Multi-zone speech recognition method, device, vehicle and storage medium

Abstract

The present disclosure relates to a multi-sound zone speech recognition method, device, vehicle and storage medium. In the embodiment of the present disclosure, after acquiring the speech uttered by the user in the cockpit of the target vehicle, it is determined whether the source sound zone of the speech is a locked sound zone of the sound zone that is pre-set to allow voice control of the target vehicle. If the source sound zone is the locked sound zone, speech recognition is performed on the speech, and speech recognition can be performed only on the speech from the locked sound zone, which can avoid interference caused by sounds in other sound zones, thereby improving user experience.

Description

Technical Field

[0001] The present disclosure relates to the field of information technology, and in particular to a multi-zone speech recognition method, device, vehicle and storage medium. Background Art

[0002] Nowadays, in-car voice assistants have become more and more popular. Users can interact with in-car voice assistants to realize functions such as navigation, voice playback and vehicle control.

[0003] To meet the needs of users, the in-vehicle voice assistant can already provide voice services for everyone in the vehicle cabin. However, the all-person voice service will continue to allow people in all positions in the vehicle cabin to interact with the in-vehicle voice assistant at the same time. If the user only wants people in certain positions in the vehicle cabin to interact with the in-vehicle voice assistant in some cases, the user's needs cannot be met. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a multi-zone speech recognition method, device, vehicle and storage medium.

[0005] A first aspect of an embodiment of the present disclosure provides a multi-zone speech recognition method, the method comprising:

[0006] Acquire a voice uttered by a user in a cockpit of a target vehicle; determine whether a source sound zone of the voice is a pre-set locked sound zone, where the locked sound zone is a sound zone that allows voice control of the target vehicle; if the source sound zone is the locked sound zone, perform voice recognition on the voice.

[0007] A second aspect of the embodiments of the present disclosure provides a multi-zone speech recognition device, the device comprising:

[0008] The acquisition module is used to acquire the voice uttered by the user in the cabin of the target vehicle; the judgment module is used to judge whether the source sound zone of the voice is a pre-set locked sound zone, and the locked sound zone is a sound zone that allows voice control of the target vehicle; the recognition module is used to perform voice recognition on the voice if the source sound zone is the locked sound zone.

[0009] A third aspect of an embodiment of the present disclosure provides a vehicle, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the multi-zone speech recognition method as described in the first aspect above is implemented.

[0010] A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the multi-zone speech recognition method as described in the first aspect above is implemented.

[0011] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0012] In the embodiment of the present disclosure, after acquiring the voice uttered by the user in the cockpit of the target vehicle, it is determined whether the source sound zone of the voice is a locked sound zone that is pre-set to allow voice control of the target vehicle. If the source sound zone is the locked sound zone, voice recognition is performed on the voice. If the user only wants people in certain positions in the vehicle cockpit to be able to voice interact with the on-board voice assistant in some cases, the area for voice control can be locked in advance according to user needs, that is, the locked sound zone of the sound zone that is allowed to voice control the target vehicle is pre-set according to user needs, and voice recognition is only performed on the voice originating from the locked sound zone, which can avoid interference caused by sounds in other sound zones and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0015] Figure 1 is a schematic diagram of a vehicle cockpit of a multi-tone zone speech recognition method provided by an embodiment of the present disclosure;

[0016] Figure 2 is a flow chart of a multi-tone zone speech recognition method provided by an embodiment of the present disclosure;

[0017] Figure 3 It is a schematic diagram of a sound zone setting interface for multi-sound zone speech recognition provided by an embodiment of the present disclosure;

[0018] Figure 4 is a flow chart of another multi-tone zone speech recognition method provided by an embodiment of the present disclosure;

[0019] Figure 5 It is a structural schematic diagram of a multi-tone zone speech recognition device provided by an embodiment of the present disclosure;

[0020] Figure 6 It is a structural schematic diagram of a vehicle provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0023] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0024] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The multi-zone speech recognition method provided by the embodiment of the present disclosure can be applied to a vehicle cockpit. In order to enable all members in the cockpit to use the voice service, one or more microphones can be set in the vehicle cockpit. The range of sound received by a microphone is called a sound zone. A sound zone can correspond to one or more seat areas. The microphone can subdivide the space in the vehicle into multiple independent sound zones, and can independently collect voice signals for each sound zone. The microphone makes each sound zone have sufficient isolation, and can isolate the sound from other sound zones. The microphone can send the collected voice signal to a multi-zone speech recognition device, and the multi-zone speech recognition device can process the voice signals of each sound zone to realize speech recognition and speech interaction. The result of speech recognition can also be sent to the car screen, and the car screen displays the result to visualize the process of speech recognition. Among them, the microphone is mainly composed of multiple digital microphones, a digital signal processing (Digital Signal Processing, DSP) chip and an automotive audio bus (Automotive AudioBus, A2B) chip.

