Call method and related device

Abstract

The present application relates to the technical field of device calls, and provides a call method and a related device. The call method comprises: in response to a first operation of a user, displaying a call interface and a first window, the first window comprising a first control and a second control, the first control being used for indicating a first noise reduction mode, the second control being used for indicating a second noise reduction mode, the first control being in a first state, and the second control being in a second state; and in response to a second operation of the user for the second control, setting the second control to the first state, setting the first control to the second state, and setting an electronic device to the second noise reduction mode. In the method, an electronic device can set different noise reduction modes in response to user operations during a call, so that the problem of incapability of adapting to different call scenarios due to too limited noise reduction modes of existing electronic devices is solved, thereby improving the call experience of the user.

Description

Calling methods and related equipment

[0001] This application claims priority to Chinese Patent Application No. 202410933800.2, filed on July 11, 2024, entitled "Method for Calling and Related Equipment", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of terminal equipment, specifically to communication technology, and particularly to a call method and related equipment. Background Technology

[0003] With the development of terminal technology, electronic devices are becoming increasingly feature-rich, especially call functions (such as audio calls or audio-video calls), which are gradually becoming more commonly used functions of electronic devices.

[0004] In related technologies, electronic devices use default noise reduction technology to reduce the noise of the sound captured by the microphone. The noise reduction mode is too simple and cannot be adapted to different scenarios. Users have limited choices of noise reduction mode and cannot meet users' call noise reduction needs in different scenarios. Summary of the Invention

[0005] In view of the above, it is necessary to provide a call method and related equipment that can solve the problem that the noise mode of existing electronic devices is too singular and cannot adapt to different scenarios.

[0006] Firstly, this application provides a call method applied to an electronic device. The call method may include: responding to a first user operation, displaying a call interface and a first window, the first window including a first control and a second control, the first control indicating a first noise reduction mode, the second control indicating a second noise reduction mode, the first control being in a first state, and the second control being in a second state; responding to a second user operation on the second control, the second control being set to the first state, the first control being set to the second state, and the electronic device being set to the second noise reduction mode. Using the above technical solution, the electronic device can display a call interface and also a first window, allowing the user to switch the noise reduction mode of the electronic device from the first noise reduction mode to the second noise reduction mode through the first window. Furthermore, the first window can display the interchangeable states of the controls corresponding to the first and second noise reduction modes, enabling the user to intuitively understand the switching of the noise reduction mode of the electronic device.

[0007] In one possible implementation, the first window includes a first form and a second form. When the first window is in the first form, it displays a first control and a second control. When the first window is in the second form, it displays a control in its first state. Using this technical solution, the first window can have different display forms, and different display forms can correspond to different window sizes and different display content to meet different user needs. For example, when the first window is in the first form, it displays a first control and a second control, facilitating the user to switch noise reduction modes. When the first window is in the second form, it displays a control in its first state, allowing the user to determine the noise reduction mode of the electronic device based on the controls in their first state. Furthermore, the second form of the first window obstructs the call interface less than the first form, allowing the user to see the information displayed on the call interface more completely.

[0008] In one possible implementation, in response to a user's second operation on the second control, the second control is set to a first state, the first control is set to a second state, and the electronic device is set to a second noise reduction mode. This includes: in response to the user's second operation on the second control, the second control is switched from the second state to the first state, the first control is switched from the first state to the second state, and the electronic device is switched from the first noise reduction mode to the second noise reduction mode. Using the above technical solution, the electronic device can respond to the user's operation on the second control, realizing the switching of the states of the two controls in the first window and the switching of the internal sound signal processing logic of the device. That is, a single click by the user can trigger the electronic device to complete the dual switching of the control state and the noise reduction mode.

[0009] In one possible implementation, the first state is the selected state, and the second state is the unselected state. Using the above technical solution, only one of the first and second controls is selected, while the other is unselected. The noise reduction mode of the electronic device is the noise reduction mode indicated by the selected control, thus clearly reminding the user of the current noise reduction mode used by the electronic device.

[0010] In one possible implementation, the electronic device has a preset application installed, which includes a call noise reduction mode interface for displaying a first control and a second control. By adopting the above technical solution, and by setting up a call noise reduction mode interface for displaying the first and second controls in the preset application, users can conveniently set the noise reduction mode of the electronic device during non-call times (e.g., before or after a call).

[0011] In one possible implementation, the call noise reduction mode interface may further include a third control. This third control indicates whether the electronic device stores voiceprint information. When the electronic device stores voiceprint information, the third control is in a third state; when the electronic device does not store voiceprint information, the third control is in a fourth state. The third and fourth states are different. By using the above technical solution, by setting a control in the call noise reduction mode interface to indicate whether the electronic device stores voiceprint information, a clear reminder is provided about whether the electronic device stores voiceprint information. This allows users to easily determine whether the electronic device stores voiceprint information simply by observing the state of the control.

[0012] In one possible implementation, the call method may further include: when the electronic device stores voiceprint information, in response to a third operation by the user on a third control, the voiceprint information stored by the electronic device is deleted. By adopting the above technical solution, the electronic device can support the deletion of stored voiceprint information, and the user can quickly delete the voiceprint information stored by the electronic device through a third control, which facilitates addressing the call needs of different users using electronic devices for voiceprint noise reduction.

[0013] In one possible implementation, the call noise reduction mode interface may further include a fourth control for indicating the recording of voiceprint information. The call method may further include: in response to the user's fourth operation on the fourth control, acquiring the user's spoken audio, extracting voiceprint information from the audio, and storing the extracted voiceprint information. By adopting the above technical solution, electronic devices can support the active recording of user voiceprint information, enabling users to actively record voiceprint information before or after a call, so that subsequent electronic devices can perform voiceprint noise reduction processing on the acquired sound signals based on the user's actively recorded voiceprint information.

[0014] In one possible implementation, the call noise reduction mode interface may further include a fifth control. This fifth control displays a declaration regarding the extraction of voiceprint information. The call method may also include: responding to a user's fifth operation on the fifth control to display an interface displaying the declaration regarding the extraction of voiceprint information. By employing the above technical solution, the electronic device can also display the declaration regarding the extraction of voiceprint information, ensuring the user's right to know about voiceprint extraction and allowing the user to quickly understand information such as the collection and use scope of voiceprint information, and privacy policies through this interface.

