WO2019201304A1 - 基于人脸识别的语音处理方法及其设备 - Google Patents

基于人脸识别的语音处理方法及其设备 Download PDF

Info

Publication number
WO2019201304A1
WO2019201304A1 PCT/CN2019/083261 CN2019083261W WO2019201304A1 WO 2019201304 A1 WO2019201304 A1 WO 2019201304A1 CN 2019083261 W CN2019083261 W CN 2019083261W WO 2019201304 A1 WO2019201304 A1 WO 2019201304A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
voice
information
facial feature
vehicle
Prior art date
Application number
PCT/CN2019/083261
Other languages
English (en)
French (fr)
Inventor
陈少贵
王书克
武伦佳
Original Assignee
比亚迪股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 比亚迪股份有限公司 filed Critical 比亚迪股份有限公司
Publication of WO2019201304A1 publication Critical patent/WO2019201304A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
    • B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
    • B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
    • B60R16/0373—Voice control
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
    • B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
    • B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
    • G10L2015/227—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of the speaker; Human-factor methodology

Definitions

  • the present disclosure relates to the field of intelligent interaction technologies, and in particular, to a voice recognition method based on face recognition and a device thereof.
  • In-vehicle intelligent voice recognition is one of them.
  • a typical The application of the vehicle intelligent voice solves the problem that the driver controls the vehicle to control the multimedia and is easily distracted, which greatly liberates the driver's hands.
  • the existing in-vehicle intelligent voice functions in the market are rich and varied, and can be used for navigation settings, air conditioning control, music playback, Bluetooth telephone, window seat control, and the like.
  • key voice wake-up, voice wake-up setting, voice broadcast sound and dialect settings can be performed.
  • an intelligent in-vehicle intelligent voice service is provided for a user based on functional requirements.
  • the service mode that only satisfies the user's functional requirements limits the distance between the user and the product, and is not conducive to improving the stickiness of the user and the product.
  • the present disclosure aims to solve at least one of the technical problems in the related art to some extent.
  • the first object of the present disclosure is to provide a voice recognition method based on face recognition, which is based on different users performing different voice services, satisfies the personalized requirements of users, and improves the intelligent experience of users.
  • a second object of the present disclosure is to provide an in-vehicle intelligent voice system.
  • a third object of the present disclosure is to propose a vehicle machine apparatus.
  • the first aspect of the present disclosure provides a voice recognition method based on face recognition, including the steps of: collecting user face information on a target position in a vehicle, and extracting facial feature information of the user. Retrieving the pre-stored setting data, determining whether the voice setting information corresponding to the facial feature information can be acquired; and if it is determined that the voice setting information corresponding to the facial feature information can be acquired, the vehicle is set according to the voice setting information
  • the intelligent voice system sets a target voice service corresponding to the user to invoke the target voice service to respond to an operation instruction sent by the user.
  • the second aspect of the present disclosure provides an in-vehicle intelligent speech system, including: an extraction module, configured to collect user facial information on a target position in the vehicle, and extract facial feature information of the user; a determining module, configured to retrieve the pre-stored setting data, to determine whether the voice setting information corresponding to the facial feature information can be acquired; and the processing module, configured to: when determining that the voice setting information corresponding to the facial feature information can be acquired And setting, according to the voice setting information, a target voice service corresponding to the user to the in-vehicle intelligent voice system, to invoke the target voice service to respond to an operation instruction sent by the user.
  • a third aspect of the present disclosure provides a vehicle equipment, including: an in-vehicle camera and a central control multimedia device, wherein the in-vehicle camera is connected to the central control multimedia device, wherein the vehicle is a camera for collecting user face information on a target position in the vehicle, and transmitting the user face information to the central control multimedia device; the central control multimedia device, configured to extract the face of the user according to the The feature information is used to retrieve the pre-stored setting data, determine whether the voice setting information corresponding to the facial feature information can be acquired, and if it is determined that the voice setting information corresponding to the facial feature information can be acquired, the voice setting information is obtained. And setting a target voice service corresponding to the user, to invoke the target voice service to respond to an operation instruction sent by the user.
  • the target voice service corresponding to the user is set to the in-vehicle intelligent voice system according to the voice setting information, to invoke the target voice service to respond to the operation instruction sent by the user. Therefore, different voice services are performed based on different users, which satisfies the personalized requirements of the user and improves the intelligent experience of the user.
  • FIG. 1 is a flowchart of a voice recognition method based on face recognition according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of storage of setting data according to an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of an in-vehicle intelligent voice system according to an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of a vehicle-mounted intelligent voice system according to another embodiment of the present disclosure.
  • FIG. 5 is a flowchart of a voice recognition method based on face recognition according to another embodiment of the present disclosure.
  • FIG. 6 is a flowchart of a voice recognition method based on face recognition according to still another embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an in-vehicle intelligent voice system according to an embodiment of the present disclosure.
  • the voice service on the vehicle end only focuses on the technical service itself to implement the corresponding function, which causes the user and the product to have a sense of distance.
  • the embodiment of the present disclosure provides a voice processing method based on face recognition, which can The face recognition technology accurately identifies the user, provides different voice services for different users, satisfies the personalized needs of the user, and improves the stickiness of the user and the product.
  • FIG. 1 is a flowchart of a voice recognition method based on face recognition according to an embodiment of the present disclosure. As shown in FIG. 1, the method includes:
  • Step 101 Collect user face information on a target position in the vehicle, and extract facial feature information of the user.
  • the target location may correspond to different locations within the vehicle according to different application scenarios.
  • the target location in order to preferentially provide the driver with a superior voice service, the target location is the driver's seat position of the vehicle;
  • the co-pilot in order to avoid distracting the driver's attention, the co-pilot performs the control of the voice service, and thus, the target position is the co-pilot position of the vehicle.
  • the facial feature information of the user includes, but is not limited to, facial features information of the user, facial contour information, and the like.
  • the first example is a first example:
  • the user's face information on the in-vehicle target position is acquired in accordance with a preset period.
  • the preset period may be determined according to the processing speed of the system. The higher the processing speed of the system, the shorter the duration corresponding to the corresponding preset period.
  • the camera installed on the front end of the vehicle can be used to collect the user's face information on the target position, wherein the camera installed at the front end of the vehicle can adjust the angle and height according to the position of the user's face at the target position, Ensure that the user's face information collected is as complete as possible, improving the accuracy of recognition.
  • the preset acquisition trigger condition includes, but is not limited to, a condition that the driver may change, such as the vehicle from the parking state to the startup state, and the user's facial information is collected only after the preset acquisition trigger condition is met. The effectiveness of the acquisition is improved, and the repeated acquisition of a user's facial information is avoided, which reduces the system processing pressure.
  • the user's facial information may not be directly obtained due to insufficient light or the like. Therefore, in one embodiment of the present disclosure, before collecting the user's facial information on the in-vehicle target position, It is also possible to detect the brightness of the light in the interior environment, for example, detecting the brightness of the light in the interior environment by the light sensor, and comparing the brightness of the light with a preset threshold, wherein the preset threshold is related to the photographing device, which can be collected corresponding to the photographing device. The minimum light brightness value of the face information.