[0027] For example, Figure 1 A schematic diagram of a vehicle cockpit for a multi-zone voice recognition method provided by an embodiment of the present disclosure, wherein the cockpit space 100 is divided into six zones from the front to the rear of the vehicle, 101 is the main driver's zone, covering the main driver's seat area; 102 is the co-driver's zone, covering the co-driver's seat area; 103 is the second row left zone, covering the second row left seat area; 104 is the second row right zone, covering the second row right seat area; 105 is the third row left zone, covering the third row left seat area; 106 is the third row right zone, covering the third row right seat area, each zone is equipped with a microphone with a corresponding sound receiving range, and the six zones can realize independent sound pickup and can automatically shield the sound sources of other zones. For example, if someone is making a phone call in a certain zone, then voice recognition can be performed normally for other zones without interference. 107 is the vehicle screen on the center console, which can visualize the process of voice recognition. Figure 1 This is only an exemplary description of the vehicle cockpit of the multi-zone speech recognition method, not the only description.

[0028] Related technologies To meet the needs of users, in-vehicle voice assistants can already provide voice services for everyone in the vehicle cabin. However, the full-person voice service will continue to allow people in all positions in the vehicle cabin to interact with the in-vehicle voice assistant at the same time. If the user only wants people in certain positions in the vehicle cabin to interact with the in-vehicle voice assistant in some cases, the user's needs cannot be met.

[0029] In response to the defects of related technologies in voice interaction functions, the embodiments of the present disclosure provide a multi-zone voice recognition method, device, vehicle and storage medium, which can pre-set and lock the area for voice control according to user needs, that is, pre-set the locked audio zone of the audio zone that allows voice control of the target vehicle according to user needs, and only perform voice recognition on the voice originating from the locked audio zone, which can avoid interference caused by sounds in other audio zones and improve user experience.

[0030] In order to better understand the inventive concept of the embodiments of the present disclosure, the technical solutions of the embodiments of the present disclosure are described below in conjunction with exemplary embodiments.

[0031] Figure 2 1 is a flow chart of a multi-zone speech recognition method provided by an embodiment of the present disclosure, which can be executed by a multi-zone speech recognition device disposed in a target vehicle. Figure 2 As shown, the multi-zone speech recognition method provided by this embodiment includes the following steps:

[0032] Step 201: Acquire a voice uttered by a user in a cabin of a target vehicle.

[0033] In the disclosed embodiment, when a user in the cabin of a target vehicle wants to perform voice interaction with an in-vehicle voice assistant in the target vehicle, the user can utter a voice, and the multi-zone voice recognition device can acquire the voice uttered by the user.

[0034] Optionally, a microphone installed in the target vehicle can collect the voice uttered by the user in the cockpit and send it to the multi-zone voice recognition device, so that the multi-zone voice recognition device can obtain the voice uttered by the user.

[0035] Step 202: determine whether the source audio zone of the voice is a preset locked audio zone, where the locked audio zone is an audio zone that allows voice control of the target vehicle.

[0036] In the disclosed embodiment, after acquiring the voice uttered by the user, the multi-zone speech recognition device can determine whether the source zone of the voice is a preset locked zone.

[0037] The source sound zone in the embodiment of the present disclosure can be understood as the sound zone where the user who utters the voice is located. Since a sound zone is the range in which a microphone receives sound, that is, the microphone and the sound zone are one-to-one corresponding, the sound zone where the user is located, that is, the source sound zone of the voice, can be determined by the sound zone corresponding to the microphone that receives the voice.

[0038] In some embodiments, before step 202, the multi-zone speech recognition method may further include: determining a target microphone for collecting speech; and determining the zone to which the target microphone belongs as the source zone.

[0039] Specifically, the multi-zone speech recognition device can first determine the microphone that collects the user's voice, and then determine the microphone that collects the user's voice as the target microphone, and then determine the sound zone to which the target microphone belongs according to the range of sound received by the target microphone, and determine the sound zone to which the target microphone belongs as the source sound zone.

[0040] Among them, each sound zone can have a unique sound zone identifier, and the target vehicle can pre-store the sound zone identifiers of each sound zone corresponding to the range of sound received by each microphone. Therefore, after the target vehicle determines the target microphone, the sound zone identifier corresponding to the pre-stored target microphone can be obtained, and then the sound zone corresponding to the obtained sound zone identifier is used as the source sound zone.

[0041] The locked sound zone in the embodiment of the present disclosure can be understood as a sound zone that allows voice control of the target vehicle. The user can speak in the locked sound zone to achieve voice control of the target vehicle through voice interaction. The unlocked sound zone can be understood as a sound zone that prohibits voice control of the target vehicle. Even if the user speaks in the unlocked sound zone, he cannot achieve voice control of the target vehicle through voice interaction.