[0015] In one possible implementation, in response to a second user operation on the second control, the second control is set to a first state, including: displaying a second window, the second window including a sixth control, in response to the second user operation on the second control; and setting the second control to the first state in response to a sixth user operation on the sixth control. By employing the above technical solution, switching between the control state and the noise reduction mode through a secondary confirmation operation ensures that the switching between a specific control state and the noise reduction mode indicated by the specific control is completed with the user's knowledge.

[0016] In one possible implementation, the second window may further include hyperlink text corresponding to the fifth control, and the call method may further include: in response to a seventh operation by the user on the hyperlink text, displaying an interface showing the declaration content of voiceprint information extraction. Using the above technical solution, the noise reduction mode indicated by the specific control involves voiceprint information extraction. Users can also view the declaration content of voiceprint information extraction through the hyperlink text, ensuring their right to know about voiceprint extraction and allowing them to quickly understand information such as the collection and use scope of voiceprint information, and privacy policies.

[0017] In one possible implementation, the call method may further include: in a second noise reduction mode, acquiring the user's spoken audio, extracting voiceprint information from the audio, and storing the extracted voiceprint information. By employing the above technical solution, the electronic device can autonomously learn and store the user's voiceprint information during a call, facilitating subsequent voiceprint noise reduction processing of the sound signals acquired by the device based on the autonomously learned voiceprint information. This eliminates the need for the user to pre-record their voiceprint information, thus improving the user's call experience.

[0018] In one possible implementation, the call method may further include: if the extracted voiceprint information is inconsistent with the voiceprint information stored in the electronic device, displaying a third window, the third window including information suggesting the user switch to a noise reduction mode. By employing the above technical solution, the electronic device can display information suggesting the user switch to a noise reduction mode when the extracted voiceprint information is inconsistent with its stored voiceprint information, reminding the user to switch to the noise reduction mode in a timely manner. This avoids situations where, if the electronic device is used by a different user, the new user's voice is suppressed during the call because they did not switch to the noise reduction mode in time, making it impossible for the other party to hear the new user's voice clearly.

[0019] In one possible implementation, the electronic device includes a display screen and a camera. The display screen has a punch-hole area corresponding to the camera. A first window is displayed in a first area of ​​the display screen, which includes the punch-hole area. Using this technical solution, the area of ​​the first window displayed on the display screen can overlap with the punch-hole area of ​​the camera, thus fully utilizing the punch-hole area of ​​the camera.

[0020] In one possible implementation, the electronic device includes a display screen and a camera. The display screen has a punch-hole area corresponding to the camera. A first window is displayed in a first area of ​​the display screen, which does not include the punch-hole area. Using this technical solution, the area of ​​the first window displayed on the display screen may not overlap with the punch-hole area of ​​the camera, thus preventing the content displayed in the first window from being obscured by the punch-hole area of ​​the camera.

[0021] In one possible implementation, the first operation includes answering a call or making a call. By employing the above technical solution, users can adjust the noise reduction mode of the electronic device according to the actual needs of the call scenario, thus improving the user's call experience.

[0022] In one possible implementation, the call interface includes a cellular network-based call interface or a Voice over Internet Protocol (VoIP)-based call interface. By employing the above technical solution, users can adjust the noise reduction mode of their electronic devices according to the actual call scenario during cellular network-based or VoIP-based calls, thereby improving the user's call experience.

[0023] In one possible implementation, the first window partially overlaps with the call interface. Using the above technical solution, the first window can partially overlap with the call interface, allowing it to be displayed within the call interface's display area without requiring an additional display area for the first window on the screen.

[0024] In one possible implementation, the call method may further include: displaying a notification bar in response to a user's eighth operation, the notification bar including a first window. Using the above technical solution, when the call interface displayed on the electronic device is switched to displaying the notification bar, the user can also set the noise reduction mode of the electronic device.

[0025] In one possible implementation, the electronic device includes a microphone, a first noise reduction mode corresponds to a first audio signal processing link, and a second noise reduction mode corresponds to a second audio signal processing link. When a first control is in a first state, the electronic device uses the first audio signal processing link to process the audio signal acquired by the microphone. When a second control is in a first state, the electronic device switches from using the first audio signal processing link to using the second audio signal processing link to process the audio signal acquired by the microphone. Using this technical solution, each control can be used to indicate an audio signal processing link. The electronic device uses the audio signal processing link corresponding to the control in the first state to process the audio signal acquired by the microphone, thereby setting the noise reduction mode during a call to the noise reduction mode indicated by the control in the first state.

[0026] In one possible implementation, both the first and second audio signal processing links include any of the following links, and the first and second audio signal processing links are different: echo cancellation, automatic noise suppression (ANS), and adaptive gain amplification are sequentially applied to the audio signal acquired by the microphone; echo cancellation, artificial intelligence (AI) noise reduction, and adaptive gain amplification are sequentially applied to the audio signal acquired by the microphone; echo cancellation, adaptive gain amplification, and voiceprint noise reduction are sequentially applied to the audio signal acquired by the microphone. Using the above technical solutions, different audio signal processing links can employ different methods to process the audio signal acquired by the microphone, achieving different noise reduction effects and realizing different noise reduction modes corresponding to different audio signal processing links.

[0027] In one possible implementation, before sequentially performing echo cancellation, adaptive gain amplification, and voiceprint noise reduction on the audio signal captured by the microphone, the call method may further include: sequentially performing echo cancellation, adaptive gain amplification, and AI noise reduction on the audio signal captured by the microphone, and extracting preset voiceprint information from the audio signal after adaptive gain amplification; and storing the preset voiceprint information in a secure area. Using the above technical solution, before performing voiceprint noise reduction on the audio signal captured by the microphone, the electronic device can autonomously extract voiceprint information based on the user's voice signal during the call and store the extracted voiceprint information in a secure area. This allows for voiceprint noise reduction processing on the audio signal captured by the microphone based on the voiceprint information stored in the secure area after voiceprint extraction, and the storage of the voiceprint information in the secure area ensures the security of the voiceprint information. Furthermore, to ensure call quality during the voiceprint extraction stage, AI noise reduction processing is performed on the audio signal captured by the microphone during the voiceprint extraction stage to suppress ambient noise, making it easier for the other party to hear the user's voice clearly.

