Voice control method based on tone recognition, related device and vehicle

Abstract

The invention provides a voice control method based on timbre recognition, and the method comprises the steps: recognizing the timbres of people in a vehicle in response to the determination of the power-on of the vehicle, and storing the recognized timbres of all people in the vehicle to form a timbre set of people in the vehicle; and in response to determining that the vehicle speed is less than or equal to the preset value, setting the tone in the tone set of the personnel in the vehicle as a target tone capable of waking up a vehicle voice system. According to the invention, the person in the vehicle is determined through the tone, and when the vehicle speed is less than or equal to the preset value, only the person in the vehicle can wake up the vehicle voice system to control the vehicle through voice, so that the vehicle voice system can be prevented from being controlled by the voice of the person outside the vehicle when the vehicle speed is less than or equal to the preset value, and the loss of the person in the vehicle and the vehicle can be avoided.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a voice control method based on tone recognition, related devices and vehicles. Background Art

[0002] Vehicles equipped with voice systems can be controlled by voice, which is convenient for users. However, at the same time, if any voice can wake up the vehicle's voice system to control the vehicle's operation by voice, it is easy to cause damage to the people in the vehicle and the vehicle. Summary of the invention

[0003] In view of this, the purpose of this application is to propose a voice control method based on tone recognition, related devices and vehicles to solve the problem that any voice can control the operation of the vehicle.

[0004] Based on the above objectives, the present application provides a voice control method based on timbre recognition, comprising:

[0005] In response to determining that the vehicle is powered on, identifying the timbre of the person in the vehicle, and storing all the identified timbre of the person in the vehicle to form a timbre set of the person in the vehicle;

[0006] In response to determining that the vehicle speed is less than or equal to a preset value, the timbre in the timbre set of the occupant's timbre is set as a target timbre that can wake up the vehicle voice system.

[0007] Furthermore, before identifying the voice of the person in the car, the method includes:

[0008] Get the occupancy status of each seat in the car;

[0009] Determine the number of passengers in the vehicle and their seating positions based on the seating status of each seat;

[0010] Based on the number of people in the car, an upper limit of the number of recognitions for recognizing the voices of people in the car is determined.

[0011] Furthermore, the step of identifying the timbre of the occupants and storing all the identified timbre of the occupants to form a timbre set of the occupants includes:

[0012] Directedly identifying the timbre of the person in the vehicle based on the seating position, wherein the timbre of the person in the vehicle has a seating position label;

[0013] Compare the recognized voice of the person in the car with the stored voice of the person in the car;

[0014] In response to determining that the recognized timbre of the vehicle occupant is different from the stored timbre of the vehicle occupant, storing the recognized timbre of the vehicle occupant, and continuing to recognize new timbre of the vehicle occupant until the number of stored timbre of the vehicle occupant reaches the upper limit of the number of recognitions;

[0015] The stored timbre of the people in the car is combined to form a timbre set of the people in the car.

[0016] Furthermore, the method of directionally identifying the voice of the person in the vehicle based on the seating position includes:

[0017] Based on the seating position, establish patrol identification rules, the patrol identification rules include patrol sequence and single seat patrol duration; based on the patrol sequence and single seat patrol duration, directionally identify the voice of the person in the car; or,

[0018] Determine a first sound emission position among the plurality of seating positions, establish a patrol recognition rule based on the first sound emission position, the patrol recognition rule including a patrol sequence and a single-seat patrol duration; and directionally recognize the voice of a person in the vehicle based on the patrol sequence and the single-seat patrol duration;

[0019] The patrol order is updated after the voice of a person in the car is recognized.

[0020] Furthermore, the method of directionally identifying the voice of the person in the vehicle based on the seating position includes:

[0021] In response to determining that a passenger in the seating position has uttered a voice, a directional identification is performed for the voice of the person in the vehicle at the seating position; wherein the time interval between two adjacent directional identifications is a preset time interval.

[0022] Furthermore, the method further comprises:

[0023] In response to determining that the voice of the person in the vehicle is not recognized and the vehicle speed is less than or equal to a preset value, the pre-stored voice is set as a target voice that can wake up the vehicle voice system.

[0024] Furthermore, the method further comprises:

[0025] In response to determining that the occupancy status of at least one seat has changed, the upper limit of the recognition quantity is updated based on the change, and the timbre set of the occupants is updated.

[0026] Further, the updating of the timbre set of the vehicle occupants includes:

[0027] determining the changed seating position as a target timbre update position;

[0028] In response to determining that the state of the target timbre update position is switched from unoccupied to occupied, the timbre of the person in the vehicle is directionally identified based on the target timbre update position, and stored in the timbre set of the person in the vehicle, until the number of the stored timbre of the person in the vehicle reaches the updated upper limit of the number of identifications, so as to update the timbre set of the person in the vehicle;

[0029] In response to determining that the state of the target timbre update position has switched from occupied to unoccupied, the timbre of the occupants in the vehicle with the target timbre update position tag is deleted from the timbre set of the occupants in the vehicle until the number of stored timbre of the occupants in the vehicle drops to the updated upper limit of the recognition number, so as to update the timbre set of the occupants in the vehicle.