[0042] Since a sound zone can have a unique sound zone identifier, to determine whether the source sound zone of the speech is a preset locked sound zone, the sound zone identifier of the source sound zone can be compared with the sound zone identifier of the preset locked sound zone. If the sound zone identifiers are the same, it is determined that the source sound zone is the locked sound zone; otherwise, it is determined that the source sound zone is not the locked sound zone.

[0043] Step 203: If the source sound zone is the locked sound zone, perform speech recognition on the speech.

[0044] In some embodiments of the present disclosure, after the multi-zone speech recognition device determines whether the source sound zone of the speech is a pre-set locked sound zone, if the source sound zone is determined to be the locked sound zone, it means that the user is uttering the speech in the locked sound zone. Therefore, the target vehicle can perform speech recognition on the acquired voice signal.

[0045] Specifically, the multi-zone speech recognition device can first perform speech recognition on the speech to obtain the speech text corresponding to the speech, and then perform semantic recognition on the speech text to obtain the semantics corresponding to the speech. If the semantics corresponding to the speech is a control instruction, the control instruction is executed; if the semantics corresponding to the speech is the content of the conversation between the user and the in-vehicle voice assistant, an answer can be generated for the conversation content, and the answer can be broadcast or displayed.

[0046] In the embodiment of the present disclosure, after acquiring the voice uttered by the user in the cockpit of the target vehicle, it is determined whether the source sound zone of the voice is a locked sound zone that is pre-set to allow voice control of the target vehicle. If the source sound zone is the locked sound zone, voice recognition is performed on the voice. If the user only wants people in certain positions in the vehicle cockpit to be able to voice interact with the on-board voice assistant in some cases, the area for voice control can be locked in advance according to user needs, that is, the locked sound zone of the sound zone that is allowed to voice control the target vehicle is pre-set according to user needs, and voice recognition is only performed on the voice originating from the locked sound zone, which can avoid interference caused by sounds in other sound zones and improve user experience.

[0047] In some other embodiments of the present disclosure, if it is determined that the source sound zone is not a locked sound zone, the multi-sound zone speech recognition device can output prompt information, which can be used to indicate that the source sound zone is a sound zone where voice control of the target vehicle is prohibited.

[0048] In some embodiments, the prompt information may be a graphic prompt information displayed on the screen. For example, the text "The source sound zone is not a locked sound zone" or "The source sound zone is a sound zone where voice control of the target vehicle is prohibited" may be displayed on the vehicle screen.

[0049] In some embodiments, the prompt information can be a voice prompt information played through a speaker, for example, a voice message "the source sound zone is not a locked sound zone" or "the source sound zone is a sound zone where voice control of the target vehicle is prohibited" can be played through a speaker on the target vehicle.

[0050] After receiving the prompt message, if the user wants to continue voice interaction in the sound zone, the user can lock the source sound zone and set the source sound zone as the locked sound zone.

[0051] In some other embodiments of the present disclosure, the user may also set the target vehicle to the sound zone suppression mode as needed.

[0052] The sound zone suppression mode can be understood as all sound zones of the target vehicle cannot perform voice control on the target vehicle, that is, all voice recognition functions of the target vehicle cannot be used. Only when the target vehicle is not in the sound zone suppression mode, the microphone of the target vehicle can obtain the voice of the user in the cabin of the target vehicle.

[0053] In some embodiments, when the target vehicle is not in the sound zone suppression mode, the multi-sound zone speech recognition device can obtain the speech of the user in the cockpit of the target vehicle. When the target vehicle is in the sound zone suppression mode, the multi-sound zone speech recognition device cannot obtain the speech of the user in the cockpit of the target vehicle.

[0054] Thereby, it can be ensured that the target vehicle acquires the voice uttered by the user in the cabin of the target vehicle in the non-sound zone suppression mode.

[0055] In other embodiments, after acquiring the voice uttered by the user in the cabin of the target vehicle, the multi-zone speech recognition device can determine whether the target vehicle is in the sound zone suppression mode, and if the target vehicle is not in the sound zone suppression mode, determine whether the source sound zone of the voice is a pre-set locked sound zone; if the target vehicle is in the sound zone suppression mode, the step of determining whether the source sound zone of the voice is a pre-set locked sound zone cannot be performed.

[0056] Thus, it can be ensured that the step of determining whether the source sound zone of the speech is a preset locked sound zone is performed in the non-sound zone suppression mode.

[0057] In these embodiments, optionally, after all users in the cockpit have completed voice interaction with the target vehicle, or when all users in the cockpit temporarily do not need to voice control the target vehicle, the user can input a sound zone suppression operation for the target vehicle to the multi-zone voice recognition device, so that the multi-zone voice recognition device can respond to the sound zone suppression operation for the target vehicle and set the target vehicle to the sound zone suppression mode.