  • the comparison light is less than the preset threshold, it indicates that the current ambient light is insufficient, and it may be difficult to collect clear user's facial information, thereby starting the auxiliary lighting device for the target position, for example, opening the interior lighting system of the vehicle, etc. .
  • step 102 the pre-stored setting data is retrieved, and it is determined whether the voice setting information corresponding to the facial feature information can be acquired.
  • the voice device information includes one or a combination of information in a broadcast volume, a broadcast voice, and a broadcast dialect.
  • the manner of setting pre-stored setting data is different.
  • the user is provided with a voice setting information interface, and receiving voice setting information set by the user according to personal preference in the interface.
  • the facial image of the user may be synchronously collected to extract the facial feature information of the user, or the user may upload the photo to extract the facial feature information according to the photo uploaded by the user, and further, the face is The part feature information is stored corresponding to the corresponding voice setting information.
  • Step 103 If it is determined that the voice setting information corresponding to the facial feature information can be acquired, the target voice service corresponding to the user is set to the in-vehicle intelligent voice system according to the voice setting information, so as to invoke the target voice service to respond to the operation instruction sent by the user.
  • the manner of the operation instruction sent by the user may be any form that can be recognized, such as a text input form and a voice input form.
  • the target voice service corresponding to the user is set to the in-vehicle intelligent voice system according to the voice setting information, to invoke the target voice service response.
  • an operation instruction input by the user through the operation panel may be acquired through a screen of the in-vehicle intelligent voice system, for example, obtaining a touch operation of the preset tab by the user, or a text input operation, or the like, or
  • the microphone of the intelligent voice system acquires an operation instruction of the user's voice input.
  • voice recognition is performed on the operation instruction input by the user voice, the local voice synthesis instruction is invoked, or the response information of the cloud feedback is obtained, that is, the operation instruction input by the user can adopt local voice recognition and perform voice synthesis and the operation.
  • the voice synthesis instruction corresponding to the instruction is the response information for the operation instruction, or the voice information after the voice recognition can be sent to the cloud, so that the cloud matches according to the correspondence between the pre-stored voice information and the response message.
  • responding to the corresponding response message outputting to the user through the in-vehicle intelligent voice system, and providing the user with the voice service corresponding to the response message based on the corresponding target voice service.
  • the in-vehicle intelligent voice system is set corresponding to the user according to the voice setting information.
  • the target voice service is "Cantonese, Volume 5".
  • the operation command issued by User 1 is "Help me navigate to ##”
  • the command is sent to the cloud to obtain the corresponding navigation information fed back to the cloud.
  • the service uses the "Cantonese, Volume 5" to navigate the voice of the user based on the navigation information.
  • the in-vehicle intelligent voice system when it is determined that the voice setting information corresponding to the facial feature information does not exist, the in-vehicle intelligent voice system is called to respond to the operation instruction sent by the user according to the standard voice service set in advance according to the default setting information. User's voice service needs.
  • the user inputs a setting instruction including voice setting information, for example, receiving “I want to make a voice service belonging to me” input by the user, and querying the pre-stored setting data to determine whether the user's face is included.
  • the part feature information if it is determined that the facial feature information of the user is included, deletes the currently stored voice setting information corresponding to the facial feature information, and stores the correspondence between the voice setting information and the facial feature information, and if the judgment is not included
  • the facial feature information of the user stores the correspondence between the voice setting information and the facial feature information of the user in the setting data.
  • the module for implementing the voice recognition method based on the face recognition may be implemented in different forms according to different application scenarios, and the following examples illustrate:
  • the corresponding in-vehicle intelligent voice system is composed of the vehicle equipment 100 and the cloud 200.
  • the vehicle equipment 100 and the cloud 200 communicate with each other through the wireless network, and the related information collected by the vehicle equipment 100 is uploaded to the cloud 200.
  • the identification is performed, and the voice content recognized by the cloud 200 is sent to the vehicle equipment 100.
  • the wireless network can be 2G, 3G, 4G or future update.
  • the mobile communication technology or the vehicle is connected to the WIFI, and the communication link can be a public network or a private network.
  • FIG. 3 is a schematic structural diagram of a vehicle-mounted intelligent voice system according to an embodiment of the present disclosure.
  • the vehicle equipment 100 includes an in-vehicle camera 110 and a central control multimedia device 120.
  • the in-vehicle camera 110 is configured to collect user facial information on a target position in the vehicle, and send the user facial information to the central control multimedia device.
  • the in-vehicle camera 110 is used as a user image capturing device of the vehicle equipment 100 for collecting facial information of the user and transmitting it to the central control multimedia device 120.
  • the camera is installed in the vehicle, and the user's face can be clearly captured.
  • the camera can use a high-resolution infrared camera with an infrared light installed in the car to clearly capture the user's facial information at night or under poor lighting conditions.
  • the central control multimedia device 120 is configured to retrieve the pre-stored setting data according to the facial feature information of the extracted user, determine whether the voice setting information corresponding to the facial feature information can be acquired, and if it is determined that the voice corresponding to the facial feature information can be acquired Setting the information, the voice setting information is set to the target voice service corresponding to the user, to invoke the target voice service to respond to the operation instruction sent by the user.
  • the central control multimedia device 120 receives the facial information of the user collected by the in-vehicle camera 110, and extracts facial feature information of the user through image processing, and identifies different users in comparison with the locally stored feature data.
  • the central control multimedia device 120 has a display screen and provides a user interaction interface, and the user interaction interface is used to display related text information of the voice service, or fault prompt information.
  • the vehicle apparatus 100 may further include a microphone 130, wherein the microphone 130 is connected to the central control multimedia device 120, wherein
  • the microphone 130 is configured to receive a setting instruction that is input by the user and includes voice setting information.
  • the microphone 130 is used as a voice receiving device of the vehicle equipment 100 for receiving voice setting information input by the user, converting the audio signal of the voice setting information into a level signal, providing a signal source for voice recognition, and the microphone 130 is provided with filtering. Features to eliminate environmental noise.
  • the central control multimedia device 120 is configured to query the pre-stored setting data, determine whether the user's facial feature information is included, and if the judgment includes the facial feature information of the user, delete the currently stored voice setting information corresponding to the facial feature information, And storing the correspondence between the voice setting information and the facial feature information. If the determination does not include the facial feature information of the user, the correspondence between the voice setting information and the facial feature information of the user is stored in the setting data.
  • the vehicle apparatus 100 may further include a speaker 140, wherein the speaker 140 is connected to the central control multimedia device 120, wherein
  • the speaker 140 is configured to perform a voice response to an operation instruction input by the user voice according to the voice setting information.