[0030] Based on the same inventive concept, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0031] Based on the same inventive concept, the present disclosure also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method as described above.

[0032] Based on the same inventive concept, the present disclosure also provides a vehicle, which includes an electronic device as described above to execute the method as described above.

[0033] From the above, it can be seen that the present application provides a voice control method based on tone recognition, which identifies and stores the tone of the people in the car to obtain the tone set of the people in the car. When the vehicle is in a specific scenario, such as when the vehicle speed is less than or equal to a preset value, the tone in the tone set of the people in the car is set as the target tone that can wake up the vehicle voice system, thereby avoiding the situation where the vehicle voice system is awakened by people outside the vehicle in this scenario to control the vehicle by voice, causing losses to the people in the car and the vehicle. This can improve the safety protection performance of the vehicle and is conducive to promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 A flow chart of a voice control method based on timbre recognition according to an embodiment of the present application;

[0036] Figure 2 This is a structural schematic diagram of a voice control device based on timbre recognition according to an embodiment of the present application;

[0037] Figure 3 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0039] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0040] As described in the background technology, with the development of technology, vehicles are becoming more and more intelligent, and various functions of vehicles are gradually developed into voice control. Through the vehicle voice system, users can control the vehicle to perform corresponding actions through voice. While it is convenient for users, it also has certain safety hazards: vehicles are easily controlled by voice by criminals, or the voice operations of other vehicles by people outside the vehicle are misidentified, causing the vehicle to perform corresponding actions based on the voice, thereby causing losses to the vehicle and the people inside the vehicle.

[0041] Based on this, the present application proposes a voice control method, related devices and vehicles based on tone recognition to prevent the vehicle voice system from being awakened by people who are not in the vehicle to control the vehicle, thereby improving the vehicle's safety protection performance.

[0042] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0043] The present application provides a voice control method based on timbre recognition, the method is executed by a vehicle controller, referring to Figure 1 , the method comprising:

[0044] Step S100, in response to determining that the vehicle is powered on, identifying the timbre of the occupants, and storing all the identified timbre of the occupants to form a timbre set of the occupants;

[0045] Specifically, the vehicle controller collects voice through the voice collection module, and performs timbre recognition on the voice collected by the voice collection module through the timbre recognition module, wherein the voice collection module can specifically collect the voice of the people in the car through a microphone, etc., and send it to the timbre recognition module, and the timbre recognition module can specifically recognize the received voice of the people in the car through a timbre recognition model (the timbre recognition model can be a pre-trained neural network model) to obtain the timbre (i.e., voiceprint) of the people in the car and store it.

[0046] When the vehicle is powered on, the vehicle controller receives the vehicle power-on signal, controls the voice collection module to collect the voices of people in the car, and wakes up the tone recognition module so that it can receive the voices of people in the car, so as to recognize the tone of the voices of people in the car and store the tone.

[0047] Step S200, in response to determining that the vehicle speed is less than or equal to a preset value, setting the timbre in the timbre set of the occupant's timbre as a target timbre that can wake up the vehicle voice system.

[0048] Specifically, the vehicle controller obtains the vehicle speed in real time. When the vehicle speed is less than or equal to a preset value (such as 5km / h), the vehicle is determined to be in a voice protection state. Because the vehicle speed is relatively low at this time, the vehicle voice system is more sensitive to external sounds and is easily awakened by external sounds. Therefore, the vehicle is determined to be in a voice protection state when the vehicle speed is less than or equal to a preset value.

[0049] The vehicle controller sets the vehicle voice system so that the tone concentrated by the people in the vehicle is the target tone that can wake up the vehicle voice system. That is to say, when the vehicle is in a voice protection state, the vehicle voice system can only be awakened by the tone concentrated by the people in the vehicle to perform voice control of the vehicle, avoiding the situation where the vehicle voice system is mistakenly awakened by people outside the vehicle when the vehicle is in a voice protection state.

[0050] In addition, the preset value is pre-set and verified through multiple experiments to determine that when the vehicle speed is less than or equal to this value, the vehicle voice system can receive external sounds and can be easily awakened by external sounds.

[0051] Specifically, the vehicle controller can also be set to determine that the vehicle is in the voice protection state when the vehicle speed is less than or equal to a preset value and the duration is greater than or equal to a preset time, so as to avoid the situation where the vehicle is determined to be in the voice protection state during a short period of slow driving or a short period of parking.

[0052] It should be noted that when the vehicle controller determines that the vehicle is in voice protection state, it only compares the vehicle speed value with the preset value and is not affected by whether the vehicle is moving forward or backward.

[0053] Specifically, based on the above steps, it can also be imagined that when the user triggers emergency protection, the vehicle controller can also be not limited by the vehicle speed and directly set the tone concentrated by the occupants as the target tone that can wake up the vehicle voice system, so as to avoid other tones waking up the vehicle voice system and causing damage to the occupants and the vehicle.

[0054] In addition, when the vehicle speed is less than or equal to a preset value, that is, when the vehicle is in a voice protection state, the vehicle controller controls the various voice collection ends (such as microphones) of the voice collection module to stop running, so as to prevent the voice collection end from recognizing the voice of people outside the vehicle approaching the vehicle as the voice of people inside the vehicle for collection, thereby affecting the accuracy of the timbre of the people inside the vehicle.