[0028] In one possible implementation, the audio signal captured by the microphone is sequentially processed by echo cancellation, adaptive gain amplification, and voiceprint noise reduction. This includes: after storing preset voiceprint information in a secure area, the audio signal captured by the microphone is sequentially processed by echo cancellation, adaptive gain amplification, and voiceprint noise reduction, with the noise reduction based on the preset voiceprint information. Using this technical solution, after extracting the user's voiceprint information, the electronic device can automatically read the stored voiceprint information from the secure area and perform voiceprint noise reduction on the audio signal captured by the microphone based on the voiceprint information. This suppresses ambient noise and interfering human voices, allowing the other party to clearly hear the user's voice and improving the user's call experience.

[0029] In one possible implementation, the electronic device can also autonomously learn and temporarily store the learned voiceprint information during each call when voiceprint noise reduction processing is performed, and delete the learned voiceprint information after the call ends, so as to meet the voiceprint noise reduction needs of different users when using the electronic device for calls, without requiring the new user to actively delete the original user's voiceprint information stored on the electronic device after the electronic device is used by a different user.

[0030] In one possible implementation, if the electronic device supports a smart assistant, it can also perform voiceprint noise reduction on the sound signal collected by the microphone based on the user's voiceprint information extracted from multiple readings of fixed phrases, without requiring the user to actively record voiceprint information again.

[0031] In one possible implementation, the electronic device can support storing one or more voiceprint information, such as storing multiple voiceprint information that is actively recorded, or storing multiple voiceprint information that is autonomously learned during each call, so that the new user does not need to actively delete the original user's voiceprint information stored in the electronic device after the user of the electronic device is changed.

[0032] In the aforementioned call method, the electronic device can display a first window simultaneously with the call interface. This first window may include multiple controls, each indicating a noise reduction mode. Noise reduction modes include, but are not limited to, noise reduction off mode, ambient sound noise reduction mode, and voiceprint noise reduction mode. Noise reduction off mode means that the electronic device does not suppress ambient noise and interfering human voices, preserving the sounds of people and objects in the surrounding environment to the greatest extent possible. Ambient sound noise reduction mode means that the electronic device suppresses ambient noise (but does not suppress interfering human voices), highlighting one or more human voices. Voiceprint noise reduction mode means that the electronic device suppresses ambient noise and interfering human voices, highlighting only specific human voices. The electronic device can respond to user actions on any control, setting the noise reduction mode during the call to the mode indicated by that control. This allows users to set different noise reduction modes according to actual call scenarios (including but not limited to voice calls, video calls, etc.) to meet their noise reduction needs in different scenarios and improve their call experience.

[0033] Secondly, this application provides an electronic device, which includes a microphone, a display screen, a memory, and a processor; the microphone, the display screen, and the memory are all coupled to the processor; the memory is used to store program instructions; and the processor is used to read the program instructions stored in the memory to implement the call method described in the first aspect and its possible implementations.

[0034] Thirdly, this application provides a computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the communication method described in the first aspect and its possible implementations.

[0035] Fourthly, this application provides a computer program product containing computer-readable instructions that, when executed by a processor, implement the call method described in the first aspect and its possible implementations.

[0036] Fifthly, this application provides a chip system coupled to a memory, the chip system being used to read and execute a computer program stored in the memory to implement the call method described in the first aspect and its possible implementations.

[0037] Furthermore, the technical effects brought about by the second to fifth aspects can be found in the descriptions of the methods in the above-mentioned method section, and will not be repeated here. Attached Figure Description

[0038] Figure 1 is a schematic diagram of a call scenario provided in an embodiment of this application;

[0039] Figure 2A is a schematic diagram of an application scenario of a call method provided in an embodiment of this application;

[0040] Figure 2B is a schematic diagram of an application scenario of a call method provided in an embodiment of this application;

[0041] Figure 3A is a set of user interface diagrams provided in an embodiment of this application;

[0042] Figure 3B is a set of user interface diagrams provided in an embodiment of this application;

[0043] Figure 4A is a set of user interface diagrams provided in an embodiment of this application;

[0044] Figure 4B is a set of user interface diagrams provided in an embodiment of this application;

[0045] Figure 4C is a set of user interface diagrams provided in an embodiment of this application;

[0046] Figure 4D is a set of user interface diagrams provided in an embodiment of this application;

[0047] Figure 4E is a set of user interface diagrams provided in an embodiment of this application;

[0048] Figure 5 is a hardware and software architecture diagram of an electronic device provided in an embodiment of this application;

[0049] Figure 6 is a schematic diagram of the interface of the unregistered voiceprint prompt box provided in the embodiment of this application;

[0050] Figure 7 is an interactive flowchart of the internal hardware and software modules of an electronic device in noise reduction off mode according to an embodiment of this application;

[0051] Figure 8 is an interactive flowchart of the internal software and hardware modules of an electronic device in ambient sound noise reduction mode according to an embodiment of this application;

[0052] Figure 9 is an interactive flowchart of the internal hardware and software modules of an electronic device in voiceprint noise reduction mode according to an embodiment of this application;

[0053] Figure 10 is a hardware architecture diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0054] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0055] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of this application, words such as "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary," "or," and "for example" is intended to present the relevant concepts in a concrete manner.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It should be understood that, unless otherwise stated, " / " in this application means "or". For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. "At least one" means one or more. "More than one" means two or more. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, and a, b, and c. It should be understood that the order of steps shown in the flowcharts herein can be changed, and some can be omitted.

[0057] To facilitate understanding of the embodiments of this application, the technical terms involved in this application will first be introduced:

[0058] A user interface (UI) is the medium through which an application or operating system interacts and exchanges information with the user. It converts the internal form of information into a form that the user can understand. The user interface is written in specific computer languages ​​such as Java or Extensible Markup Language (XML). This source code is parsed and rendered on the electronic device, ultimately presenting content that the user can recognize. A common form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed graphically. It can be visible interface elements displayed on the screen of an electronic device, such as text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, and widgets.

[0059] Application (APP): A software program that can perform one or more specific functions. Examples include calling applications, instant messaging applications, video applications, audio applications, image capture applications, cloud desktop applications, etc.