  • the speaker 140 is used as a sounding device of the vehicle equipment 100 for issuing a voice synthesis command of the central control multimedia device 120, and converting the level signal of the synthesized voice command into audio information, which is a part of the intelligent voice system and the user interaction output.
  • the voice recognition method uses the method in combination with the application of the above system as an example, wherein, for convenience of description, the data center and the user personality are respectively concentrated on the pre-stored setting.
  • the voice service identification side is described.
  • the target location is the driving position.
  • FIG. 5 is a flowchart of a voice recognition method based on face recognition according to another embodiment of the present disclosure, wherein, as shown in FIG. 5, the method includes:
  • Step 201 Start a central control multimedia device.
  • the condition for starting the completion is that the multimedia functions can work normally, and the peripherals such as the car camera, the microphone, and the speaker can be called.
  • Step 202 After the central control multimedia is started, the in-vehicle camera is called to collect the driver's face information on the driver's position, and the driver's facial feature information is extracted.
  • Step 203 The user sets a setting option of the intelligent voice system, and personalizes the voice recognition system according to personal preferences, and determines setting data.
  • the voice setting can be performed using smart voice, or can be set through the setting interface on the touch screen of the central control multimedia device.
  • Step 204 The user saves the content of the smart voice system setting option, and the central control multimedia device extracts the facial facial feature information of the current user and the intelligent voice system setting data forming list, and compares the stored facial features with the same facial feature information of the user, and then determines For the same user, only the setting data is updated. If it is not the same, it is judged as a new user, and the facial feature information and the setting data storage of the new user are added to the local list.
  • the central control multimedia information cannot collect the driver facial feature information, for example, the driver seat is not occupied, the camera is blocked, and the setting data is stored, the user facial feature in the setting data list of the intelligent voice system The information is vacant, and then all the setting data for which the user's facial feature information cannot be determined is stored in the user information vacancy column.
  • FIG. 6 is a flowchart of a voice recognition method based on face recognition according to still another embodiment of the present disclosure. As shown in FIG. 6, the method includes:
  • step 301 the central control multimedia device is started.
  • the condition for starting the completion is that the multimedia functions can work normally, and the peripherals such as the car camera, the microphone, and the speaker can be called.
  • Step 302 After the central control multimedia is started, the in-vehicle camera is called to collect the driver's face information on the driver's position, and the driver's facial feature information is extracted.
  • Step 303 The central control multimedia extracts the current driver facial feature information, and retrieves and compares the local existing user setting information list. If the user information is the same, the corresponding intelligent voice system setting data is extracted, and if there is no user information, the smart voice is set.
  • the system's setting data is the default setting.
  • Step 304 According to the extracted user setting data, the central control multimedia actively sets the setting options of the intelligent voice system, and completes adaptation to different system settings of different users.
  • the central control multimedia extracts the facial feature information of the user, and if it is not in the existing setting data, the user is determined to be a new user, and the setting option of the intelligent voice system is initialized to a default value. If the setting information is extracted in the existing setting data, when the user invokes the in-vehicle intelligent voice system, the user can set the wake-up word set by the user, and when the smart voice function is awakened, the user-set name is answered, including the broadcast volume and the broadcast sound. , broadcast dialects, etc., are in line with the user's own set of needs.
  • the face recognition-based voice processing method of the embodiment of the present disclosure collects user face information on a target position in the vehicle, extracts facial feature information of the user, retrieves pre-stored setting data, and determines whether the face can be acquired. If the voice setting information corresponding to the feature information is determined, the voice setting information corresponding to the facial feature information is obtained, and the target voice service corresponding to the user is set to the in-vehicle intelligent voice system according to the voice setting information, to invoke the target voice service response.
  • the operation instruction sent by the user Therefore, different voice services are performed based on different users, which satisfies the personalized requirements of the user and improves the intelligent experience of the user.
  • FIG. 7 is a schematic structural diagram of an in-vehicle intelligent speech system according to an embodiment of the present disclosure. As shown in FIG. 7, the system includes an extraction module 1100 and a determination. Module 1200 and processing module 1300.
  • the extraction module 1100 is configured to collect user facial information on a target position in the vehicle, and extract facial feature information of the user.
  • the extraction module 1100 is specifically configured to collect user facial information on a target position in the vehicle according to a preset period; or, to detect whether the preset acquisition trigger condition is met, and if the detection meets the preset collection.
  • the trigger condition is used to collect the user's face information on the target position in the car.
  • the determining module 1200 is configured to retrieve the pre-stored setting data, and determine whether the voice setting information corresponding to the facial feature information can be acquired.
  • the processing module 1300 is configured to: when determining that the voice setting information corresponding to the facial feature information is acquired, set a target voice service corresponding to the user to the in-vehicle intelligent voice system according to the voice setting information, to invoke the target voice service to respond to the user Operation instructions.
  • the processing module 1300 is further configured to: when determining that the voice setting information corresponding to the facial feature information does not exist, call the in-vehicle intelligent voice system to respond to the user in advance according to the standard voice service set by the default setting information.
  • the in-vehicle intelligent speech system of the embodiment of the present disclosure collects user facial information on a target position in the vehicle, extracts facial feature information of the user, retrieves pre-stored setting data, and determines whether the facial feature information can be acquired. If the voice setting information is obtained, the voice setting information corresponding to the facial feature information is obtained, and the target voice service corresponding to the user is set to the in-vehicle intelligent voice system according to the voice setting information, to invoke the target voice service to respond to the operation sent by the user. instruction. Therefore, different voice services are performed based on different users, which satisfies the personalized requirements of the user and improves the intelligent experience of the user.
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” or “second” may include at least one of the features, either explicitly or implicitly.
  • the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
  • Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logic function or process.
  • the scope of the preferred embodiments of the present disclosure includes additional implementations, in which the functions may be performed in a substantially simultaneous manner or in an inverse order depending on the functions involved, in the order shown or discussed. It will be understood by those skilled in the art to which the embodiments of the present disclosure pertain.
  • a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
  • computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
  • portions of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware and in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.
  • each functional unit in various embodiments of the present disclosure may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like. While the embodiments of the present disclosure have been shown and described above, it is understood that the foregoing embodiments are illustrative and are not to be construed as limiting the scope of the disclosure The embodiments are subject to variations, modifications, substitutions and variations.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • General Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Navigation (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种基于人脸识别的语音处理方法及其设备，其中，方法包括：采集车内目标位置上的用户脸部信息，提取用户的脸部特征信息（101）；检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息（102）；若判断获知能够获取与脸部特征信息对应的语音设置信息，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令（103）。由此，基于不同的用户进行不同的语音服务，满足了用户的个性化要求，提高了用户的智能化体验。