[0055] In this embodiment, the timbre of the occupants of the vehicle is identified and stored to obtain a timbre set of the occupants of the vehicle. When the vehicle is in a specific scenario, such as when the vehicle speed is less than or equal to a preset value, the timbre in the timbre set of the occupants of the vehicle is set as the target timbre that can wake up the vehicle voice system. This avoids the situation in which the vehicle voice system is woken up by people outside the vehicle in order to control the vehicle by voice when the vehicle is in this scenario, causing losses to the occupants and the vehicle. This can improve the safety protection performance of the vehicle and is conducive to promotion and application.

[0056] In some embodiments, before identifying the voice of the person in the car, the method includes:

[0057] Step S101, obtaining the occupancy status of each seat in the vehicle;

[0058] Specifically, the vehicle controller obtains the occupancy status of each seat in the vehicle through a seat sensor or camera, and the occupancy status includes occupied and unoccupied. For a five-seater car, each seat exemplarily includes the main driver's seat, the front passenger seat, the main rear seat, the front rear seat and the middle rear seat; for a seven-seater car, each seat exemplarily includes the main driver's seat, the front passenger seat, the second-row main rear seat, the second-row front rear seat, the third-row main rear seat, and the third-row middle rear seat, i.e., the third-row front rear seat.

[0059] Step S102, determining the number of passengers in the vehicle and their seating positions based on the seating status of each seat;

[0060] Specifically, the vehicle controller determines which seats are occupied based on the seating status of the seats. On this basis, the seating positions can be determined based on the seats that are occupied, and the number of people in the vehicle can be confirmed based on the number of seats that are occupied.

[0061] Exemplarily, the occupancy status of each seat in the car is: main driver's seat (occupied), front passenger seat (unoccupied), main rear seat (unoccupied), front rear seat (occupied), middle rear seat (unoccupied), then the vehicle controller determines that the number of people in the car is 2, and the seating positions are: main driver's seat and front rear seat.

[0062] Step S103, based on the number of people in the car, determining an upper limit of the number of recognitions of the voices of the people in the car.

[0063] Specifically, the vehicle controller obtains the upper limit of the identification quantity based on the number of people in the vehicle to limit the number of timbres in the timbre set of the people in the vehicle.

[0064] Exemplarily, the upper limit of the number of recognitions is equal to the number of people in the car, or under set conditions, the upper limit of the number of recognitions is equal to the number of people in the car plus a set number. For example, if N passengers have a cold, their voiceprints may be unstable. In this case, the upper limit of the number of recognitions may be the number of people in the car + N. If the owner lends the car to other people, the upper limit of the number of recognitions can be set in advance to be equal to the number of people in the car plus the owner, and the owner's voice can be stored in the car's voice collection. When the voice of a person in the car is recognized, it will be stored in the car's voice collection.

[0065] The vehicle owner's timbre may be a timbre with a vehicle owner tag retrieved from a pre-stored timbre set by the vehicle controller.

[0066] In this embodiment, the number of people in the car and their seating positions are determined based on the seating status of the people in the car, so as to facilitate subsequent identification of the voices of the people in the car, thereby creating basic conditions for identifying the voices of the people in the car and avoiding repeated identification of the voices of the people in the car, which would waste computing power and lead to waste of resources.

[0067] In some embodiments, the step of identifying the timbre of the occupants and storing all the identified timbre of the occupants to form a timbre set of the occupants includes:

[0068] Step S104, based on the seating position, directionally identifying the timbre of the person in the vehicle, wherein the timbre of the person in the vehicle has a seating position label;

[0069] Specifically, based on the known seating position, the vehicle controller controls the voice collection module to directionally collect the voice at the seating position, and sends the collected voice to the timbre recognition module for recognition.

[0070] Specifically, the voice collection module has multiple voice collection terminals, and they are arranged one by one corresponding to each seat in the car to realize the directional collection of the voices of the people in the car at the sitting positions. Each voice collection terminal has a position tag, and its position tag is each seat in the car. The voices of the people in the car collected by the voice collection terminal also have the same position tag as the voice collection terminal. After receiving the voices of the people in the car, the timbre recognition module recognizes the timbre of the voices, and also sets the recognized timbre of the people in the car with the position tag corresponding to the recognized voice of the people in the car. The seating position tag of the timbre of the people in the car is the same as the position tag of the corresponding voice of the people in the car.

[0071] Exemplarily, the position labels of the voices of the people in the car collected by the voice collection end with the position label of the main driver's seat are respectively the main driver's seat, and the timbre recognition module receives the voice of the people in the car with the position label of the main driver's seat, performs timbre recognition on it, and obtains the timbre of the people in the car with the sitting position label of the main driver's seat. Specifically, each voice collection end includes at least two microphones arranged side by side. When the voice collection end collects the voice, the generalized cross-correlation algorithm (Generalized Cross-Correlation, GCC) is used to analyze the voices collected by at least two microphones to determine the azimuth and distance of the sound source corresponding to the voice, and judge whether the sound source position is the sitting position corresponding to the voice collection end according to the azimuth and distance of the sound source, that is, judge whether the sound source position corresponding to the voice belongs to the inside or outside of the car, and when the sound source position belongs to the inside of the car, it can also be judged whether the sound source position belongs to the sitting position.