[0058] Among them, the sound zone suppression operation may include a click operation on a sound zone suppression virtual button on the vehicle screen, and may also include a click operation on a sound zone suppression physical button on the target vehicle. There is no restriction here. The multi-sound zone speech recognition device of the target vehicle responds to the sound zone suppression operation on the target vehicle and sets the target vehicle to the sound zone suppression mode, so that the sound zone suppression mode can be switched with one click.

[0059] Furthermore, when the target vehicle is in the sound zone suppression mode, when the user in the cockpit needs to perform voice control on the target vehicle, the user can input a sound zone suppression cancellation operation for the target vehicle into the multi-sound zone speech recognition device, so that the target vehicle leaves the sound zone suppression mode.

[0060] Among them, the sound zone suppression cancellation operation may include a click operation on a sound zone suppression cancellation virtual button on the vehicle computer screen, and may also include a click operation on a sound zone suppression cancellation physical button on the target vehicle. There is no limitation here. The multi-sound zone speech recognition device of the target vehicle can cancel the sound zone suppression mode with one click in response to the sound zone suppression cancellation operation of the target vehicle, so that the multi-sound zone speech recognition device can respond to the sound zone suppression cancellation operation of the target vehicle and make the target vehicle enter the non-sound zone suppression mode.

[0061] Therefore, the user can switch between the sound zone suppression mode and the non-sound zone suppression mode according to actual needs, thereby improving the user experience.

[0062] In some further embodiments of the present disclosure, the user may also set a locked sound zone and an unlocked sound zone as needed.

[0063] In some embodiments, when a user wants to allow voice control of a target vehicle by voice within a first sound zone among multiple sound zones, the user can input a lock setting operation for the first sound zone into the multi-zone voice recognition device, so that the multi-zone voice recognition device can set the first sound zone as a locked sound zone in response to detecting the lock setting operation for the first sound zone.

[0064] The first sound zone may be a sound zone in which the user wants to allow voice control of the target vehicle, and the first sound zone may include one or more sound zones of the target vehicle.

[0065] The lock setting operation may include a click operation on a virtual button for locking the audio zone on the vehicle screen, and may also include a click operation on a physical button for locking the audio zone on the target vehicle. There is no limitation here. In response to detecting a lock setting operation on the first audio zone, the multi-zone speech recognition device of the target vehicle sets the first audio zone as a locked audio zone, and sets audio zones outside the first audio zone as non-locked audio zones.

[0066] In other embodiments, when a user wants to prohibit voice control of a target vehicle by sound in a second sound zone among multiple sound zones, the user can input a lock cancellation operation on the second sound zone into the multi-zone voice recognition device, so that the multi-zone voice recognition device can set the second sound zone as a non-locked sound zone in response to detecting the lock cancellation operation on the second sound zone.

[0067] The second audio zone may be a audio zone where the user wants to prohibit voice control of the target vehicle, and the second audio zone may include one or more locked audio zones of the target vehicle.

[0068] The lock cancel operation may include a click operation on a lock cancel virtual button on the vehicle screen, and may also include a click operation on a lock cancel physical button on the target vehicle. There is no limitation here. The multi-zone voice recognition device of the target vehicle sets the second zone as a non-locked zone in response to detecting a lock cancel operation on the second zone.

[0069] Optionally, the second sound zone can be the same sound zone as the first sound zone, that is, after the user sets the first sound zone as the locked sound zone, before the sound in the first sound zone interacts with the target vehicle by voice, during the voice interaction, or after the voice interaction, that is, at any time after the user sets the first sound zone as the locked sound zone, if the user wants to prohibit the sound in the first sound zone from voice controlling the target vehicle, the first sound zone can be switched from a locked sound zone to a non-locked sound zone.

[0070] In some examples, the car screen or physical buttons can be installed on the center console of the target vehicle. The center console can be understood as the vehicle control area located in front of the driver and co-driver areas. Users can use the car screen or physical buttons on the center console to perform operations such as sound zone suppression, sound zone suppression cancellation, sound zone lock, and lock cancellation.

[0071] In other examples, in addition to being installed on the center console of the target vehicle, the car screen or physical button can also be installed in each sound zone of the target vehicle, that is, each sound zone has a corresponding car screen or physical button. The user can suppress the sound zone, lock the sound zone, cancel the lock, and perform other operations through the car screen or physical button on the center console, or suppress the sound zone, cancel the sound zone suppression, lock the sound zone, cancel the lock, and perform other operations through the car screen or physical button in the sound zone where the user is located.