Description

基于人脸识别的语音处理方法及其设备
相关申请的交叉引用
本公开要求比亚迪股份有限公司于2018年04月20日提交的、公开名称为“基于人脸识别的语音处理方法及其设备”的、中国专利申请号“201810360826.7”的优先权。
技术领域
本公开涉及智能交互技术领域，尤其涉及一种基于人脸识别的语音处理方法及其设备。
背景技术
随着汽车消费的逐渐普及，以车代步成为了一种生活，越来越多的信息娱乐功能加入到车辆中，这大大地增加了司机及乘员的舒适性，车载智能语音识别便是其中的一个典型。车载智能语音的应用解决了驾驶员操控车辆中控多媒体易分心导致事故的问题，大大地解放了驾驶员的双手。目前市场现有的车载智能语音功能丰富多样，能够导航设置、空调控制、音乐播放、蓝牙电话、车窗座椅控制等。对于智能语音识别功能本身，可以进行按键语音唤醒、语音唤醒设置、语音播报声音及方言设置等。
相关技术中，基于功能要求为用户提供智能化的车载智能语音服务，然而，这种仅仅满足用户功能要求的服务方式，限制了用户与产品的距离，不利于提高用户和产品的粘性。
公开内容
本公开旨在至少在一定程度上解决相关技术中的技术问题之一。
为此，本公开的第一个目的在于提出一种基于人脸识别的语音处理方法，该方法基于不同的用户进行不同的语音服务，满足了用户的个性化要求，提高了用户的智能化体验。本公开的第二个目的在于提出一种车载智能语音系统。
本公开的第三个目的在于提出一种车机设备。
为达上述目的，本公开第一方面实施例提出了一种基于人脸识别的语音处理方法，包括以下步骤：采集车内目标位置上的用户脸部信息，提取所述用户的脸部特征信息；检索预存设置数据，判断是否能够获取与所述脸部特征信息对应的语音设置信息；若判断获知能够获取与所述脸部特征信息对应的语音设置信息，则根据所述语音设置信息对车载智能语音系统设置与所述用户对应的目标语音服务，以调用所述目标语音服务响应所述用户发 送的操作指令。
为达上述目的，本公开第二方面实施例提出了一种车载智能语音系统，包括：提取模块，用于采集车内目标位置上的用户脸部信息，提取所述用户的脸部特征信息；判断模块，用于检索预存设置数据，判断是否能够获取与所述脸部特征信息对应的语音设置信息；处理模块，用于在判断获知能够获取与所述脸部特征信息对应的语音设置信息时，根据所述语音设置信息对车载智能语音系统设置与所述用户对应的目标语音服务，以调用所述目标语音服务响应所述用户发送的操作指令。
为达上述目的，本公开第三方面实施例提出了一种车机设备，包括：车载摄像头和中控多媒体设备，其中，所述车载摄像头与所述中控多媒体设备连接，其中，所述车载摄像头，用于采集车内目标位置上的用户脸部信息，并将所述用户脸部信息发送至所述中控多媒体设备；所述中控多媒体设备，用于根据提取所述用户的脸部特征信息，检索预存设置数据，判断是否能够获取与所述脸部特征信息对应的语音设置信息，若判断获知能够获取与所述脸部特征信息对应的语音设置信息，则将所述语音设置信息设置与所述用户对应的目标语音服务，以调用所述目标语音服务响应所述用户发送的操作指令。
本公开实施例提供的技术方案可以包括以下有益效果：
采集车内目标位置上的用户脸部信息，提取用户的脸部特征信息，检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息，若判断获知能够获取与脸部特征信息对应的语音设置信息，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令。由此，基于不同的用户进行不同的语音服务，满足了用户的个性化要求，提高了用户的智能化体验。
本公开附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本公开的实践了解到。
附图说明
本公开上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1是根据本公开一个实施例的基于人脸识别的语音处理方法的流程图；
图2是根据本公开一个实施例的设置数据的存储示意图；
图3是根据本公开一个实施例的车载智能语音系统的结构示意图；
图4是根据本公开另一个实施例的车载智能语音系统的结构示意图；
图5是根据本公开另一个实施例的基于人脸识别的语音处理方法的流程图；
图6是根据本公开又一个实施例的基于人脸识别的语音处理方法的流程图；
图7是根据本公开一个实施例的车载智能语音系统的结构示意图。
具体实施方式
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本公开，而不能理解为对本公开的限制。
为了解决现有技术中，车载端的语音服务仅仅着眼于功能服务本身实施对应功能，导致用户和产品具有距离感的技术问题，本公开实施例提供了一种基于人脸识别的语音处理方法，可以通过人脸识别技术准确识别用户，针对不同的用户提供不同的语音服务，满足了用户的个性化需求，提高了用户和产品的粘性。
图1是根据本公开一个实施例的基于人脸识别的语音处理方法的流程图，如图1所示，该方法包括：
步骤101，采集车内目标位置上的用户脸部信息，提取用户的脸部特征信息。
其中，目标位置根据应用场景的不同，可以对应于车辆内的不同位置，在一些可能的实施例中，为了优先给驾驶员提供较优的语音服务，目标位置为车辆的驾驶座位置；在一些可能的实施例中，为了避免分散驾驶员的注意力，由副驾驶进行语音服务的控制，因而，目标位置为车辆的副驾驶位置。
另外，用户的面部特征信息包括但不限于用户的五官特征信息、面部轮廓信息等。
需要说明的是，在不同的应用场景下，采集车内目标位置上用户脸部信息的方式不同，示例说明如下：
第一种示例：
在本示例中，按照预设周期采集车内目标位置上的用户脸部信息。
其中，预设周期可以是根据系统处理速度确定的，系统处理速度越高，对应的预设周期对应的时长越短。
在实际执行过程中，可以调用安装在车内前端的摄像头采集目标位置上的用户脸部信息，其中，安装在车内前端的摄像头可以根据目标位置上用户脸部的位置调整角度和高度，以保证采集的用户脸部信息尽量完整，提高识别的精确度。
第二种示例：
在本示例中，检测是否满足预设的采集触发条件，若检测满足预设的采集触发条件，则采集车内目标位置上的用户脸部信息。
其中，预设的采集触发条件包括但不限于车辆由停车状态到启动状态等驾驶员有可能发生变化的条件，当检测到满足预设的采集触发条件后，才进行用户脸部信息的采集，提 高了采集的有效性，避免了重复采集一个用户面部信息，减轻了系统处理压力。
在实际执行过程中，可能由于光线不足等原因导致无法直接获取到有效的用户的脸部信息，因而，在本公开的一个实施例中，在采集车内目标位置上的用户脸部信息之前，还可以检测车内环境的光线亮度，比如，通过光线传感器检测车内环境的光线亮度，将光线亮度与预设阈值进行比较，其中，预设阈值与拍照装置有关，对应于拍照装置可以采集到脸部信息的最小光线亮度值。
进而，如果比较获知光线亮度小于预设阈值，则表明当前环境光线不足，可能难以采集到清晰的用户的脸部信息，从而，对目标位置启动辅助照明设备，比如，打开车辆内部的照明系统等。
步骤102，检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息。
其中，语音设备信息包括播报音量、播报声音、播报方言中的一种或者多种信息组合。
可以理解，为了拉近产品和用户的距离，在本公开的实施例中，在用户启动语音服务时，针对不同的用户提供不同的语音服务，比如，如图2所示，针对不同的用户对应存储了不同的语音设置信息，在本实施例中，预先设置并存储设置数据，该设置数据中存储有脸部特征信息和语音设置信息的对应关系，从而，在获取到用户的脸部特征信息后，查询该对应关系以匹配出对应的语音设置信息。
需要说明的是，根据应用场景的不同，设置预存设置数据的方式不同，作为一种可能的实现方式，为用户提供语音设置信息界面，接收用户在该界面中根据个人喜好设定的语音设置信息，其中，在用户输入语音设置信息时，可以同步采集用户的面部图像以提取用户的脸部特征信息，或者，由用户上传照片以便于根据用户上传的照片提取脸部特征信息，进而，将脸部特征信息与对应的语音设置信息对应存储。
步骤103，若判断获知能够获取与脸部特征信息对应的语音设置信息，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令。
其中，用户发送的操作指令的方式可以为文字输入形式、语音输入形式等任意可以被识别的形式。
在本公开的实施例中，如果判断获知能够获取到与脸部特征信息对应的语音设置信息，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令，以实现对用户提供个性化的语音服务。
在本实施例中，可以通过车载智能语音系统的屏幕获取用户通过操作面板输入的操作指令，比如，获取用户对预设的选项卡的触控操作，或者，文字输入操作等，或者，通过 车载智能语音系统的麦克风获取用户语音输入的操作指令。
进而，对用户语音输入的操作指令进行语音识别，调用本地的语音合成指令或者获取云端反馈的响应信息，也就是说，对用户输入的操作指令可以采用本地的语音识别并进行语音合成与该操作指令对应的语音合成指令，该语音合成指令为针对操作指令的响应信息，或者，可以将语音识别后的语音信息发送至云端，以供云端根据预先存储的语音信息和响应消息的对应关系，匹配并反馈对应的响应消息，通过车载智能语音系统输出给用户，以基于对应的目标语音服务为用户提供该响应消息对应的语音服务。
举例而言，在当前用户为用户1时，如果获取到与用户1的脸部特征对应的语音设置信息为“粤语、音量5”，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务为“粤语、音量5”，则当用户1发出的操作指令为“帮我导航去##”，则将该指令发送至云端后获取到云端反馈的对应的导航信息，车载智能语音服务以“粤语、音量5”根据导航信息为用户进行语音导航。
在本公开的一个实施例中，当判断获知不存在与脸部特征信息对应的语音设置信息，则调用车载智能语音系统预先根据默认设置信息设置的标准语音服务响应用户发送的操作指令，以满足用户的语音服务需求。
当然，为了进一步提高基于人脸识别的语音处理方法的灵活性，也可以根据应用需求随时更改或者添加与语音设置信息。