[0072] Exemplarily, the voice collection terminal is arranged relative to the horizontal center of the corresponding seating position. When the sound source position is at the seating position, the sound source azimuth is (-30°, 30°), and the distance is 40 cm to 100 cm. The seating position corresponding to a voice collection terminal is the front passenger seat, and the sound source azimuth corresponding to the collected voice is 60°, and the distance is 110 cm. The voice collection terminal can determine that the sound source position is not the seating position corresponding to the voice collection terminal, and the voice collection terminal can ignore the voice.

[0073] In addition, when the voice collection end determines that the sound source position corresponding to the voice belongs to the seating position, it adjusts the angle of the microphone according to the identified sound source azimuth so that the microphone can more clearly collect the sound emitted from the sound source position, which is conducive to improving the accuracy of directional recognition of the voice of people in the car.

[0074] Step S105, comparing the recognized voice of the person in the car with the stored voice of the person in the car;

[0075] Specifically, the vehicle controller compares the timbre of the occupant with the stored timbre of the occupant. The comparison process includes both timbre comparison and seating position label comparison of the timbre, so as to avoid repeated storage of timbre of the occupant with the same seating position label and the same timbre, so as to ensure that the stored timbre of the occupant has one seating position label corresponding to one timbre, avoid the situation where the stored timbre of the occupant has the same seating position label, and avoid the situation where the same timbre corresponds to different seating position labels.

[0076] Step S106, in response to determining that the recognized timbre of the vehicle occupant is different from the stored timbre of the vehicle occupant, storing the recognized timbre of the vehicle occupant, and continuing to recognize new timbre of the vehicle occupant until the number of stored timbre of the vehicle occupant reaches the upper limit of the number of recognitions;

[0077] Specifically, the vehicle controller compares the identified voice of the person in the vehicle with the stored voice of the person in the vehicle. If the seating position label and voice of the identified person in the vehicle are different from those of the stored voice of the person in the vehicle, it is determined that the identified voice of the person in the vehicle is different from the stored voice of the person in the vehicle, and the identified voice of the person in the vehicle can be stored at this time.

[0078] When the number of stored voices of people in the car does not reach the upper limit of the recognition number, the voice collection module and the voice recognition module continue to work to recognize and store all the voices of the people in the car, so as to avoid the situation where some people in the car cannot wake up the vehicle voice system when the vehicle speed is less than or equal to the preset value, that is, when the vehicle is in a protection state.

[0079] When the number of stored voices of people in the car reaches the upper limit of the recognition number, the voice collection work of all passengers in the car is completed, and the voice collection module and the voice recognition module stop working, so as to avoid the situation where the voice collection module and the voice recognition module continue to work after the voice collection work of all passengers in the car is completed, thereby wasting energy and resources.

[0080] Step S107, combining the stored timbre of the people in the car to form a timbre set of the people in the car.

[0081] Specifically, the stored timbre of the occupants of the vehicle is combined together to form the timbre set of the occupants of the vehicle, so that when the vehicle speed is less than or equal to a preset value, the timbre in the timbre set of the occupants of the vehicle can be set as the target timbre that can wake up the vehicle voice system, which is conducive to improving the setting efficiency and calling the timbre contained in the timbre set of the occupants of the vehicle when updating the timbre set.

[0082] In this embodiment, based on the seating position of the occupants in the vehicle, the voices of the occupants in the vehicle are collected in a targeted manner, and the collected voices of the occupants in the vehicle are subjected to timbre recognition to obtain the timbre of the occupants in the vehicle, and the timbre of the occupants in the vehicle has a seating position label, so as to facilitate the storage and management of the timbre of the occupants in the vehicle, ensure the unity and simplicity of the timbre in the timbre concentration of the occupants in the vehicle, facilitate the subsequent calling of the timbre in the timbre concentration of the occupants in the vehicle, and also facilitate setting the timbre in the timbre concentration of the occupants in the vehicle as the target timbre that can wake up the vehicle voice system when the vehicle speed is less than or equal to a preset value.

[0083] In some embodiments, the step S104: based on the seating position, directionally identifying the voice of the person in the vehicle includes:

[0084] Step S104-1, based on the seating position, establish patrol identification rules, the patrol identification rules include patrol sequence and single seat patrol duration; based on the patrol sequence and single seat patrol duration, directionally identify the voice of the person in the car; or,

[0085] Step S104-2, determining a first sound emission position among the plurality of seating positions, establishing a patrol recognition rule based on the first sound emission position, wherein the patrol recognition rule includes a patrol sequence and a patrol duration for a single seat; and directionally recognizing the voice of a person in the vehicle based on the patrol sequence and the patrol duration for a single seat;

[0086] The patrol order is updated after the voice of a person in the car is recognized.

[0087] Specifically, the patrol order is the order in which the voice collection terminals are started in sequence based on the seating positions, and the single-seat patrol duration is the duration from the start to the shutdown of a voice collection terminal.

