this embodiment includes:

[0077] S310: Acquire multiple groups of sound data, and when the sound data contains an interaction request instruction, send the vehicle identification and the sound data containing the interaction request instruction to the cloud server.

[0078] Among them, the cloud server is used to call the corresponding recorded voiceprint data in the voiceprint database based on the vehicle identification, compare the voiceprint data corresponding to the sound data containing the interaction request instruction with the recorded voiceprint data, process the sound data with successful voiceprint comparison, and obtain the processing result. The voiceprint database pre-stores the recorded voiceprint data of multiple users.

[0079] S320: Receive the processing result sent by the cloud server.

[0080] Based on the above embodiment, before obtaining multiple sets of sound data, the method includes: obtaining the vehicle identification and the sound data entered by the user, and sending the vehicle identification and the sound data entered by the user to a cloud server; wherein the cloud server is used to generate recorded voiceprint data based on the sound data entered by the user, and associate the recorded voiceprint data with the vehicle identification and store it in a voiceprint database.

[0081] For example, when the car-machine network is activated, the vehicle identification and the voice data entered by the user can be sent to the cloud server, and the cloud server creates a vehicle account based on the vehicle identification; when the vehicle is used for the first time, the car screen displays and guides the user to enter the voice data, and the voice data can be entered in multiple groups; in addition, the car screen has a voiceprint data change entry, which can be clicked to update the stored voiceprint data. When the car screen records the voice data, the host calls the sound collection module and calls the microphone to collect the user's voice; and uploads the collected voice data to the cloud server, which processes the voice data to generate voiceprint data and binds it to the vehicle identification, and stores it in the voiceprint database.

[0082] According to the technical solution of the disclosed embodiment, the vehicle processor obtains multiple groups of sound data, and when the sound data contains interaction request instructions, the vehicle identification and the sound data containing the interaction request instructions are sent to the cloud server, so that the sound data is processed in the cloud server; further, based on the vehicle identification, the corresponding recorded voiceprint data is called in the voiceprint database, and the voiceprint data corresponding to the sound data is compared with the recorded voiceprint data, so that the sound data of the non-recorded voiceprint can be filtered; the sound data with successful voiceprint comparison is processed to obtain the processing result, and the processing result of the cloud server is sent to the vehicle processor, thereby reducing the data processing amount of the vehicle processor, thereby solving the problem of vehicle system jamming.

[0083] refer to Figure 4 , Figure 4 The flowchart of the speech processing method provided by the embodiment of the present disclosure is as follows. Based on the above embodiment, this embodiment provides a preferred example to specifically illustrate the speech processing method of the above embodiment. The speech processing method can be applied to a speech processing system, such as Figure 5As shown, the voice processing system includes: a vehicle computer processing device (hereinafter referred to as the vehicle computer), a vehicle computer screen display device (hereinafter referred to as the vehicle computer screen), a power amplifier, a microphone input device (hereinafter referred to as the microphone), a speaker output device (hereinafter referred to as the speaker), and a cloud storage processing (hereinafter referred to as the cloud). The vehicle computer can be configured as 1 or 2 according to the vehicle model; the vehicle computer screen can be configured as 1, 2 or 4 according to the vehicle model, and the two are connected through an LVDS line; one end of the power amplifier is connected to the vehicle computer, and the other end is connected to a microphone or a speaker, among which the microphones are four for the main driver, the co-driver, the left rear, and the right rear, to ensure that the voice command is correctly input; the speakers are configured as multiple according to the vehicle model to ensure the normal output of the vehicle computer sound; the cloud can store the user's vehicle model configuration, voiceprint information, etc., process voice commands, issue vehicle computer commands, etc.

[0084] like Figure 4 , the method of this embodiment includes:

[0085] Step 1: The multi-channel microphones in the multi-sound zones can collect one or more groups of sound data information, and the vehicle computer (i.e., the vehicle processor) calls the data upload interface to upload the collected sound data to the cloud (i.e., the cloud server) for processing;

[0086] Step 2: After the cloud receives the sound data, it retrieves the voiceprint information corresponding to the VIN code from the voiceprint database for comparison. If the voiceprint data of the sound data does not match any of the voiceprint data in the library, it is deemed to be an invalid wake-up command and ignored. If the voiceprint data of the sound data matches one of the voiceprint data in the library, it is deemed to be a valid wake-up command, and the sound data is processed to obtain the user's intention (i.e., user intention information).