在本公开的一个实施例中，接收用户输入的包含语音设置信息的设置指令，比如，接收用户输入的“我要制定属于我的语音服务”，则查询预存设置数据，判断是否包含用户的脸部特征信息，若判断获知包含用户的脸部特征信息，则删除当前存储的与脸部特征信息对应的语音设置信息，并存储语音设置信息与脸部特征信息的对应关系，若判断获知不包含用户的脸部特征信息，则在设置数据中存储语音设置信息与用户的脸部特征信息的对应关系。由此，通过对预存设置数据的更新和修改，一方面，适应新用户的个性化语音服务的提供，另一方面，适应已经注册的用户的喜好的变化。
基于以上描述，在实际执行过程中，实现基于人脸识别的语音处理方法的模块可以根据应用场景的不同，以不同的形式实现，下面示例说明：
在本示例中，由包括车机设备100和云端200组成对应的车载智能语音系统，其中，车机设备100与云端200通过无线网络实现通讯，将车机设备100采集的相关信息上传至云端200进行识别，并将云端200识别出的语音内容下下发至车机设备100，当然，根据应用需要，也可以下发至第三方设备，其中无线网络可以是2G、3G、4G或者未来更新的移动通讯技术或者车机连接WIFI，通讯链路可以是公网也可以是专网。
图3是根据本公开一个实施例的车载智能语音系统的结构示意图，如图3所示，车机 设备100包括车载摄像头110和中控多媒体设备120。
其中，车载摄像头110，用于采集车内目标位置上的用户脸部信息，并将用户脸部信息发送至中控多媒体设备。
其中，车载摄像头110作为车机设备100的用户图像采集设备，用于采集用户的脸部信息传输至中控多媒体设备120，摄像头安装于车内，要求可清晰地拍摄到用户脸部。作为一种可能的实现方式，摄像头可采用高分辨率红外摄像头，车内安装有红外灯，以便在晚上或者光照条件差的情况下仍可以清晰地采集用户脸部信息。
中控多媒体设备120，用于根据提取用户的脸部特征信息，检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息，若判断获知能够获取与脸部特征信息对应的语音设置信息，则将语音设置信息设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令。
在本公开的实施例中，中控多媒体设备120接收车载摄像头110采集的用户的脸部信息，经过图像处理，提取用户面部特征信息，对比本地存储的特征数据识别不同用户。
作为一种可能的实现方式，中控多媒体设备120带有显示屏，提供用户交互界面，用户交互界面用于显示语音服务的相关文字信息，或者，故障提示信息等。
在本公开的一个实施例中，参照图4，车机设备100还可包括麦克风130，其中，麦克风130与中控多媒体设备120连接，其中，
麦克风130，用于接收用户输入的包含语音设置信息的设置指令。
其中，麦克风130作为车机设备100的语音接收设备，用于接收用户输入的语音设置信息等，将语音设置信息的音频信号转换成电平信号，为语音识别提供信号源，麦克风130带有滤波功能，以消除环境噪声。
中控多媒体设备120，用于查询预存设置数据，判断是否包含用户的脸部特征信息，若判断获知包含用户的脸部特征信息，则删除当前存储的与脸部特征信息对应的语音设置信息，并存储语音设置信息与脸部特征信息的对应关系，若判断获知不包含用户的脸部特征信息，则在设置数据中存储语音设置信息与用户的脸部特征信息的对应关系。
在本公开的一个实施例中，继续参照图4，车机设备100还可包括扬声器140，其中，扬声器140与中控多媒体设备120连接，其中，
扬声器140用于根据语音设置信息对用户语音输入的操作指令进行语音响应。
扬声器140作为车机设备100的发声设备，用于发出中控多媒体设备120的语音合成指令，将合成语音指令的电平信号转换为音频信息，为智能语音系统与用户交互输出的一部分。
为了更加清楚的说明本公开实施例的基于人脸识别的语音处理方法，下面以该方法结 合上述系统的应用为例进行说明，其中，为了说明的方便，分别集中在预存设置数据侧和用户个性化语音服务识别侧进行描述。
在本示例中，目标位置为驾驶位置。
首先，集中在预存设置数据侧描述。
图5是根据本公开另一个实施例的基于人脸识别的语音处理方法的流程图，其中，如图5所示，该方法包括：
步骤201，启动中控多媒体设备。
其中，启动完成的条件是多媒体各项功能可以正常工作，可以调用车载摄像头、麦克风、扬声器等外设。
步骤202，中控多媒体启动后，调用车载摄像头，采集驾驶员位置上的驾驶员脸部信息，提取驾驶员的脸部特征信息。
步骤203，用户设置智能语音系统的设置选项，对语音识别系统按照个人的喜好进行个性化设置，确定设置数据。
用户设置智能语音系统的设置选项时，可以是使用智能语音来进行语音设置，也可以是通过中控多媒体设备触摸显示屏上的设置界面进行设置。
步骤204，用户保存智能语音系统设置选项的内容，中控多媒体设备提取当前用户的面部脸部特征信息与智能语音系统设置数据形成列表，对比已存储的列表中有用户面部特征信息相同，则判断为同一用户，只更新设置数据，如果没有相同，则判断为新用户，将新用户的面部特征信息和设置数据存储添加到本地列表中。
其中，在本实施例中，当中控多媒体采集不到驾驶员脸部特征信息时，例如驾驶座无人、摄像头被遮挡，存储设置数据时，智能语音系统的设置数据列表中，用户脸部特征信息空缺，之后所有无法确定用户脸部特征信息的设置数据都存储在这一用户信息空缺栏中。
下面其次集中在用户个性化语音服务识别侧进行描述。
图6是根据本公开又一个实施例的基于人脸识别的语音处理方法的流程图，如图6所示，该方法包括：
步骤301，启动中控多媒体设备。
其中，启动完成的条件是多媒体各项功能可以正常工作，可以调用车载摄像头、麦克风、扬声器等外设。
步骤302，中控多媒体启动后，调用车载摄像头，采集驾驶员位置上的驾驶员脸部信息，提取驾驶员的脸部特征信息。
步骤303，中控多媒体提取当前驾驶员脸部特征信息，检索对比本地已有用户设置信息列表，如果有用户信息相同，则提取对应的智能语音系统设置数据，如果没有用户信息， 则设置智能语音系统的设置数据为默认设置。
步骤304，根据提取的用户设置数据，中控多媒体主动设置智能语音系统的设置选项，完成对不同用户不同系统设置的自适应。
其中，中控多媒体提取用户脸部特征信息，经检索对比，如果不在已有的设置数据中，则判断该用户为新用户，智能语音系统的设置选项初始化为默认值。如果在已有的设置数据中，则提取设置信息，用户调用车载智能语音系统时，可以用户自己设定的唤醒词，智能语音功能被唤醒时应答用户设定的称呼，包括播报音量、播报声音、播报方言等，都是符合用户自己设定的需求。
由此通过用户人脸识别、设置数据、设置数据提取，形成了自动的对不同用户存储不同设置数据、设置不同的目标语音服务，达到了智能语音系统设置的智能化与自动化目的。
综上所述，本公开实施例的基于人脸识别的语音处理方法，采集车内目标位置上的用户脸部信息，提取用户的脸部特征信息，检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息，若判断获知能够获取与脸部特征信息对应的语音设置信息，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令。由此，基于不同的用户进行不同的语音服务，满足了用户的个性化要求，提高了用户的智能化体验。
为了实现上述实施例，本公开还提出了一种车载智能语音系统，图7是根据本公开一个实施例的车载智能语音系统的结构示意图，如图7所示，该系统包括提取模块1100、判断模块1200和处理模块1300。
其中，提取模块1100，用于采集车内目标位置上的用户脸部信息，提取用户的脸部特征信息。
在本公开的一个实施例中，提取模块1100具体用于按照预设周期采集车内目标位置上的用户脸部信息；或者，检测是否满足预设的采集触发条件，若检测满足预设的采集触发条件，则采集车内目标位置上的用户脸部信息。
判断模块1200，用于检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息。
处理模块1300，用于在判断获知能够获取与脸部特征信息对应的语音设置信息时，根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令。
在本公开的一个实施例中，处理模块1300，还用于在判断获知不存在与脸部特征信息对应的语音设置信息时，调用车载智能语音系统预先根据默认设置信息设置的标准语音服 务响应用户发送的操作指令。
综上所述，本公开实施例的车载智能语音系统，采集车内目标位置上的用户脸部信息，提取用户的脸部特征信息，检索预存设置数据，判断是否能够获取与脸部特征信息对应的语音设置信息，若判断获知能够获取与脸部特征信息对应的语音设置信息，则根据语音设置信息对车载智能语音系统设置与用户对应的目标语音服务，以调用目标语音服务响应用户发送的操作指令。由此，基于不同的用户进行不同的语音服务，满足了用户的个性化要求，提高了用户的智能化体验。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本公开的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本公开的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本公开的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本公开的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及 便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本公开的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本公开各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。尽管上面已经示出和描述了本公开的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本公开的限制，本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (14)