[0060] Figure 1 illustrates a call scenario provided in an embodiment of this application. This scenario includes a first electronic device 100 and a second electronic device 200. Both the first electronic device 100 and the second electronic device 200 can be devices with call functionality. This embodiment does not limit the device types of the first electronic device 100 and the second electronic device 200. For example, the first electronic device 100 and the second electronic device 200 can be mobile phones, tablets, personal computers, Voice over Internet Protocol (VoIP) phones, etc. Figure 1 uses a smartphone as an example, where user A uses the first electronic device 100 and user B uses the second electronic device 200. For instance, the call scenario shown in Figure 1 is a call in an office setting. User A is surrounded by environmental noise (e.g., the sound of colleague C typing on a keyboard) and interfering voices (e.g., colleague C's voice). In this situation, during a call between user B and user A, user B may hear user A's voice mixed with environmental noise and interfering voices, making it difficult for user B to clearly hear what user A is saying, thus affecting the call experience for both parties. As shown in Figure 1, in order for the other party to hear one's voice more clearly, there is a need to reduce environmental noise and interference from human voices.

[0061] For example, the call scenario shown in Figure 1 is a call at the beach. User A is surrounded by environmental noise (e.g., the sound of waves) and interfering human voices (e.g., the interfering human voice is made by a nearby tourist C). User A wants User B to hear the sound of waves, or the sound of waves and interfering human voices, in order to share the beach travel experience. That is, in the call scenario shown in Figure 1, since some types of noise need to be shared, there is no need to reduce the environmental noise and interfering human voices, or only a need to reduce the interfering human voices.

[0062] To reduce ambient noise interference and improve call quality, electronic devices generally enable ambient noise reduction algorithms by default to automatically reduce ambient noise. However, they lack the ability to actively select noise reduction modes for different scenarios, thus failing to meet users' noise reduction needs in various situations.

[0063] In view of this, embodiments of this application provide a call method that enables electronic devices to provide users with the ability to actively select noise reduction modes for different scenarios, thereby meeting users' call noise reduction needs in different scenarios.

[0064] Please refer to Figure 2A, which is a schematic diagram of a scenario for a call method applicable to an embodiment of this application. This scenario includes a first electronic device 100 and a second electronic device 200. The first electronic device 100 and the second electronic device 200 can be devices with call functionality, and this embodiment of the application does not limit the device types of the first electronic device 100 and the second electronic device 200. For example, the first electronic device 100 and the second electronic device 200 can be mobile phones, tablets, personal computers, VoIP phones, etc.

[0065] Taking a scenario where both the first electronic device 100 and the second electronic device 200 are smartphones, both can have applications installed that enable phone calls. The first electronic device 100 can respond to an operation by a first user by initiating a request to establish a call connection with the second electronic device 200. The second electronic device 200 can respond to an operation by a second user by confirming the establishment of a call connection with the first electronic device 100. Thus, the first user and the second user can make calls through the first electronic device 100 and the second electronic device 200. The call can be made via the internet or a carrier network; this embodiment does not limit the scope of the call.

[0066] Please refer to Figure 2B, which is a schematic diagram of a scenario for a call method applicable to an embodiment of this application. This scenario can be a scenario where a first user participates in a multi-person online conference. For example, the first user can participate in a multi-person online conference through a first electronic device 100. Figure 2B illustrates the first electronic device 100 as a tablet computer, which may have an application for making calls (e.g., an online meeting application) installed. The first electronic device 100 can respond to the first user's operation, join the multi-person online conference, and establish a call connection with the electronic devices of other participating users (second user, third user, fourth user, etc.), thereby enabling the first user to conduct online conference calls with other users through the first electronic device 100. The online conference call can be implemented based on the Internet or a carrier network, which is not limited in this embodiment of the application. In some embodiments, the first electronic device 100 and / or the second electronic device 200 may include multiple noise reduction modes, and different noise reduction modes can be used to achieve different noise reduction requirements. For example, multiple noise reduction modes may include, but are not limited to: noise reduction off mode, ambient sound noise reduction mode, and voiceprint noise reduction mode.

[0067] For example, the noise reduction off mode can mean that the electronic device (the electronic device referred to in this application embodiment can be the first electronic device 100 in Figure 2A, or the second electronic device 200, or the first electronic device 100 in Figure 2B) does not suppress environmental noise and interfering human voices in this mode, and can preserve the sounds of people and objects in the surrounding environment to the greatest extent. The noise reduction off mode can be applied to scenarios where users want to transmit call scene information to the other party, such as online musical instrument teaching call scenarios.

[0068] For example, ambient noise reduction mode can refer to a mode in which electronic devices suppress ambient noise (but do not suppress interfering human voices), highlighting one or more human voices. Ambient noise reduction mode is suitable for scenarios involving multiple people in a call, such as a conference call with multiple participants. In ambient noise reduction mode, electronic devices can suppress ambient noise through relevant artificial intelligence (AI) noise reduction models; for example, AI noise reduction models can learn various types of ambient noise in advance.

[0069] For example, voiceprint noise reduction mode can refer to an electronic device suppressing ambient noise and interfering human voices, highlighting only specific human voices. For instance, voiceprint noise reduction mode can be applied to one-on-one calls. In voiceprint noise reduction mode, electronic devices can suppress ambient noise and interfering human voices through relevant voiceprint noise reduction models. For example, the voiceprint noise reduction model can learn the voiceprint information of the registered user and suppress ambient noise and interfering human voices based on the learned voiceprint information.

[0070] In some embodiments, a noise reduction mode can also be configured in the electronic device that only suppresses interfering human voices and does not suppress ambient noise.

[0071] In some embodiments, the electronic device may provide a UI for selecting a noise cancellation mode, allowing users to set or switch the noise cancellation mode of the electronic device.

[0072] For example, as shown in Figure 3A, taking a mobile phone as an example, the electronic device responds to the operation of clicking the settings application icon and displays the settings main interface 101 of the settings application. The settings main interface 101 may include one or more controls, such as "WLAN" control, "Bluetooth" control, "Mobile Network" control, "Smart Connectivity" control, "More Connections" control, "Accessibility" control, etc.

[0073] In response to clicking the “Accessibility” control in the main settings interface 101, the electronic device displays the accessibility interface 102 of the settings application. The accessibility interface 102 may include one or more controls, such as the “Accessibility” control, the “Quick Launch and Gestures” control, the “Smart Multi-Window” control, the “Favorites” control, the “Audio and Video Call Enhancement” control, etc. The “Audio and Video Call Enhancement” control is used to provide functions that may be used in audio and video call mode.