[0088] Specifically, in step S104-1, the vehicle controller establishes a patrol recognition rule based on the known seating positions of the occupants in the vehicle, and directionally identifies the voices of the occupants in the vehicle based on the rule. When the voice of a occupant in the vehicle is identified, the seating position with the same seating position label as the voice of the occupant in the vehicle is deleted from the patrol sequence in the patrol recognition rule to update the patrol sequence. The single-seat patrol duration remains unchanged, and an updated patrol recognition rule is obtained.

[0089] For example, if it is known that the seating positions of the occupants in the vehicle are: main driver's seat, co-pilot seat, and rear passenger seat, then the patrol order in the patrol identification rule is: main driver's seat → co-pilot seat → rear passenger seat → main driver's seat, and the patrol duration for a single seat is 5 seconds. When the voicing of the occupant whose seating position label is the main driver's seat is identified, the patrol order is updated to: co-pilot seat → rear passenger seat → co-pilot seat, and the patrol duration for a single seat is 5 seconds.

[0090] Specifically, in step S104-2, the vehicle controller determines a first sound emission position based on the known seating position of the occupant, the first sound emission position being the seating position where the occupant's voice is first recognized. When there are two or more seating positions, there are multiple seating positions.

[0091] Specifically, based on the known seating positions of the people in the vehicle, the vehicle controller drives all the voice collection terminals corresponding to the seating positions to start collecting voices. When one of the voice collection terminals collects voices, the vehicle controller determines the seating position corresponding to the voice collection terminal as the first sound emission position, and on this basis, establishes patrol recognition rules, and directionally identifies the voices of people in the vehicle based on the rules.

[0092] Exemplarily, it is known that the seating positions of the occupants of the vehicle are: main driver's seat, co-driver's seat, and co-rear seat, and the first sound emission position is the co-driver's seat, then the patrol order in the patrol recognition rule is established as: co-driver's seat → main driver's seat → co-rear seat → co-driver's seat, and the patrol time for a single seat is 5 seconds. Since at least the timbre of the co-driver's seat is recognized in this round, therefore, when only the timbre of the co-driver's seat is recognized in this round, the patrol order for the next round is updated as: main driver's seat → co-rear seat → main driver's seat, and the patrol time for a single seat is 5 seconds.

[0093] In this embodiment, based on the known seating positions of the occupants in the vehicle, the timbre of the occupants in the vehicle is directionally identified, and it is specifically determined that the timbre of the occupants in the vehicle is directionally identified in sequence according to the patrol identification rules, thereby ensuring the accuracy of the directional identification and the accuracy of the identified timbre of the occupants in the vehicle, thereby improving the accuracy and practicality of the method.

[0094] In some embodiments, the step S104: based on the seating position, directionally identifying the voice of the person in the vehicle includes:

[0095] Step S104-3, in response to determining that a passenger in the seating position has made a sound, directional recognition is performed on the voice of the passenger in the seating position; wherein the time interval between two adjacent directional recognitions is a preset time interval.

[0096] Specifically, based on the known seating positions of the occupants in the vehicle, the vehicle controller controls the voice collection terminals corresponding to the seating positions to operate so as to collect the voices of the occupants in the vehicle. When a voice collection terminal collects the voices of the occupants in the vehicle, it is determined that the occupant in the seating position corresponding to the voice collection terminal has spoken. The vehicle controller controls the timbre recognition module to only accept the voices of the occupants in the vehicle sent by the voice collection terminal within a preset time interval so as to identify the timbre of the occupants in the vehicle corresponding to the seating position. When another voice collection terminal collects the voices of the occupants in the vehicle, the vehicle controller controls the timbre recognition module to only accept the voices of the occupants in the vehicle sent by the voice collection terminal within a preset time interval. The preset time interval is based on the moment when the timbre recognition module receives the signal from the vehicle controller.

[0097] It should be noted that when the voice collection terminal corresponding to a seating position collects the voice of a person in the car, it can stop working.

[0098] In this embodiment, based on the known seating positions of the occupants in the car, the timbre of the occupants in the car is directional recognized, and the directional recognition is specifically determined according to the order in which the voices of the occupants in the car are collected. This not only avoids missing the collected voices of the occupants in the car, but also avoids the situation where too many voice collection terminals are opened and wastes resources, which is conducive to promotion and application.

[0099] In some embodiments, the method further comprises:

[0100] Step S300, in response to determining that the voice of the person in the vehicle is not recognized and the vehicle speed is less than or equal to a preset value, the pre-stored voice is set as the target voice that can wake up the vehicle voice system.

[0101] Specifically, if after the vehicle is powered on, the voice collection module has not been able to collect the voice of the person in the car, and the corresponding tone recognition module has not been able to recognize the tone of the person in the car, and the tone set of the person in the car is an empty set, then it is determined that the person in the car has not made a sound after the vehicle is powered on. If the vehicle controller monitors that the vehicle speed is less than or equal to the preset value, it is determined that the vehicle is in a voice protection state. At this time, the vehicle controller calls the pre-stored tone and sets it as the target tone that can wake up the vehicle voice system, so as to wake up the vehicle voice system when the vehicle is in the voice protection state.