[0087] Step three: Analyze the user's intention to control the car system (such as navigation, music, video, system settings, etc.) or the vehicle system (such as windows, sunroof, air conditioning, trunk, etc.).

[0088] Step 4: When the user intends to control the vehicle system, the cloud obtains the vehicle configuration information through the VIN to determine whether the vehicle configuration can meet the user's intention. When the user's intention in multiple audio zones is to control the vehicle system, if there is only one execution device, the instructions are mutually exclusive.

[0089] 1) If the vehicle configuration can meet the user's intention, the cloud will send the corresponding voice command to the vehicle computer (i.e., execute the command).

[0090] Furthermore, the car computer receives the voice command sent from the cloud and determines whether the car computer meets the user's intention. If the user's intention in the co-pilot / left rear / right rear audio zone is to play music, video or other vocal actions, it is necessary to determine whether the co-pilot / left rear / right rear audio zone is connected to a Bluetooth headset. If the Bluetooth headset is connected, the car computer meets the user's intention, and the car computer executes the voice command and gives feedback; if the Bluetooth headset is not connected, the car computer does not meet the user's intention, and the reason for the failure is fed back through the voice assistant.

[0091] 2) If the vehicle configuration cannot meet the user's intention, the reason for the execution failure will be sent to the vehicle computer.

[0092] Furthermore, the vehicle computer receives the reason for the failure of the voice system execution sent from the cloud to the vehicle computer, and the vehicle computer determines whether the current central control screen voice assistant is occupied. If occupied, it will queue; if not occupied, the reason for the failure will be fed back through the central control screen voice assistant.

[0093] Step 5: When the user intends to control the vehicle system, the cloud obtains the vehicle configuration information through the VIN, determines whether the vehicle configuration can meet the user's intention, and determines whether the current vehicle configuration has an execution device to execute the user's intention - the in-vehicle controller (i.e., the controller).

[0094] 1) If the vehicle configuration information can meet the user's intention, the cloud will send the corresponding voice command to the vehicle computer; after receiving the voice command, the vehicle computer will send the command to the in-vehicle controller, receive feedback from the in-vehicle controller, and feedback the execution result through the voice assistant.

[0095] 2) If the vehicle configuration cannot meet the user's intention, the cloud will send the failure reason to the car computer. At this time, according to the car computer screen configuration information, if it is a high-end four-screen, the failure reason will be fed back in the car computer screen voice assistant corresponding to each audio zone; if it is a mid-range two-screen, the driver / passenger audio zone will feed back the failure reason in the corresponding car computer screen voice assistant, and the two rear audio zones will feed back the failure reason through the unoccupied central control screen voice assistant; if it is a low-end single-screen, all audio zones will feed back the failure reason through the unoccupied central control screen voice assistant. If the central control screen voice assistant is occupied, they will be queued.

[0096] The technical solution of the disclosed embodiment, based on the voiceprint recognition function, solves the problems of false awakening and false triggering of commands of the voice system caused by driving noise, vehicle multimedia sound and temporary passengers; further, the sound data processing and storage are transplanted to the cloud to realize simultaneous interaction of multiple audio zones to avoid vehicle jams.

[0097] Figure 6 is a structural diagram of a voice processing device provided by an embodiment of the present disclosure. The voice processing device is applied to a cloud server, such as Figure 6 As shown, the device comprises:

[0098] The data receiving module 510 is used to receive the vehicle identification and multiple groups of sound data containing interaction request instructions sent by the vehicle processor;

[0099] The voiceprint comparison module 520 is used to call the corresponding recorded voiceprint data in the voiceprint database based on the vehicle identification, and compare the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores the recorded voiceprint data of multiple users;

[0100] The data processing module 530 is used to process the voice data that has been successfully matched with the voiceprint to obtain a processing result;

[0101] The result sending module 540 is used to send the processing result to the vehicle computer processor.

[0102] In some optional implementations of the embodiments of the present disclosure, the data processing module 530 includes:

[0103] A semantic recognition unit, used to perform semantic recognition on the voice data that has successfully matched the voiceprint to obtain user intention information;

[0104] The intention judgment unit is used to judge the user intention information and obtain a processing result.