[0074] In response to a click on the "Audio / Video Call Enhancement" control in the accessibility interface 102, the electronic device displays the audio / video call enhancement interface 103. The audio / video call enhancement interface 103 may include one or more controls, such as a "Call Noise Reduction Mode" control, which is used by the user to select a call noise reduction mode.

[0075] In response to clicking the "Call Noise Reduction Mode" control in the audio / video call enhancement interface 103, the electronic device displays the call noise reduction mode interface 104. The call noise reduction mode interface 104 may include one or more controls, each representing one or more call noise reduction modes. Examples include a "Noise Reduction Off" control, an "Ambient Sound Noise Reduction" control, and an "AI Voiceprint Noise Reduction" control. The "Noise Reduction Off" control sets the electronic device's noise reduction mode to noise reduction off mode, the "Ambient Sound Noise Reduction" control sets the electronic device's noise reduction mode to ambient sound noise reduction mode, and the "AI Voiceprint Noise Reduction" control sets the electronic device's noise reduction mode to voiceprint noise reduction mode.

[0076] In some embodiments, text descriptions of the corresponding functions can be displayed below the "Turn off noise cancellation" control, the "Ambient sound noise cancellation" control, and the "AI voiceprint noise cancellation" control to help users understand the function of each control. For example, the text descriptions can be displayed in the mode description box below each control shown in Figure 3A. For example, the "Turn off noise cancellation" control may display the text description "Preserve ambient sound and surrounding voices," the "Ambient sound noise cancellation" control may display the text description "Suppress ambient sound and preserve surrounding voices," and the "AI voiceprint noise cancellation" control may display the text description "Suppress ambient sound and surrounding voices, preserve your voice."

[0077] In some embodiments, the electronic device can autonomously learn voiceprint information during a call to extract and store it, meaning the user does not need to record voiceprint information before the call. Optionally, the electronic device will only store one voiceprint. In voiceprint noise reduction mode, the electronic device can consider sounds other than those corresponding to the stored voiceprint as noise (including interfering human voices and environmental noise).

[0078] In other embodiments, the electronic device may collect and store the user's voiceprint information in advance according to the noise reduction mode setting. For example, if the electronic device includes a voiceprint noise reduction mode, or if it detects that the user has set the noise reduction mode of the electronic device to voiceprint noise reduction mode, the electronic device will collect and store the user's voiceprint information. The collection process may be imperceptible to the user, or it may remind the user through a notification. In practical applications, there are no restrictions on this.

[0079] As shown in Figure 3B(a), the call noise reduction mode interface 104 may also include a "voiceprint information" control and a "description of AI voiceprint noise reduction" control. The "voiceprint information" control can be used to indicate whether the electronic device automatically extracts and stores voiceprint information. In other possible embodiments, the "voiceprint information" control can also be used to actively record the user's voiceprint information.

[0080] The "Instructions on AI Voiceprint Noise Reduction" control can be used to display a statement about extracting the user's voiceprint information in voiceprint noise reduction mode. For example, an electronic device can respond to the user clicking the "Instructions on AI Voiceprint Noise Reduction" control and display an interface that shows the statement about extracting the user's voiceprint information in voiceprint noise reduction mode.

[0081] Before the electronic device stores voiceprint information, the "Voiceprint Information" control displays a "Not Recorded" message, indicating that the electronic device currently does not store voiceprint information. As shown in Figure 3B(b), after the electronic device stores voiceprint information, the "Voiceprint Information" control changes to a "Delete Voiceprint Information" control. The electronic device can delete the currently stored voiceprint information in response to clicking the "Delete Voiceprint Information" control. After deleting the currently stored voiceprint information, the electronic device can autonomously learn voiceprint information during the next call to retrieve and store the voiceprint information again.

[0082] In some embodiments, a text description of the corresponding function can also be displayed below the "Voiceprint Information" control to help users understand the function of the "Voiceprint Information" control. For example, the text description "Select AI voiceprint noise reduction to automatically extract voiceprint information during a call" can be displayed below the "Voiceprint Information" control.

[0083] As shown in Figure 3B(c), the electronic device can display a voiceprint deletion prompt box 105 in response to clicking the "Delete Voiceprint Information" field. The voiceprint deletion prompt box 105 can cover part of the content of the call noise reduction mode interface 104. The voiceprint deletion prompt box 105 may include a "Cancel" control, a "Delete" control, and voiceprint deletion prompt information. The content of the voiceprint deletion prompt information can be set according to actual needs, and this application example does not limit it. For example, the voiceprint deletion prompt information may include "After deletion, the voiceprint information will need to be extracted again after selecting 'AI Voiceprint Noise Reduction' next time. Do you want to delete it?".

[0084] For example, the electronic device can delete the currently stored voiceprint information in response to clicking the "Delete" control in the voiceprint deletion prompt box 105. After the currently stored voiceprint information is deleted, the "Delete Voiceprint Information" control can be transformed into a "Voiceprint Information" control. Alternatively, the electronic device can not delete the currently stored voiceprint information in response to clicking the "Cancel" control in the voiceprint deletion prompt box 105.

[0085] Optionally, for scenarios where an electronic device only supports storing one voiceprint, if the user of the electronic device changes, the new user needs to actively delete the original user's voiceprint stored on the electronic device to avoid the new user's voice being identified as interfering with human voice and filtered out in voiceprint noise reduction mode. To solve this problem, the electronic device can also be configured to temporarily store the voiceprint information extracted during the call, and automatically delete the temporarily stored voiceprint information after the call ends, so that in scenarios where the user of the electronic device changes, the new user does not need to actively delete the voiceprint information. Specifically, the electronic device can autonomously learn and temporarily store the learned voiceprint information during each call when voiceprint noise reduction mode is enabled, and delete the learned voiceprint information after the call ends, so as to meet the voiceprint noise reduction needs of different users using the electronic device for calls. In this case, as shown in Figure 3B(a), if the "AI Voiceprint Noise Reduction" control is not selected, the "Voiceprint Information" control displays a "Not Recorded" prompt message.

[0086] In some embodiments, the call noise reduction mode interface 104 may also include a control for actively recording voiceprint information (hereinafter referred to as a voiceprint recording control). The electronic device may actively record the user's voiceprint information in response to clicking the voiceprint recording control. For example, the electronic device may display a voiceprint recording interface in response to clicking the voiceprint recording control. The voiceprint recording interface may display a piece of text. The electronic device may extract and store the user's voiceprint information based on the user's voice when reading the text.