[0102] The pre-stored tone may be the vehicle owner's tone or the tone of another person pre-stored by the vehicle owner, and is used to wake up the vehicle voice system when the vehicle is in a special condition, to avoid a situation where there is no tone that can wake up the vehicle voice system.

[0103] For example, the process of pre-storing the timbre can be that the owner must perform recognition and storage when the vehicle is first activated. This is a step that must be completed when the vehicle is first activated. The vehicle controller prompts the user to complete the pre-storage of the timbre on the vehicle's central control screen, so that the vehicle voice system can perform timbre recognition in special circumstances to start the vehicle voice system. In the subsequent use of the vehicle, the owner can add or delete the pre-stored timbre according to actual use needs to meet the use requirements.

[0104] When pre-storing the timbre, the vehicle controller drives a voice collection end in the voice collection module to collect the timbre, prompts the user to speak to the voice collection end on the central control screen, and displays the user's speaking content so that the voice collection end can accurately collect the user's timbre. The voice collection end sends the collected voice to the timbre recognition module for timbre recognition. After the timbre recognition module completes the timbre recognition, it sends the completion timbre recognition information to the vehicle controller and stores the recognized timbre. After receiving the completion timbre recognition information, the vehicle controller displays the completion timbre pre-storage information on the central control screen and controls the voice collection end to stop running. If the timbre recognized by the timbre recognition module based on the voice collected by the voice collection end is relatively mixed, it sends the re-acquired voice information to the vehicle controller. The vehicle controller generates the re-collected voice information on the central control screen and drives the voice collection end to continue collecting voice.

[0105] For example, when the vehicle is powered on and the occupants are sleeping, the vehicle's windows are partially open and the vehicle controller is unable to collect the voices of the occupants. At this time, if the vehicle voice system is to be awakened, only the pre-stored voices can be used.

[0106] In this embodiment, by limiting the setting of the target tone that can wake up the vehicle voice system when no one in the vehicle speaks, when the vehicle is in a voice protection state, it can not only play the role of voice protection, but also wake up the vehicle voice system when the tone is a pre-stored tone, so that users can use the vehicle voice system, which is conducive to the promotion and use of the method.

[0107] In some embodiments, the method further comprises:

[0108] Step S400, in response to determining that the occupancy status of at least one seat has changed, the upper limit of the recognition quantity is updated based on the change, and the timbre set of the occupants is updated.

[0109] Specifically, the vehicle controller obtains the seating status of each seat in the vehicle through a seat sensor or a camera. When the seating status of a seat changes, the vehicle controller obtains the seating status of the seat to obtain the seating status of the seat after the change, and then compares the seating status of the seat after the change with the seating status before the change to obtain the change. On this basis, the upper limit of the recognition quantity is updated. Since the upper limit of the recognition quantity is related to the number of timbres in the timbre set of the occupants of the vehicle, if the upper limit of the recognition quantity changes after being updated, the timbre set of the occupants of the vehicle will also change accordingly to complete the update, so that the timbre set of the occupants of the vehicle corresponds to the seating status of each seat in the vehicle after the change.

[0110] Exemplarily, when the occupancy status of the seat changes from occupied to unoccupied, the upper limit of the recognition number is updated to the original upper limit of the recognition number minus one, and when the occupancy status of the seat changes from unoccupied to occupied, the upper limit of the recognition number is updated to the original upper limit of the recognition number plus one.

[0111] In this embodiment, when the occupancy status of each seat in the vehicle changes, the voice set of the occupants is updated to avoid the situation where the voice set of the occupants is not updated when the occupants get off the vehicle or new occupants get on the vehicle, which affects the wake-up use of the vehicle voice system when the vehicle is in a voice protection state, thereby improving the practicality and applicability of the method.

[0112] In some embodiments, updating the timbre set of the vehicle occupants includes:

[0113] Step S401, determining the changed sitting position as the target timbre update position;

[0114] Specifically, when the sitting state of a seat changes, the vehicle controller obtains the changed sitting state of the seat and determines the sitting position corresponding to the seat as the target timbre update position.

[0115] Exemplarily, if the seating state of the main driver's seat changes, the main driver's seat is determined as the target timbre update position.

[0116] Step S402, in response to determining that the state of the target timbre update position is switched from unoccupied to occupied, directionally identifying the timbre of the person in the vehicle based on the target timbre update position, and storing it in the timbre set of the person in the vehicle, until the number of the stored timbre of the person in the vehicle reaches the updated upper limit of the number of identifications, so as to update the timbre set of the person in the vehicle;

[0117] Specifically, the vehicle controller confirms the status of the target timbre update position. When it is confirmed that the status of the target timbre update position is switched from unmanned to manned, it means that a new person has boarded the vehicle. The vehicle controller drives the voice collection end corresponding to the target timbre update position to start, so as to collect the voice of the person in the vehicle corresponding to the position. When the voice collection end collects the voice of the person in the vehicle, it sends it to the timbre recognition module for timbre recognition to obtain the timbre of the person in the vehicle. The seating position label of the timbre of the person in the vehicle corresponds to the target timbre update position. When the voice collection end collects the voice of the person, it stops working. When the number of timbres in the timbre set of the person in the vehicle reaches the upper limit of the recognition number after the update, the timbre recognition module stops working, and the update of the timbre set of the person in the vehicle is completed.