[0105] In some optional implementations of the embodiments of the present disclosure, the processing result includes an execution instruction, and the intention judgment unit is further configured to:

[0106] If the user intention information is to control the vehicle system, an execution instruction corresponding to the vehicle system is sent to the vehicle processor;

[0107] The vehicle computer processor is further used to control the vehicle computer system to execute corresponding actions based on the execution instructions corresponding to the vehicle computer system.

[0108] In some optional implementations of the embodiments of the present disclosure, the device is further used for:

[0109] If the user intention information is not to control the vehicle system, a secondary determination is performed on the user intention information, and if the user intention information obtained by the secondary determination is to control the vehicle system, an execution instruction corresponding to the vehicle system is sent to the vehicle processor;

[0110] The vehicle processor is further used to send execution instructions corresponding to the vehicle system to a controller, and the controller is used to control the vehicle system to perform corresponding actions.

[0111] In some optional implementations of the embodiments of the present disclosure, the device further includes:

[0112] A vehicle configuration information acquisition module, used to acquire the vehicle configuration information corresponding to the vehicle identification based on the vehicle identification;

[0113] The sending condition judgment module is used to judge whether the user intention information meets the instruction execution condition based on the vehicle configuration information corresponding to the vehicle identification.

[0114] In some optional implementations of the embodiments of the present disclosure, the sending condition judgment module is specifically used to:

[0115] If the vehicle configuration information includes the number of execution devices to be controlled in the user intention information, the instruction execution condition is met.

[0116] The speech processing device provided in the embodiments of the present disclosure can execute the speech processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects for executing the speech processing method.

[0117] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0118] Figure 7 is a structural diagram of a voice processing device provided by an embodiment of the present disclosure. The voice processing device is applied to a vehicle computer processor, such as Figure 7 As shown, the device comprises:

[0119] The data sending module 610 is used to obtain multiple groups of sound data, and when the sound data contains an interaction request instruction, send the vehicle identification and the sound data containing the interaction request instruction to the cloud server;

[0120] The cloud server is used to call the corresponding recorded voiceprint data in the voiceprint database based on the vehicle identification, compare the voiceprint data corresponding to the voice data containing the interactive request instruction with the recorded voiceprint data, process the voice data with successful voiceprint comparison, and obtain a processing result. The voiceprint database pre-stores the recorded voiceprint data of multiple users;

[0121] The result receiving module 620 is used to receive the processing result sent by the cloud server.

[0122] In some optional implementations of the embodiments of the present disclosure, the device is further used for:

[0123] Obtaining a vehicle identification and voice data entered by a user, and sending the vehicle identification and voice data entered by the user to a cloud server;

[0124] The cloud server is used to generate recorded voiceprint data according to the sound data recorded by the user, and associate the recorded voiceprint data with the vehicle identification and store them in the voiceprint database.

[0125] The speech processing device provided in the embodiments of the present disclosure can execute the speech processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects for executing the speech processing method.

[0126] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0127] Reference below Figure 8 , which shows an electronic device (eg, Figure 8 The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0128] like Figure 8 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0129] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0130] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0131] The electronic device provided in the embodiment of the present disclosure and the voice processing method provided in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0132] The embodiment of the present disclosure provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the speech processing method provided by the above embodiment is implemented.

[0133] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0134] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0135] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0136] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0137] Receiving a vehicle identification and multiple groups of voice data containing interaction request instructions sent by a vehicle processor;

[0138] Based on the vehicle identification, calling corresponding recorded voiceprint data in a voiceprint database, and comparing the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores recorded voiceprint data of multiple users;

[0139] Process the voice data that has successfully matched the voiceprint to obtain a processing result;

[0140] The processing result is sent to the vehicle computer processor.

[0141] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0142] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0143] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit / module does not, in some cases, constitute a limitation on the unit itself.