  1. 一种基于人脸识别的语音处理方法，其特征在于，包括以下步骤：
    采集车内目标位置上的用户脸部信息，提取所述用户的脸部特征信息；
    检索预存设置数据，判断是否能够获取与所述脸部特征信息对应的语音设置信息；
    若判断获知能够获取与所述脸部特征信息对应的语音设置信息，则根据所述语音设置信息对车载智能语音系统设置与所述用户对应的目标语音服务，以调用所述目标语音服务响应所述用户发送的操作指令。
  2. 如权利要求1所述的方法，其特征在于，在所述判断是否能够获取与所述脸部特征信息对应的语音设置信息之后，还包括：
    若判断获知不存在与所述脸部特征信息对应的语音设置信息，则调用所述车载智能语音系统预先根据默认设置信息设置的标准语音服务响应所述用户发送的操作指令。
  3. 如权利要求1或2所述的方法，其特征在于，在所述提取所述用户的脸部特征信息之后，还包括：
    接收所述用户输入的包含语音设置信息的设置指令；
    查询预存设置数据，判断是否包含所述用户的脸部特征信息；
    若判断获知包含所述用户的脸部特征信息，则删除当前存储的与所述脸部特征信息对应的语音设置信息，并存储所述语音设置信息与所述脸部特征信息的对应关系；
    若判断获知不包含所述用户的脸部特征信息，则在所述设置数据中存储所述语音设置信息与所述用户的脸部特征信息的对应关系。
  4. 如权利要求1-3任一所述的方法，其特征在于，所述语音设置信息，包括：
    播报音量、播报声音、播报方言中的一种或者多种信息组合。
  5. 如权利要求1-4任一所述的方法，其特征在于，在所述采集车内目标位置上的用户脸部信息之前，还包括：
    检测车内环境的光线亮度，将所述光线亮度与预设阈值进行比较；
    若比较获知所述光线亮度小于预设阈值，则对所述目标位置启动辅助照明设备。
  6. 如权利要求1-5任一所述的方法，其特征在于，所述采集车内目标位置上的用户脸部信息，包括：
    按照预设周期采集车内目标位置上的用户脸部信息；或者，
    检测是否满足预设的采集触发条件，若检测满足预设的采集触发条件，则采集车内目标位置上的用户脸部信息。
  7. 如权利要求1-6任一所述的方法，其特征在于，还包括：
    通过所述车载智能语音系统的屏幕获取所述用户通过操作面板输入的操作指令；
    或者，
    通过所述车载智能语音系统的麦克风获取所述用户语音输入的操作指令。
  8. 如权利要求7所述的方法，其特征在于，还包括：
    对所述用户语音输入的操作指令进行语音识别；
    调用本地的语音合成指令或者获取云端反馈的响应信息，通过所述车载智能语音系统输出给所述用户。
  9. 一种车载智能语音系统，其特征在于，包括：
    提取模块，用于采集车内目标位置上的用户脸部信息，提取所述用户的脸部特征信息；
    判断模块，用于检索预存设置数据，判断是否能够获取与所述脸部特征信息对应的语音设置信息；
    处理模块，用于在判断获知能够获取与所述脸部特征信息对应的语音设置信息时，根据所述语音设置信息对车载智能语音系统设置与所述用户对应的目标语音服务，以调用所述目标语音服务响应所述用户发送的操作指令。
  10. 如权利要求的9所述的车载智能语音系统，其特征在于，所述处理模块，还用于：
    在判断获知不存在与所述脸部特征信息对应的语音设置信息时，调用所述车载智能语音系统预先根据默认设置信息设置的标准语音服务响应所述用户发送的操作指令。
  11. 如权利要求的9或10所述的车载智能语音系统，其特征在于，所述提取模块，具体用于：
    按照预设周期采集车内目标位置上的用户脸部信息；或者，
    检测是否满足预设的采集触发条件，若检测满足预设的采集触发条件，则采集车内目标位置上的用户脸部信息。
  12. 一种车机设备，其特征在于，包括：车载摄像头和中控多媒体设备，其中，所述车载摄像头与所述中控多媒体设备连接，其中，
    所述车载摄像头，用于采集车内目标位置上的用户脸部信息，并将所述用户脸部信息发送至所述中控多媒体设备；
    所述中控多媒体设备，用于根据提取所述用户的脸部特征信息，检索预存设置数据，判断是否能够获取与所述脸部特征信息对应的语音设置信息，若判断获知能够获取与所述脸部特征信息对应的语音设置信息，则将所述语音设置信息设置与所述用户对应的目标语音服务，以调用所述目标语音服务响应所述用户发送的操作指令。
  13. 如权利要求12所述的车机设备，其特征在于，还包括：
    麦克风，其中，所述麦克风与所述中控多媒体设备连接，其中，
    所述麦克风，用于接收所述用户输入的包含语音设置信息的设置指令；
    所述中控多媒体设备，用于查询预存设置数据，判断是否包含所述用户的脸部特征信息，若判断获知包含所述用户的脸部特征信息，则删除当前存储的与所述脸部特征信息对应的语音设置信息，并存储所述语音设置信息与所述脸部特征信息的对应关系，若判断获知不包含所述用户的脸部特征信息，则在所述设置数据中存储所述语音设置信息与所述用户的脸部特征信息的对应关系。
  14. 如权利要求12或13所述的车机设备，其特征在于，还包括：
    扬声器，其中，所述扬声器与所述中控多媒体设备连接，其中，
    所述扬声器，用于根据所述语音设置信息对所述用户语音输入的操作指令进行语音响应。
PCT/CN2019/083261 2018-04-20 2019-04-18 基于人脸识别的语音处理方法及其设备 WO2019201304A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810360826.7A CN110390932A (zh) 2018-04-20 2018-04-20 基于人脸识别的语音处理方法及其设备
CN201810360826.7 2018-04-20