[0118] Exemplarily, the two target timbre update positions are the front passenger seat and the rear passenger seat, and the status of the two positions are switched from unoccupied to occupied, then the voice collection terminals of the front passenger seat and the rear passenger seat are driven to collect the voices of the people in the car corresponding to the two seats.

[0119] Step S403, in response to determining that the state of the target timbre update position is switched from occupied to unoccupied, the timbre of the occupants in the vehicle with the target timbre update position tag is deleted from the timbre set of the occupants in the vehicle until the number of stored timbre of the occupants in the vehicle drops to the updated upper limit of the recognition number, so as to update the timbre set of the occupants in the vehicle.

[0120] Specifically, the vehicle controller confirms the status of the target timbre update position. When it is confirmed that the status of the target timbre update position is switched from someone in the vehicle to no one in the vehicle, it means that a new person in the vehicle has got off the vehicle. The vehicle controller searches for the timbre of the person in the vehicle with the target timbre update position label in the timbre set of the person in the vehicle, and deletes the timbre until all the timbre of the person in the vehicle with the target timbre update position label in the timbre set of the person in the vehicle are deleted. That is, when the number of timbre in the timbre set of the person in the vehicle is the same as the upper limit of the recognition number after the update, the update of the timbre set of the person in the vehicle is completed.

[0121] Exemplarily, the two target timbre update positions are the front passenger seat and the rear passenger seat, and the status of the two positions are switched from occupied to unoccupied. Then, the timbre of the occupants in the vehicle whose seating positions are labeled as the front passenger seat and the rear passenger seat are searched for and deleted in the timbre set of the occupants in the vehicle, so as to obtain an updated timbre set of the occupants in the vehicle.

[0122] In this embodiment, during the vehicle power-on process, the seating status of the occupants is monitored to update the timbre set of the occupants. This not only avoids repeated identification of the timbre of the occupants, but also enables timely deletion of the timbre of the people who are not in the car, thereby ensuring timely updating of the timbre set of the occupants, so that the timbre set of the occupants matches the occupants, which is beneficial to improving the accuracy of the method and further conducive to the promotion and use of the method.

[0123] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0124] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a voice control device based on timbre recognition.

[0126] refer to Figure 2 , the voice control device based on timbre recognition comprises:

[0127] The recognition module 100 is configured to recognize the timbre of the person in the vehicle in response to determining that the vehicle is powered on, and store all the recognized timbre of the person in the vehicle to form a timbre set of the person in the vehicle;

[0128] The setting module 200 is configured to set the timbre in the timbre set of the occupant as the target timbre that can wake up the vehicle voice system in response to determining that the vehicle speed is less than or equal to a preset value.

[0129] In some embodiments, the identification module 100 is further configured to obtain the occupancy status of each seat in the vehicle;

[0130] Determine the number of passengers in the vehicle and their seating positions based on the seating status of each seat;

[0131] Based on the number of people in the car, an upper limit of the number of recognitions for recognizing the voices of people in the car is determined.

[0132] In some embodiments, the recognition module 100 is further configured to directionally recognize the timbre of the person in the vehicle based on the sitting position, wherein the timbre of the person in the vehicle has a sitting position tag;

[0133] Compare the recognized voice of the person in the car with the stored voice of the person in the car;

[0134] In response to determining that the recognized timbre of the vehicle occupant is different from the stored timbre of the vehicle occupant, storing the recognized timbre of the vehicle occupant, and continuing to recognize new timbre of the vehicle occupant until the number of stored timbre of the vehicle occupant reaches the upper limit of the number of recognitions;

[0135] The stored timbre of the people in the car is combined to form a timbre set of the people in the car.

[0136] In some embodiments, the recognition module 100 is further configured to establish a patrol recognition rule based on the seating position, wherein the patrol recognition rule includes a patrol sequence and a single-seat patrol duration; and to directionally recognize the voice of the person in the vehicle based on the patrol sequence and the single-seat patrol duration; or,

[0137] Determine a first sound emission position among the plurality of seating positions, establish a patrol recognition rule based on the first sound emission position, the patrol recognition rule including a patrol sequence and a single-seat patrol duration; and directionally recognize the voice of a person in the vehicle based on the patrol sequence and the single-seat patrol duration;

[0138] The patrol order is updated after the voice of a person in the car is recognized.

[0139] In some embodiments, the recognition module 100 is further configured to, in response to determining that a passenger in the seating position has made a sound, perform directionally recognition of the voice of the person in the vehicle at the seating position; wherein the time interval between two adjacent directionally recognitions is a preset time interval.

[0140] In some embodiments, the apparatus further comprises a resetting module;

[0141] The resetting module is configured to set the pre-stored timbre as the target timbre that can wake up the vehicle voice system in response to determining that the timbre of the person in the vehicle is not recognized and the vehicle speed is less than or equal to a preset value.

[0142] In some embodiments, the apparatus further comprises an update module;

[0143] The updating module is configured to update the upper limit of the recognition quantity and the timbre set of the occupants in the vehicle based on the change in response to determining that the occupancy status of at least one seat has changed.