[0072] Figure 3 A schematic diagram of a sound zone setting interface for multi-zone speech recognition provided by an embodiment of the present disclosure. As shown in the figure, the interface can be operated and displayed on the vehicle screen. 301 is a sound zone suppression virtual button, 302 is a suppression cancel virtual button, 303 is a sound zone lock virtual button, 304 is a lock cancel virtual button, and 305 is a sound zone selection area. When the user needs to perform a sound zone suppression operation, the user can directly click the sound zone suppression button on the interface. The multi-zone speech recognition device responds to the sound zone suppression operation and enters the sound zone suppression mode. When the user needs to cancel the suppression operation, the user can directly click the suppression cancel button on the interface. The multi-zone speech recognition device enters the sound zone suppression mode. The sound recognition device responds to the sound zone cancel operation and enters the non-sound zone suppression mode; when the user needs to perform a sound zone locking operation, he can select the sound zone to be locked in the sound zone selection interface, click the confirm selection button after selection, and then click the sound zone lock button. The multi-zone speech recognition device responds to the sound zone locking operation and can lock the selected sound zone. When the user needs to perform a lock cancel operation, he can select the sound zone to be unlocked in the sound zone selection interface, click the confirm selection button after selection, and then click the cancel lock button. The multi-zone speech recognition device responds to the lock cancel operation and can cancel the lock of the selected sound zone.

[0073] In some further embodiments of the present disclosure, the multi-zone speech recognition device may directly determine the source zone of the speech based on the microphone that collects the speech, and may also modify the determined source zone to more accurately determine the source of the speech.

[0074] In some embodiments, a multi-zone speech recognition device can, after acquiring a speech uttered by a user in a cockpit of a target vehicle, determine a target microphone for collecting the speech, determine the sound zone to which the target microphone belongs as a source sound zone, and then determine whether the source sound zone of the speech is a pre-set locked sound zone. If the source sound zone is a locked sound zone, speech recognition is performed on the speech.

[0075] In other embodiments, before determining whether the source sound zone of the speech is a preset locked sound zone, the multi-sound zone speech recognition device may further perform sound zone correction on the source sound zone, and then determine whether the corrected source sound zone is a preset locked sound zone. If the source sound zone is a locked sound zone, speech recognition is performed on the speech, such as Figure 4 shown.

[0076] Figure 4 FIG. 1 is a flow chart of another multi-tone speech recognition method provided by an embodiment of the present disclosure. Figure 4 As shown, the multi-zone speech recognition method provided by this embodiment includes the following steps:

[0077] Step 401: Acquire a voice uttered by a user in a cabin of a target vehicle.

[0078] Step 402: determine a target microphone for collecting voice, and determine the sound zone to which the target microphone belongs as the source sound zone.

[0079] Steps 401-402 in the embodiment of the present disclosure may refer to the above-mentioned steps 201-202, which will not be repeated here.

[0080] Step 403: perform sound zone correction on the source sound zone.

[0081] In the disclosed embodiment, the sound zone correction of the source sound zone can be understood as the correction of the sound zone position of the source sound zone. The target vehicle can arrange at least one car screen in front of the sound zone to which each row of seats belongs, or arrange a car screen behind the backrest of the front seat in each sound zone. The car screen can display the instructions and results of the voice recognition in the sound zone, which is convenient for the user to interact with the vehicle. When the seat is lying down or the person's head and buttocks are separated due to the side face speaking, the source sound zone determined based on the sound zone to which the target microphone for collecting voice belongs will not meet the actual needs, so that the instructions displayed on the car screen corresponding to the sound zone are not in front of the speaker. For example, the user sits on the main driver's seat and lies the main driver's seat to the left of the second row. At this time, when the user interacts with the voice, the microphone in the left sound zone of the second row will collect the user's voice and display the voice on the car screen of the sound zone to which the second row belongs or the car screen behind the backrest of the main driver's seat, making it difficult for the user in the main driver's seat to see the voice instructions displayed on the car screen. Therefore, it is necessary to correct the source sound zone so that the instructions displayed on the car screen in the source sound zone are always in front of the speaker, which meets the actual use needs.

[0082] In some embodiments, the source sound zone may be corrected based on the seat data, which may include steps 4031-4032:

[0083] Step 4031: Receive seat data, where the seat data includes at least one of seat pressure data and seat posture data.

[0084] In the disclosed embodiment, the multi-zone speech recognition device of the target vehicle receives seat data of all seats, wherein the seat pressure data can be understood as the pressure on the seat surface and can be obtained through the pressure sensor inside the seat, and the seat posture data can include the seat back angle in the longitudinal direction from the front to the rear of the vehicle.

[0085] Step 4032: Based on the seat data, perform sound zone correction on the source sound zone.

[0086] In the disclosed embodiment, the position of the sound zone can be divided according to the position of the seats in the sound zone. Taking a three-row seat vehicle as an example, the row positions of the sound zone include one row, two rows and three rows in the direction from the front to the rear of the vehicle. The preset sound zone correction coefficients of the sound zones in the same row position are the same, the first preset sound zone correction coefficient of the one row is greater than the second preset sound zone correction coefficient of the two row, and the second preset sound zone correction coefficient of the two row is greater than the third preset sound zone correction coefficient of the three row, wherein the preset sound zone correction coefficient can be understood as the weight of the sound zone correction. The weight of the sound zone correction for each row of seats in this embodiment can be understood as summarized according to the number of actual application scenarios. Assuming that there are two seats in each row, one seat in the first row is in the first position and the other seat is in the second position, one seat in the second row is in the third position and the other seat is in the fourth position, one seat in the third row is in the fifth position and the other seat is in the sixth position.