Publications (1)

Publication Number Publication Date
WO2019201304A1 true WO2019201304A1 (zh) 2019-10-24

Family

ID=68239903

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/083261 WO2019201304A1 (zh) 2018-04-20 2019-04-18 基于人脸识别的语音处理方法及其设备

Country Status (2)

Country Link
CN (1) CN110390932A (zh)
WO (1) WO2019201304A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110834338A (zh) * 2019-11-04 2020-02-25 深圳勇艺达机器人有限公司 一种车载机器人及其控制方法
CN112918381A (zh) * 2019-12-06 2021-06-08 广州汽车集团股份有限公司 一种车载机器人迎送宾方法、装置及系统
CN112992122A (zh) * 2021-03-05 2021-06-18 济南中维世纪科技有限公司 一种电视摄像头的隐私安全保护方法及设备
CN113382307A (zh) * 2020-03-10 2021-09-10 海信视像科技股份有限公司 显示设备及其显示方法
CN113808410A (zh) * 2021-08-25 2021-12-17 阿波罗智联(北京)科技有限公司 车辆行驶的提示方法、装置、电子设备及可读存储介质
CN114312818A (zh) * 2022-01-29 2022-04-12 中国第一汽车股份有限公司 一种车辆控制方法、装置、车辆及介质
CN117456584A (zh) * 2023-11-13 2024-01-26 江苏创斯达智能科技有限公司 一种应用于智能保险柜的面部识别设备