[0087] Optionally, the electronic device may store multiple voiceprint information, for example, multiple voiceprint information that is actively recorded, and the voiceprint recording interface may display a voiceprint identifier corresponding to each voiceprint information.

[0088] Optionally, the electronic device can also learn and store the current user's voiceprint information during each call, enabling the storage of multiple voiceprint information entries that are not actively recorded. For example, during a call, if the voiceprint noise reduction mode is in use and the user's voiceprint information does not match the stored voiceprint information, a prompt box can be displayed to remind the user whether to record their voiceprint information.

[0089] In some embodiments, the electronic device may automatically display a mode selection window for selecting a noise reduction mode when a call scenario is detected. The call scenario may include voice call scenarios, video call scenarios, etc. For example, the detection of a call scenario may employ relevant detection algorithms, which will not be described in detail in this embodiment.

[0090] The mode selection window can be a window displayed in a first display area, which includes, but is not limited to, the top center area of ​​the display screen. For example, if an electronic device includes a front-facing camera, the first display area is the punch-hole area containing the front-facing camera.

[0091] Optionally, the electronic device includes a front-facing camera, and the first display area may not overlap with the punch-hole area where the front-facing camera is located. For example, the punch-hole area where the front-facing camera is located may be the top center area of ​​the display, and the first display area may be the top left or top right area of ​​the display.

[0092] In some embodiments, the mode selection window may have an expanded state and a collapsed state. The mode selection window may have a fixed display area, and the mode selection window may also move in response to user swiping operations, that is, the mode selection window may also be displayed in different display areas following user swiping operations.

[0093] As shown in Figure 4A, when the electronic device displays the call interface 106, it can also display the mode selection window 107. The mode selection window 107 is illustrated as being displayed in the top center area of ​​the screen. The mode selection window 107 can display controls corresponding to the currently selected noise reduction mode. The call interface 106 can be a voice call interface or a video call interface; Figure 4A illustrates this as a voice call interface. As shown in Figure 4B, the electronic device can respond to clicking the mode selection window 107 shown in Figure 4A, changing the mode selection window 107 from a collapsed state to an expanded state. In other possible embodiments, the electronic device can also respond to clicking the mode selection window 107 shown in Figure 4A by displaying the mode selection window 107 as shown in Figure 4B through a jump display or pop-up display.

[0094] As shown in Figure 4B, the mode selection window 107 can display a "Turn off noise cancellation" control, an "Ambient sound noise cancellation" control, and an "AI voiceprint noise cancellation" control. The "Turn off noise cancellation" control is used to set the noise cancellation mode of the electronic device to noise cancellation off mode, the "Ambient sound noise cancellation" control is used to set the noise cancellation mode of the electronic device to ambient sound noise cancellation mode, and the "AI voiceprint noise cancellation" control is used to set the noise cancellation mode of the electronic device to voiceprint noise cancellation mode. For example, the electronic device can enter the corresponding noise cancellation mode in response to clicking the "Turn off noise cancellation" control, the "Ambient sound noise cancellation" control, or the "AI voiceprint noise cancellation" control displayed in the mode selection window 107.

[0095] For example, an electronic device can set the noise reduction mode to noise reduction off mode in response to a click on the "Turn off noise reduction" control displayed in the mode selection window 107. As another example, an electronic device can set the noise reduction mode to voiceprint noise reduction mode in response to a click on the "AI voiceprint noise reduction" control displayed in the mode selection window 107.

[0096] Understandably, when an electronic device displays the call interface 106, it may also display the mode selection window 107 as shown in Figure 4A, or when an electronic device displays the call interface 106, it may also display the mode selection window 107 as shown in Figure 4B.

[0097] For the mode selection window 107 shown in Figure 4B, besides designing it to switch between different noise reduction modes by clicking controls, it can also be designed to switch between different noise reduction modes by sliding a slider on a slider bar. For example, the "Turn off noise reduction" control corresponds to the left area of ​​the slider bar, the "Ambient sound noise reduction" control corresponds to the middle area of ​​the slider bar, and the "AI voiceprint noise reduction" control corresponds to the right area of ​​the slider bar. For example, when the slider is in the right area of ​​the slider bar, it indicates that the electronic device is currently in voiceprint noise reduction mode; when the slider slides to the left and is in the middle area of ​​the slider bar, it indicates that the electronic device is currently in ambient sound noise reduction mode; when the slider slides to the left again and is in the left area of ​​the slider bar, it indicates that the electronic device is currently in noise reduction off mode.

[0098] In some embodiments, after the mode selection window 107 is displayed, it may automatically collapse after a preset time, or respond to user operations (e.g., swiping, double-clicking, etc. on the mode selection window 107) and change from an expanded state to a collapsed state. That is, the mode selection window 107 may change from the expanded state shown in FIG4B to the collapsed state shown in FIG4A. The preset time can be set according to actual needs, and this embodiment does not limit it.

[0099] In some embodiments, the electronic device may also activate the voiceprint extraction prompt box 108 in response to clicking the "AI Voiceprint Noise Reduction" control. For example, the display style of the voiceprint extraction prompt box 108 is shown in Figure 4C. The voiceprint extraction prompt box 108 may include a "Cancel" control, an "OK" control, and voiceprint extraction prompt information. The content of the voiceprint extraction prompt information can be set according to actual needs, and this application example does not limit it. For example, the voiceprint extraction prompt information may include two parts: function prompt information and security statement information. For example, the function prompt information may include: "AI Voiceprint Noise Reduction" automatically extracts your voiceprint information during a call, and will highlight your voice after extraction is complete; if you change users, you need to exit this mode or delete the voiceprint information in the settings. The security statement information may include: the voiceprint information is only stored locally, and you can learn more about the AI ​​Voiceprint Noise Reduction instructions.

[0100] In some embodiments, the "Instructions on AI Voiceprint Noise Reduction" in the security statement can be in the form of a hyperlink. The electronic device can respond to a user clicking on this link to display an interface showing the statement content regarding the extraction of the user's voiceprint information in voiceprint noise reduction mode. That is, the interface displayed after the user clicks on the "Instructions on AI Voiceprint Noise Reduction" link is the same as the interface displayed after the user clicks on the "Instructions on AI Voiceprint Noise Reduction" control.