[0087] In some examples, the source sound zone may be modified based on the seat pressure data, which may include:

[0088] Optionally, when the pressure of a seat in the source sound zone is greater than a preset pressure threshold and the pressure of a seat in any other position is less than the preset pressure threshold, the source sound zone is not corrected.

[0089] Optionally, when the position of the source sound zone is the first position in a row and the pressure of the seat at the first position is less than a preset pressure threshold, if the pressure of the seat at the second position in the row is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the sound zone at the second position is determined to be the corrected sound zone. For example, when the position of the source sound zone is the main driver's seat area and the pressure of the main driver's seat is less than the preset pressure threshold, if the pressure of the passenger seat is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the sound zone at the passenger seat is determined to be the corrected sound zone.

[0090] If the pressure of seats at any position in the second and third rows is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, no correction is made to the source sound zone.

[0091] Optionally, when the position of the source sound zone is the third position in the second row and the pressure of the seat in the third position is less than the preset pressure threshold, if the pressure of the seat in the first position of the first row is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the first position is determined to be the corrected sound zone. For example, the position of the source sound zone is the left area of ​​the second row and the seat pressure in the left area of ​​the second row is less than the preset pressure threshold, if the pressure of the main driver's seat is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the sound zone at the main driver's seat is determined to be the corrected sound zone; if the pressure of the seat in the fourth position of the second row is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the sound zone at the fourth position is determined to be the corrected sound zone;

[0092] If the pressure of the seats at the fourth position and any position in the three rows is greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the sound zone at the third position is determined to be the corrected sound zone.

[0093] Optionally, when the position of the source sound zone is the fifth position in the three rows and the pressure of the seat at the fifth position is less than the preset pressure threshold, if the pressure of the seat at the fourth position in the second row is greater than or equal to the preset pressure threshold and the surface pressures of the remaining seats are less than the preset pressure threshold, the sound zone at the fourth position is determined to be the corrected sound zone.

[0094] In other examples, the source sound zone may be corrected based on the seat pressure data and the seat posture data, which may include:

[0095] Optionally, when the source sound zone is located at the third position in the second row, and the pressure of the seat at the third position is less than the preset pressure threshold, if the pressure of the seat at the front row corresponding to the third position and the pressure of the seat at the fourth position in the second row are both greater than or equal to the preset pressure threshold, the pressure of the remaining seats is less than the preset pressure threshold, and the seat back angle at the front row is greater than or equal to the preset angle threshold, the sound zone at the front row is determined to be a corrected sound zone. For example, when the source sound zone is located at the left area of ​​the second row, and the seat pressure at the left area of ​​the second row is less than the preset pressure threshold, if the pressure of the main driver's seat and the pressure of the seat at the right of the second row are both greater than or equal to the preset pressure threshold, and the pressure of the remaining seats is less than the preset pressure threshold, the sound zone at the main driver's position is determined to be a corrected sound zone. The scenario at this time is that the main driver's seat lies down to the left of the second row, the user speaks in the left area of ​​the second row, there are people in the right area of ​​the second row, and the source sound zone is the left of the second row. After the sound zone correction, the sound zone at the main driver's position is determined as the final source sound zone.

[0096] Optionally, when the position of the source sound zone is the fifth position in the three rows and the pressure of the seat in the fifth position is less than a preset pressure threshold, if the pressure of the seat in the front row and the pressure of the seat in the back row corresponding to the fifth position are both greater than or equal to the preset pressure threshold, the pressure of the remaining seats is less than the preset pressure threshold, and the seat back angle of the front row is greater than or equal to the preset angle threshold, the sound zone in the front row is determined to be a corrected sound zone.

[0097] The preset pressure threshold and the preset angle threshold in the embodiment of the present disclosure can be set as needed, without specific limitation here. When the pressure of the seat is greater than or equal to the preset pressure threshold, it can be considered that there is someone on the seat, and when the pressure of the seat is less than the preset pressure threshold, it can be considered that there is no one on the seat; when the seat back angle is greater than or equal to the preset angle threshold, it can be considered that the seat back is tilted toward the rear area, and when the seat back angle is less than the preset angle threshold, it can be considered that the seat back is tilted toward the area where it is located.

[0098] In some other embodiments, the source sound area may be modified based on the image data, which may include steps 4033-4034:

[0099] Step 4033: Receive image data in the cockpit.

[0100] The image data in the embodiment of the present disclosure can be understood as the image data sent by the camera to the multi-zone speech recognition device. Specifically,

[0101] The target vehicle can arrange at least one camera in front of the sound zone to which each row of seats belongs, or arrange a camera behind the backrest of the front seat in each sound zone, or arrange a camera at the front of the cabin, so that the camera can capture the image of any sound zone inside the cabin of the target vehicle. After the camera converts the captured image into image data, the image data is sent to the multi-sound zone speech recognition device.