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110816470B (zh) * 2019-11-18 2022-03-08 上海擎感智能科技有限公司 基于车载终端的用户授权添加方法、系统、介质及车载终端
CN113518474A (zh) * 2020-03-27 2021-10-19 阿里巴巴集团控股有限公司 检测方法、装置、设备、存储介质和系统
WO2021217572A1 (zh) * 2020-04-30 2021-11-04 华为技术有限公司 车内用户定位方法、车载交互方法、车载装置及车辆
CN111696548A (zh) * 2020-05-13 2020-09-22 深圳追一科技有限公司 显示行车提示信息的方法、装置、电子设备以及存储介质
CN111857638A (zh) * 2020-06-01 2020-10-30 江西江铃集团新能源汽车有限公司 一种基于人脸识别的语音交互方法、系统及汽车
CN113038420A (zh) * 2021-03-03 2021-06-25 恒大新能源汽车投资控股集团有限公司 基于车联网的服务方法及装置
CN113538944A (zh) * 2021-06-11 2021-10-22 广汽本田汽车有限公司 汽车语音提示信息的配置系统、方法、设备及存储介质
CN117370961B (zh) * 2023-12-05 2024-03-15 江西五十铃汽车有限公司 一种车辆语音交互方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104795067A (zh) * 2014-01-20 2015-07-22 华为技术有限公司 语音交互方法及装置
CN105825167A (zh) * 2016-01-29 2016-08-03 维沃移动通信有限公司 一种提高唇语识别率的方法和移动终端
CN106650601A (zh) * 2016-10-18 2017-05-10 武汉慧能机器人科技有限公司 人机交互方法及智能机器人
US20170247000A1 (en) * 2012-03-14 2017-08-31 Autoconnect Holdings Llc User interface and virtual personality presentation based on user profile
CN107122692A (zh) * 2017-04-11 2017-09-01 胡渐佳 基于开关门图像识别的语音智能播放系统
CN107391122A (zh) * 2017-07-01 2017-11-24 珠海格力电器股份有限公司 设置终端系统语言的方法、装置和终端
CN206877691U (zh) * 2017-05-04 2018-01-12 珠海格力电器股份有限公司 语音控制器
CN107919117A (zh) * 2016-10-10 2018-04-17 德尔福电子(苏州)有限公司 一种基于人脸识别的主动语音助手

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101568789B1 (ko) * 2009-10-14 2015-11-12 현대모비스 주식회사 차량용 개인화 서비스 장치 및 방법
KR101172213B1 (ko) * 2010-12-08 2012-08-07 현대자동차주식회사 얼굴인증 시스템 및 그 방법
US9851882B2 (en) * 2015-12-27 2017-12-26 Thunder Power New Energy Vehicle Development Company Limited Fully designable vehicle information panel interface
CN105667433A (zh) * 2016-01-12 2016-06-15 戴姆勒股份公司 车内装置调节系统及方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170247000A1 (en) * 2012-03-14 2017-08-31 Autoconnect Holdings Llc User interface and virtual personality presentation based on user profile
CN104795067A (zh) * 2014-01-20 2015-07-22 华为技术有限公司 语音交互方法及装置
CN105825167A (zh) * 2016-01-29 2016-08-03 维沃移动通信有限公司 一种提高唇语识别率的方法和移动终端
CN107919117A (zh) * 2016-10-10 2018-04-17 德尔福电子(苏州)有限公司 一种基于人脸识别的主动语音助手
CN106650601A (zh) * 2016-10-18 2017-05-10 武汉慧能机器人科技有限公司 人机交互方法及智能机器人
CN107122692A (zh) * 2017-04-11 2017-09-01 胡渐佳 基于开关门图像识别的语音智能播放系统
CN206877691U (zh) * 2017-05-04 2018-01-12 珠海格力电器股份有限公司 语音控制器
CN107391122A (zh) * 2017-07-01 2017-11-24 珠海格力电器股份有限公司 设置终端系统语言的方法、装置和终端

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110834338A (zh) * 2019-11-04 2020-02-25 深圳勇艺达机器人有限公司 一种车载机器人及其控制方法
CN112918381A (zh) * 2019-12-06 2021-06-08 广州汽车集团股份有限公司 一种车载机器人迎送宾方法、装置及系统
CN112918381B (zh) * 2019-12-06 2023-10-27 广州汽车集团股份有限公司 一种车载机器人迎送宾方法、装置及系统
CN113382307A (zh) * 2020-03-10 2021-09-10 海信视像科技股份有限公司 显示设备及其显示方法
CN113382307B (zh) * 2020-03-10 2022-04-22 海信视像科技股份有限公司 显示设备及其显示方法
CN112992122A (zh) * 2021-03-05 2021-06-18 济南中维世纪科技有限公司 一种电视摄像头的隐私安全保护方法及设备
CN113808410A (zh) * 2021-08-25 2021-12-17 阿波罗智联(北京)科技有限公司 车辆行驶的提示方法、装置、电子设备及可读存储介质
CN113808410B (zh) * 2021-08-25 2023-06-06 阿波罗智联(北京)科技有限公司 车辆行驶的提示方法、装置、电子设备及可读存储介质
CN114312818A (zh) * 2022-01-29 2022-04-12 中国第一汽车股份有限公司 一种车辆控制方法、装置、车辆及介质
CN117456584A (zh) * 2023-11-13 2024-01-26 江苏创斯达智能科技有限公司 一种应用于智能保险柜的面部识别设备

Also Published As

Publication number Publication date
CN110390932A (zh) 2019-10-29

Similar Documents

Publication Publication Date Title
WO2019201304A1 (zh) 基于人脸识别的语音处理方法及其设备
TWI440573B (zh) 多模組辨識系統及其控制方法
EP3563373B1 (en) Voice recognition system
JP4304952B2 (ja) 車載制御装置、並びにその操作説明方法をコンピュータに実行させるプログラム
CN105329187A (zh) 蓝牙按键触发实现安全操作的智能车载系统及控制方法
WO2017059815A1 (zh) 一种快速识别方法及家庭智能机器人
JP6011584B2 (ja) 音声認識装置及び音声認識システム
CN113459943B (zh) 车辆控制方法、装置、设备和存储介质
US10490188B2 (en) System and method for language selection
JP2017090613A (ja) 音声認識制御システム
CN112051887A (zh) 一种基于方向盘按键的控制方法和装置
CN109686368B (zh) 语音唤醒应答处理方法及装置、电子设备及存储介质
CN111128168A (zh) 语音控制方法、装置及存储介质
US20220396204A1 (en) Vehicle horn sound output device
US9771038B2 (en) Notification device
US20240126503A1 (en) Interface control method and apparatus, and system
US20160217332A1 (en) Vehicle and method of controlling the same
JP2004155410A (ja) スマート所有者マニュアル
US9715878B2 (en) Systems and methods for result arbitration in spoken dialog systems
US11282517B2 (en) In-vehicle device, non-transitory computer-readable medium storing program, and control method for the control of a dialogue system based on vehicle acceleration
US20070043570A1 (en) Method of controlling a dialoging process
CN111756986A (zh) 一种摄像头控制方法、存储介质、装置及具有其的电子设备
CN107832726B (zh) 使用者识别和确认装置及车用中央控制系统
CN111204339B (zh) 一种主动语音开启lka功能的方法及装置
US20220020374A1 (en) Method, device, and program for customizing and activating a personal virtual assistant system for motor vehicles

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19788774

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19788774

Country of ref document: EP

Kind code of ref document: A1