[0101] For example, if the electronic device does not store voiceprint information and displays the call interface 106, the electronic device responds to the operation of clicking the "AI voiceprint noise reduction" control shown in Figure 4B or sliding the slider to the area corresponding to the "AI voiceprint noise reduction" control, and opens the voiceprint extraction prompt box 108.

[0102] For example, if the electronic device supports storing multiple voiceprint information, when the call interface 106 is displayed, the electronic device responds to the operation of clicking the "AI voiceprint noise reduction" control shown in Figure 4B or sliding the slider to the area corresponding to the "AI voiceprint noise reduction" control, and detects that the user's voiceprint information is not stored in the electronic device, and opens the voiceprint extraction prompt box 108.

[0103] For example, the electronic device can respond to clicking the "OK" control in the voiceprint extraction prompt box 108, allowing the electronic device to extract voiceprint information. Alternatively, the electronic device can respond to clicking the "Cancel" control in the voiceprint extraction prompt box 108, disallowing the electronic device to extract voiceprint information, and the electronic device will not enter the voiceprint noise reduction mode.

[0104] In some embodiments, when extracting voiceprint information, a pop-up window can be displayed to indicate that voiceprint extraction has started and that it has been completed.

[0105] In some embodiments, the selection of the noise reduction mode control displayed on the call noise reduction mode interface 104 is linked to the selection of the noise reduction mode control displayed on the mode selection window 107. For example, as shown in Figure 4D(a), if a user selects the "ambient sound noise reduction" control on the call noise reduction mode interface 104 and initiates a call with another user, the mode selection window 107 will show that the "ambient sound noise reduction" control is selected, that is, the electronic device is currently in ambient sound noise reduction mode.

[0106] For example, as shown in Figure 4D(b), if the user selects the "AI Voiceprint Noise Reduction" control in the mode selection window 107 to switch the ambient sound noise reduction mode to the voiceprint noise reduction mode, after the call ends, if the electronic device responds to the user's operation and displays the call noise reduction mode interface 104, the call noise reduction mode interface 104 can show that the "AI Voiceprint Noise Reduction" control is selected.

[0107] In some embodiments, as shown in FIG4E, a mode selection window 107 may also be displayed in the notification bar during a call. That is, during a call, the user can also select the noise reduction mode through the mode selection window 107 displayed in the notification bar.

[0108] To better understand the implementation details of the above-mentioned call method on electronic devices, the following section, in conjunction with Figures 5 and 7 to 9, describes the process by which various software and hardware components in the electronic device work together to implement the above-mentioned call method.

[0109] Specifically as follows:

[0110] Operating systems for electronic devices can adopt layered architectures, event-driven architectures, microkernel architectures, microservice architectures, or cloud architectures. This application uses the layered architecture of the Android system as an example to illustrate the software structure of an electronic device. As shown in Figure 5, the layered architecture divides the software into several layers, each with a clear role and division of labor. Layers communicate with each other through software interfaces. Taking the Android system as an example, in some embodiments, the Android system is divided into four layers, from top to bottom: the application layer (Apk), the application framework layer (Framework), the hardware abstraction layer (HAL), and the kernel layer (Kernel).

[0111] The application layer can include a series of application packages. For example, an application package may include applications such as calling applications, gallery applications, interface applications, and system applications. Calling applications may include applications that support voice calls and video calls. System applications may include settings applications. Interface applications are applications related to the user interface, such as mode selection windows.

[0112] The application framework layer provides application programming interfaces (APIs) and programming frameworks for applications in the application layer. For example, the application framework layer may include a parameter setting module (SetParam), an audio service module (AudioService), an audio processing module (AudioFlinger), an audio recording module (AudioRecord), and a scene recognition module. The parameter setting module can be used to send parameter information of the noise reduction mode set in the application or mode selection window to the hardware abstraction layer. The audio service module is responsible for managing the audio resources of the application and system, such as managing system audio routing, audio format conversion, volume control, connecting and disconnecting audio devices, and notifying applications and services of audio events starting / stopping. The audio processing module is responsible for managing input and output stream devices and processing and transmitting audio streams. The audio recording module is used to record audio signals.

[0113] The scene recognition module is used to identify whether the electronic device is in a call scenario. When it is determined that the electronic device is in a call scenario, the scene recognition module can control the active display of the mode selection window, automatically popping up a mode selection window for setting the noise reduction mode during a call. For example, the scene recognition module can identify whether the electronic device is in a call scenario based on information transmitted by the AudioService (e.g., audio routing information, audio event information, etc.).

[0114] The hardware abstraction layer includes a mode control module and a voiceprint noise reduction processing module. The mode control module receives parameter information from the parameter setting module to set the noise reduction mode, and controls the hardware layer to select / switch audio links based on this parameter information. Different audio links can be used to implement different functions. For example, as shown in Figure 5, audio link ① is the link for noise reduction off mode, audio link ② is the link for ambient sound noise reduction mode, audio link ③ is the link for voiceprint self-learning, and audio link ④ is the link for voiceprint noise reduction mode.

[0115] The voiceprint noise reduction module can be used for autonomous learning of voiceprint information and for voiceprint noise reduction (suppressing environmental noise and interfering human voices).

[0116] In some embodiments, the voiceprint noise reduction processing module may include a voiceprint autonomous learning unit, an AI noise reduction unit, and a voiceprint noise reduction module. The voiceprint autonomous learning unit can be used to extract the registrant's voiceprint information and store it in a secure area (Trust Zone). To improve the accuracy of learning the registrant's voiceprint information, the voiceprint autonomous learning unit can learn the voiceprint information based on the registrant's continuous speech for 20-40 seconds. The secure area can be a storage area on a secure chip, which can run a secure operating system (secure OS) independent of the Android system. The secure area can also be used to store facial information, fingerprint information, etc.

[0117] AI noise reduction units can be used to suppress environmental noise. For example, an AI noise reduction unit is deployed with an AI noise reduction model trained on a neural network. The AI ​​noise reduction model can learn various types of environmental noise in advance.

[0118] Voiceprint noise reduction units can be used to suppress environmental noise and interfering human voices. For example, a voiceprint noise reduction unit is deployed with a voiceprint noise reduction model trained on a neural network. The voiceprint noise reduction model can read the voiceprint information of the registrant from the safe area and regard other sounds besides the sound corresponding to the voiceprint information of the registrant as noise (interfering human voice, environmental noise), thereby suppressing environmental noise and interfering human voices.