[0102] Step 4034: Based on the seat data and the image data, perform sound zone correction on the source sound zone.

[0103] In some embodiments, the source sound zone may be corrected based on the image data:

[0104] Optionally, a human figure in the image that is located within the seat range corresponding to the source sound zone is detected. If a human head is detected within the seat range in the image, the person's sitting posture is determined. If the sitting posture is in the sound zone corresponding to the seat area of ​​the human head, but the body is in other sound zones, where the body refers to the other parts of the human body except the head, the sound zone where the body is located is used as the corrected source sound zone. If the sitting posture is in the sound zone corresponding to the seat area of ​​the human head and body, no correction is required. If two human heads are detected within the seat range in the image, no correction is required.

[0105] In some other embodiments, the source sound zone may be modified based on the seat data and the image data:

[0106] Optionally, the multi-zone speech recognition device can obtain seat data and image data at the same time, or obtain image data after correcting the second source sound zone based on the seat data. The multi-zone speech recognition device can first correct the source sound zone based on the seat data to obtain the first confirmed source sound zone, and then determine whether there is someone in the first confirmed source sound zone by analyzing the image data. If there is someone in the first confirmed source sound zone, no correction will be made, and the first confirmed source sound zone will be determined as the final source sound zone; if there is no one in the first confirmed source sound zone, the source sound zone before the first confirmation will be determined as the final source sound zone.

[0107] Step 404: Determine whether the source audio zone of the voice is a preset locked audio zone.

[0108] Step 405: If the source sound zone is the locked sound zone, perform speech recognition on the speech.

[0109] Steps 404-405 in the embodiment of the present disclosure may refer to the above steps 202-203, which will not be repeated here.

[0110] In the disclosed embodiment, a voice uttered by a user in a cockpit of a target vehicle is acquired, a target microphone for collecting the voice is determined, and a sound zone to which the target microphone belongs is determined as a source sound zone; sound zone correction is performed on the source sound zone; it is determined whether the source sound zone of the voice is a pre-set locked sound zone; if the source sound zone is a locked sound zone, voice recognition is performed on the voice, and sound zone correction is performed on the source sound zone, so that the voice control command displayed on the vehicle computer screen in the source sound zone is always in front of the speaker, which meets the actual use needs of the user, and the area for voice control can be pre-set according to the user's needs to be locked, that is, a locked sound zone for the sound zone that allows voice control of the target vehicle is pre-set according to the user's needs, and voice recognition is only performed on the voice originating from the locked sound zone, which can avoid interference caused by sounds in other sound zones and improve the user experience.

[0111] Figure 5 is a schematic diagram of the structure of a multi-tone speech recognition device provided by an embodiment of the present disclosure, and the device can be understood as a partial functional module of the above-mentioned vehicle. Figure 5 As shown, the multi-tone zone speech recognition device 500 includes:

[0112] An acquisition module 501 is used to acquire a voice uttered by a user in a cabin of a target vehicle;

[0113] The judging module 502 is used to judge whether the source audio zone of the voice is a preset locked audio zone, where the locked audio zone is an audio zone that allows voice control of the target vehicle;

[0114] The recognition module 503 is used to perform speech recognition on the speech if the source sound zone is the locked sound zone.

[0115] In the disclosed embodiment, after the acquisition module acquires the voice uttered by the user in the cockpit of the target vehicle, the judgment module determines whether the source sound zone of the voice is a locked sound zone that is pre-set to allow voice control of the target vehicle. If the source sound zone is the locked sound zone, the recognition module performs voice recognition on the voice. If the user only wants people in certain positions in the vehicle cockpit to be able to interact with the on-board voice assistant by voice in some cases, the area for voice control can be locked in advance according to user needs, that is, the locked sound zone of the sound zone that allows voice control of the target vehicle is pre-set according to user needs, and only voice originating from the locked sound zone is recognized, which can avoid interference caused by sounds in other sound zones and improve user experience.

[0116] Optionally, the multi-zone speech recognition device 500 includes:

[0117] The output module is used to output prompt information if the source sound zone is not the locked sound zone, and the prompt information is used to prompt that the source sound zone is a sound zone where voice control of the target vehicle is prohibited.

[0118] Optionally, the multi-zone speech recognition device 500 includes:

[0119] A first determination module is used to determine a target microphone for collecting voice;

[0120] The second determining module is used to determine the sound zone to which the target microphone belongs as the source sound zone.

[0121] Optionally, the multi-zone speech recognition device 500 includes:

[0122] A first receiving module, configured to receive seat data, the seat data including at least one of seat pressure data and seat posture data;

[0123] The first correction module is used to correct the source sound zone based on the seat data.