[0144] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0145] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0147] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0148] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A speech processing method, characterized in that: Applied to cloud servers, suitable for multi-zone voice interaction in car computers, including: Receiving a vehicle identification and multiple groups of voice data containing interaction request instructions sent by a vehicle processor; Based on the vehicle identification, calling corresponding recorded voiceprint data in a voiceprint database, and comparing the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores recorded voiceprint data of multiple users; Process the voice data that has successfully matched the voiceprint to obtain a processing result; Sending the processing result to the vehicle computer processor; The processing of the sound data with successful voiceprint matching to obtain the processing result includes: Perform semantic recognition on the voice data that has successfully matched the voiceprint to obtain user intent information; If the user intention information is to control the vehicle system, an execution instruction corresponding to the vehicle system is sent to the vehicle processor; wherein the vehicle processor is further used to control the vehicle system to perform a corresponding action based on the execution instruction corresponding to the vehicle system; When the user intention information is to control the vehicle system, the vehicle configuration information is obtained, and based on the vehicle configuration information, it is determined whether the vehicle configuration can meet the user intention, and if the vehicle configuration can meet the user intention, a corresponding voice command is sent to the vehicle processor; The vehicle computer processor is used to receive voice commands and determine whether the vehicle computer meets the user's intention. If the user's intention in the non-driver's voice zone is to make a sound, it is determined whether the non-driver's car is connected to a Bluetooth headset; if the non-driver's car is connected to a Bluetooth headset, the vehicle computer meets the user's intention, and the vehicle computer executes the voice command and gives feedback; if the non-driver's car is not connected to a Bluetooth headset, the vehicle computer does not meet the user's intention, and the reason for failure is fed back through the voice assistant.

2. The method according to claim 1, characterized in that The method further comprises: If the user intention information is not to control the vehicle system, a secondary judgment is performed on the user intention information, and if the user intention information obtained by the secondary judgment is to control the vehicle system, an execution instruction corresponding to the vehicle system is sent to the vehicle processor; wherein the vehicle processor is also used to send the execution instruction corresponding to the vehicle system to the controller, and the controller is used to control the vehicle system to perform corresponding actions.

3. The method according to claim 2, characterized in that Before obtaining and sending the execution instruction corresponding to the vehicle system to the vehicle processor, the method further includes: Acquire vehicle configuration information corresponding to the vehicle identification based on the vehicle identification; Based on the vehicle configuration information corresponding to the vehicle identification, it is determined whether the user intention information meets the instruction execution condition.

4. The method according to claim 3, characterized in that The determining whether the user intention information satisfies the instruction execution condition based on the vehicle configuration information corresponding to the vehicle identification includes: If the vehicle configuration information includes the number of execution devices to be controlled in the user intention information, the instruction execution condition is met.

5. A speech processing method, characterized in that: Applied to car processors, suitable for multi-zone voice interaction in cars, including: Acquire multiple groups of sound data, and if the sound data includes an interaction request instruction, send the vehicle identification and the sound data including the interaction request instruction to a cloud server; The cloud server is used to call the corresponding recorded voiceprint data in the voiceprint database based on the vehicle identification, compare the voiceprint data corresponding to the voice data containing the interactive request instruction with the recorded voiceprint data, process the voice data with successful voiceprint comparison, and obtain a processing result. The voiceprint database pre-stores the recorded voiceprint data of multiple users; Receiving the processing result sent by the cloud server; The processing of the sound data with successful voiceprint matching to obtain a processing result includes: performing semantic recognition on the sound data with successful voiceprint matching to obtain user intention information; if the user intention information is to control the vehicle system, obtaining an execution instruction corresponding to the vehicle system and sending it to the vehicle processor; wherein the vehicle processor is further used to control the vehicle system to perform a corresponding action based on the execution instruction corresponding to the vehicle system; The cloud server is used to obtain vehicle configuration information when the user intention information is to control the vehicle system, and determine whether the vehicle configuration can meet the user intention based on the vehicle configuration information. If the vehicle configuration can meet the user intention, the cloud server sends a corresponding voice command to the vehicle processor; The vehicle computer processor is used to receive voice commands and determine whether the vehicle computer meets the user's intention. If the user's intention in the non-driver's voice zone is to make a sound, it is determined whether the non-driver's car is connected to a Bluetooth headset; if the non-driver's car is connected to a Bluetooth headset, the vehicle computer meets the user's intention, and the vehicle computer executes the voice command and gives feedback; if the non-driver's car is not connected to a Bluetooth headset, the vehicle computer does not meet the user's intention, and the reason for failure is fed back through the voice assistant.