[0144] In some embodiments, the updating module is further configured to determine the changed sitting position as the target timbre updating position;

[0145] In response to determining that the state of the target timbre update position is switched from unoccupied to occupied, the timbre of the person in the vehicle is directionally identified based on the target timbre update position, and stored in the timbre set of the person in the vehicle, until the number of the stored timbre of the person in the vehicle reaches the updated upper limit of the number of identifications, so as to update the timbre set of the person in the vehicle;

[0146] In response to determining that the state of the target timbre update position has switched from occupied to unoccupied, the timbre of the occupants in the vehicle with the target timbre update position tag is deleted from the timbre set of the occupants in the vehicle until the number of stored timbre of the occupants in the vehicle drops to the updated upper limit of the recognition number, so as to update the timbre set of the occupants in the vehicle.

[0147] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0148] The device of the above embodiment is used to implement the corresponding voice control method based on timbre recognition in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0149] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the voice control method based on timbre recognition described in any of the above embodiments is implemented.

[0150] Figure 3 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0151] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0152] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0153] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0154] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0155] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0156] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0157] The electronic device of the above embodiment is used to implement the corresponding voice control method based on timbre recognition in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0158] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the voice control method based on timbre recognition as described in any of the above embodiments.

[0159] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0160] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the voice control method based on timbre recognition as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0161] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0162] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0163] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0164] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0165] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0166] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0167] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0168] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0169] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A voice control method based on timbre recognition, characterized in that: include: In response to determining that the vehicle is powered on, identifying the timbre of the person in the vehicle, and storing all the identified timbre of the person in the vehicle to form a timbre set of the person in the vehicle; In response to determining that the vehicle speed is less than or equal to a preset value, the timbre in the timbre set of the occupant's timbre is set as a target timbre that can wake up the vehicle voice system.

2. The method according to claim 1, characterized in that: Before the identification of the voice of the person in the car, the following steps are included: Get the occupancy status of each seat in the car; Determine the number of passengers in the vehicle and their seating positions based on the seating status of each seat; Based on the number of people in the car, an upper limit of the number of recognitions for recognizing the voices of people in the car is determined.

3. The method according to claim 2, characterized in that The step of identifying the timbre of the occupants and storing all the identified timbre of the occupants to form a timbre set of the occupants includes: Directedly identifying the timbre of the person in the vehicle based on the seating position, wherein the timbre of the person in the vehicle has a seating position label; Compare the recognized voice of the person in the car with the stored voice of the person in the car; In response to determining that the recognized timbre of the vehicle occupant is different from the stored timbre of the vehicle occupant, storing the recognized timbre of the vehicle occupant, and continuing to recognize new timbre of the vehicle occupant until the number of stored timbre of the vehicle occupant reaches the upper limit of the number of recognitions; The stored timbre of the people in the car is combined to form a timbre set of the people in the car.

4. The method according to claim 3, characterized in that The method of directionally identifying the voice of a person in the vehicle based on the seating position includes: Based on the seating position, establish patrol identification rules, the patrol identification rules include patrol sequence and single seat patrol duration; based on the patrol sequence and single seat patrol duration, directionally identify the voice of the person in the car; or, Determine a first sound emission position among the plurality of seating positions, establish a patrol recognition rule based on the first sound emission position, the patrol recognition rule including a patrol sequence and a single-seat patrol duration; and directionally recognize the voice of a person in the vehicle based on the patrol sequence and the single-seat patrol duration; The patrol order is updated after the voice of a person in the car is recognized.

5. The method according to claim 3, characterized in that: The method of directionally identifying the voice of a person in the vehicle based on the seating position includes: In response to determining that a passenger in the seating position has uttered a voice, a directional identification is performed for the voice of the person in the vehicle at the seating position; wherein the time interval between two adjacent directional identifications is a preset time interval.

6. The method according to claim 1, characterized in that Also includes: In response to determining that the voice of the person in the vehicle is not recognized and the vehicle speed is less than or equal to a preset value, the pre-stored voice is set as a target voice that can wake up the vehicle voice system.

7. The method according to claim 3, characterized in that Also includes: In response to determining that the occupancy status of at least one seat has changed, the upper limit of the recognition quantity is updated based on the change, and the timbre set of the occupants is updated.

8. The method according to claim 7, characterized in that The updating of the timbre set of the vehicle occupants includes: determining the changed seating position as a target timbre update position; In response to determining that the state of the target timbre update position is switched from unoccupied to occupied, the timbre of the person in the vehicle is directionally identified based on the target timbre update position, and stored in the timbre set of the person in the vehicle, until the number of the stored timbre of the person in the vehicle reaches the updated upper limit of the number of identifications, so as to update the timbre set of the person in the vehicle; In response to determining that the state of the target timbre update position has switched from occupied to unoccupied, the timbre of the occupants in the vehicle with the target timbre update position tag is deleted from the timbre set of the occupants in the vehicle until the number of stored timbre of the occupants in the vehicle drops to the updated upper limit of the recognition number, so as to update the timbre set of the occupants in the vehicle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A vehicle, characterized in that: Comprising an electronic device as claimed in claim 9.

Images