[0124] Optionally, the multi-zone speech recognition device 500 includes:

[0125] A second receiving module, used for receiving image data in the cockpit;

[0126] The second correction module is used to correct the source sound zone based on the image data.

[0127] Optionally, the multi-zone speech recognition device 500 includes:

[0128] The first setting module is used to set the first sound zone as a locked sound zone in response to detecting a locking setting operation on the first sound zone.

[0129] Optionally, the multi-zone speech recognition device 500 includes:

[0130] The second setting module is used to set the second sound zone as a non-locking sound zone in response to detecting a lock canceling operation on the second sound zone, where the non-locking sound zone is a sound zone where voice control of the target vehicle is prohibited.

[0131] The multi-zone speech recognition device provided in this embodiment can execute the method described in any of the above embodiments, and its execution method and beneficial effects are similar, which will not be repeated here.

[0132] Figure 6 A schematic structural diagram of a vehicle provided by an embodiment of the present disclosure is shown.

[0133] like Figure 6 As shown, the vehicle may include a processor 601 and a memory 602 storing computer program instructions.

[0134] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0135] The memory 602 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 602 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 602 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 602 is a non-volatile solid-state memory. In a particular embodiment, the memory 602 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0136] The processor 601 reads and executes the computer program instructions stored in the memory 602 to perform the steps of the multi-zone speech recognition method provided in the embodiment of the present disclosure.

[0137] In one example, the vehicle may further include a transceiver 603 and a bus 604. Figure 6 As shown, the processor 601, the memory 602 and the transceiver 603 are connected via a bus 604 and communicate with each other.

[0138] The bus 604 includes hardware, software or both. For example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a Memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 404 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0139] Furthermore, the vehicle may also include a human-computer interaction device, such as a vehicle screen, which can communicate with the processor through a bus. The human-computer interaction device can display the voice control instructions and the corresponding execution results to the user, visualize the voice interaction, and improve the user's voice interaction experience.

[0140] The embodiments of the present disclosure also provide a computer-readable storage medium, which may store a computer program. When the computer program is executed by a processor, the processor implements the multi-zone speech recognition method provided by the embodiments of the present disclosure.

[0141] The above-mentioned storage medium may, for example, include a memory 602 of computer program instructions, and the above-mentioned instructions may be executed by the processor 601 of the voice control device to complete the multi-tone zone speech recognition method provided by the embodiment of the present disclosure. Optionally, the storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc. The above-mentioned computer program may be written in any combination of one or more programming languages ​​to perform the program code of the operation of the embodiment of the present disclosure, and the programming language includes an object-oriented programming language, such as Java, C++, etc., and also includes a conventional procedural programming language, such as "C" language or a similar programming language. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device, partially on the remote computing device, or entirely on the remote computing device or server.

[0142] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-zone speech recognition method, characterized in that: include: Acquire a voice uttered by a user in a cabin of a target vehicle; Determining whether the source sound zone of the voice is a preset locked sound zone, the locked sound zone being a sound zone that allows voice control of the target vehicle; If the source sound zone is the locked sound zone, speech recognition is performed on the speech.

2. The method according to claim 1, characterized in that After determining whether the source sound zone of the voice is a preset locked sound zone, the method further includes: If the source sound zone is not the locked sound zone, a prompt message is output, wherein the prompt message is used to prompt that the source sound zone is a sound zone where voice control of the target vehicle is prohibited.

3. The method according to claim 1, characterized in that Before determining whether the source sound zone of the voice is a preset locked sound zone, the method further includes: Determining a target microphone for collecting the speech; The sound zone to which the target microphone belongs is determined as the source sound zone.

4. The method according to claim 3, characterized in that The method further comprises: receiving seat data, the seat data comprising at least one of seat pressure data and seat posture data; Based on the seat data, the source sound zone is corrected.

5. The method according to claim 3 or 4, characterized in that: The method further comprises: Receiving image data in the cockpit; Based on the image data, the source sound zone is corrected.

6. The method according to claim 1, characterized in that The method further comprises: In response to detecting a lock setting operation on a first sound zone, the first sound zone is set as the lock sound zone.

7. The method according to claim 1, characterized in that The method further comprises: In response to detecting a lock cancel operation on a second sound zone, the second sound zone is set as a non-lock sound zone, where voice control of the target vehicle is prohibited.

8. A multi-zone speech recognition device, characterized in that: The device comprises: An acquisition module, used to acquire a voice uttered by a user in a cockpit of a target vehicle; A judging module, used to judge whether the source sound zone of the voice is a preset locked sound zone, wherein the locked sound zone is a sound zone that allows voice control of the target vehicle; The recognition module is used for performing speech recognition on the speech if the source sound zone is the locked sound zone.

9. A vehicle, characterized in that: The vehicle comprises: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the multi-zone speech recognition method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the multi-zone speech recognition method according to any one of claims 1 to 7 is implemented.

Images