6. The method according to claim 5, characterized in that Before acquiring multiple sets of sound data, the method includes: Obtaining a vehicle identification and voice data entered by a user, and sending the vehicle identification and voice data entered by the user to a cloud server; The cloud server is used to generate recorded voiceprint data according to the sound data recorded by the user, and associate the recorded voiceprint data with the vehicle identification and store them in the voiceprint database.

7. A speech processing device, characterized in that: Applied to cloud servers, suitable for multi-zone voice interaction in car computers, including: A data receiving module, used for receiving a vehicle identification and multiple groups of sound data containing interaction request instructions sent by the vehicle processor; a voiceprint comparison module, configured to call corresponding recorded voiceprint data in a voiceprint database based on the vehicle identification, and compare the voiceprint data corresponding to the sound data with the recorded voiceprint data, wherein the voiceprint database pre-stores recorded voiceprint data of multiple users; A data processing module is used to process the voice data that has been successfully matched with the voiceprint to obtain a processing result; A result sending module, used for sending the processing result to the vehicle computer processor; The data processing module is specifically used for: performing semantic recognition on the sound data successfully matched with the voiceprint to obtain user intention information; if the user intention information is to control the vehicle system, then obtaining an execution instruction corresponding to the vehicle system and sending it to the vehicle processor; wherein the vehicle processor is further used for controlling the vehicle system to perform corresponding actions based on the execution instruction corresponding to the vehicle system; When the user intention information is to control the vehicle system, the vehicle configuration information is obtained, and based on the vehicle configuration information, it is determined whether the vehicle configuration can meet the user intention, and if the vehicle configuration can meet the user intention, a corresponding voice command is sent to the vehicle processor; The vehicle computer processor is used to receive voice commands and determine whether the vehicle computer meets the user's intention. If the user's intention in the non-driver's voice zone is to make a sound, it is determined whether the non-driver's car is connected to a Bluetooth headset; if the non-driver's car is connected to a Bluetooth headset, the vehicle computer meets the user's intention, and the vehicle computer executes the voice command and gives feedback; if the non-driver's car is not connected to a Bluetooth headset, the vehicle computer does not meet the user's intention, and the reason for failure is fed back through the voice assistant.

8. A speech processing device, characterized in that: Applied to car processors, suitable for multi-zone voice interaction in cars, including: A data sending module, used for acquiring multiple groups of sound data, and sending the vehicle identification and the sound data containing the interaction request instruction to the cloud server when the sound data contains the interaction request instruction; The cloud server is used to call the corresponding input voiceprint data in the voiceprint database based on the vehicle identification, compare the voiceprint data corresponding to the voice data containing the interactive request instruction with the input voiceprint data, process the voice data with successful voiceprint comparison to obtain a processing result, and the voiceprint database pre-stores the input voiceprint data of multiple users; the processing of the voice data with successful voiceprint comparison to obtain a processing result includes: semantic recognition of the voice data with successful voiceprint comparison to obtain user intention information; if the user intention information is to control the vehicle system, then send the execution instruction corresponding to the vehicle system to the vehicle processor; wherein the vehicle processor is also used to control the vehicle system to perform corresponding actions based on the execution instruction corresponding to the vehicle system; A result receiving module, used to receive the processing result sent by the cloud server; The cloud server is used to obtain vehicle configuration information when the user intention information is to control the vehicle system, and determine whether the vehicle configuration can meet the user intention based on the vehicle configuration information. If the vehicle configuration can meet the user intention, the cloud server sends a corresponding voice command to the vehicle processor; The vehicle computer processor is used to receive voice commands and determine whether the vehicle computer meets the user's intention. If the user's intention in the non-driver's voice zone is to make a sound, it is determined whether the non-driver's car is connected to a Bluetooth headset; if the non-driver's car is connected to a Bluetooth headset, the vehicle computer meets the user's intention, and the vehicle computer executes the voice command and gives feedback; if the non-driver's car is not connected to a Bluetooth headset, the vehicle computer does not meet the user's intention, and the reason for failure is fed back through the voice assistant.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the speech processing method as described in any one of claims 1-4, or the speech processing method as described in any one of claims 5-6.

10. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the speech processing method as described in any one of claims 1 to 4, or the speech processing method as described in any one of claims 5 to 6 when executed by a computer processor.

Images