[0119] The kernel layer may include audio drivers, display drivers, etc. It may also include hardware-dependent programs such as interrupt handlers and device drivers, as well as basic, common, and frequently running modules such as clock management modules and process scheduling modules, and critical data structures. The kernel layer can be located within the processor or embedded in internal memory.

[0120] The hardware layer may include a display screen, audio module, microphone, etc. The audio module may include a digital signal processor (DSP) or an audio digital signal processor (ADSP).

[0121] In some embodiments, the audio module can be divided into multiple units. For example, the audio module shown in Figure 5 includes a link control unit, an acoustic echo cancel (AEC) unit, an AI noise reduction unit, an automatic noise suppression (ANS) unit, and an automatic gain control (AGC) unit.

[0122] The AEC unit can be used for echo cancellation, such as eliminating echoes during a call. Echoes can be reflected echoes, sounds played from a speaker, etc.

[0123] The link control unit can be used to select / switch audio links based on control information issued by the mode control module.

[0124] Both AI noise cancellation units and ANS units can suppress environmental noise. ANS units are generally used to suppress steady-state noise, which refers to noise whose acoustic characteristics, such as sound intensity and frequency distribution, do not change or change slowly over time, such as background noise from electronic devices, fan noise from heat sinks, and ambient hum. AI noise cancellation units can suppress both steady-state and non-steady-state noise. Non-steady-state noise refers to noise whose acoustic characteristics, such as sound intensity and frequency distribution, change over time, such as the sound of doors opening and closing, keyboard typing, doorbell rings, and musical instrument sounds. In other words, ANS units can only suppress a portion of environmental noise, while AI noise cancellation units can suppress a wide variety of environmental noise.

[0125] The AGC unit can be used to automatically adjust the gain of the internal amplifier circuit according to the intensity of the sound signal. For example, if the sound signal intensity is high, the AGC unit can automatically reduce the gain, and if the sound signal intensity is low, the AGC unit can automatically increase the gain to ensure that the volume is maintained at a relatively stable level.

[0126] In some embodiments, users can set the noise reduction mode through a settings application or mode selection window at the application layer. The settings application or mode selection window can send user operation information to a parameter setting module. The parameter setting module can generate parameter information for setting the noise reduction mode based on the user operation information, and this parameter information can be sent to the mode control module. The mode control module can then control the link control unit to select / switch the audio link based on the parameter information sent by the parameter setting module.

[0127] If the parameter information used to set the noise reduction mode is the same as the parameter information for setting the voiceprint noise reduction mode, the mode control module can also wake up the voiceprint noise reduction processing module to perform autonomous learning of voiceprint information or suppress environmental noise and interference with human voices.

[0128] In some embodiments, users can delete voiceprint information stored in a secure area through an application-level settings application. For example, in response to a user's deletion operation, the settings application can send a deletion command to the secure area, and the secure area can delete the stored voiceprint information in response to the deletion command. For instance, if an electronic device only supports noise reduction for a single voiceprint, for electronic devices that have registered voiceprint information, if other users wish to use the voiceprint noise reduction function, they can delete the voiceprint information stored in the secure area through the settings application. After deleting the voiceprint information, it can be automatically extracted and stored in the next call scenario.

[0129] In some embodiments, if the electronic device only supports storing a single voiceprint for noise reduction, for electronic devices that have registered voiceprint information, when the electronic device is in voiceprint noise reduction mode, environmental noise and interfering voices can be suppressed during the call, highlighting the registered user's voice. If the electronic device is used by a different user, during the call (in voiceprint noise reduction mode), if the new user does not switch the noise reduction mode in time or delete the voiceprint information stored in the safe area (for example, deleting the voiceprint information stored in the safe area can trigger the re-extraction and storage of the new user's voiceprint information in this call), the new user's voice will be suppressed. The electronic device can also display a non-registered voiceprint prompt box when it detects that the sound signal collected by the microphone at a preset time after the start of the call does not contain the registered user's voiceprint information but contains the voiceprint information of a non-registered user. The non-registered voiceprint prompt box can be used to prompt the user to switch the noise reduction mode or register the voiceprint information.

[0130] For example, as shown in Figure 6, the prompt message included in the unregistered voiceprint prompt box 109 is: "An unregistered voice has been detected. It is recommended to exit 'AI voiceprint noise reduction' to prompt the user to switch noise reduction modes or register voiceprint information." It is understood that the prompt message included in the unregistered voiceprint prompt box 109 can be set according to actual needs, and this embodiment does not limit this.

[0131] For example, the preset duration for the start of a call can refer to the preset duration starting from the time the call interface is displayed, or it can refer to the preset duration starting from the time the call is connected.

[0132] It is understandable that if an electronic device supports storing multiple voiceprint information for noise reduction, if the electronic device is used by a different person, during a call (in voiceprint noise reduction mode), the voiceprint information of the new user can be directly extracted and stored in a safe area to avoid the new user's voice being suppressed. Alternatively, before extracting the voiceprint information of the new user, a voiceprint extraction prompt box 108 as shown in Figure 4C can be displayed so that the new user can confirm whether to allow the extraction and storage of voiceprint information.

[0133] Optionally, if the secure area stores multiple voiceprint information, each voiceprint information may correspond to a voiceprint identifier. The settings application interface (e.g., the call noise reduction mode interface or voiceprint registration interface mentioned above) may display multiple voiceprint identifiers. The settings application may respond to the user's operation of deleting the voiceprint information of a specified voiceprint identifier by sending a deletion command for the voiceprint information of that voiceprint identifier to the secure area, thereby allowing the secure area to delete the voiceprint information of the specified voiceprint identifier.

[0134] The following provides a detailed explanation of audio link ①, audio link ②, audio link ③, and audio link ④.

[0135] For example, in an online music lesson scenario, User A is the student using a first electronic device, while User B is the teacher using a second electronic device. During the call, User B needs to hear not only User A's voice but also the sound of the instrument. In this case, User A can select the noise reduction mode of the first electronic device to be off by setting the application or mode selection window. The off noise reduction mode corresponds to audio link ①, which preserves the sound of the instrument, allowing User A's voice and the instrument sound to be transmitted to the second electronic device, so that User B can hear User A's voice and the instrument sound.

[0136] Specifically, on the first electronic device side, a microphone collects sound signals. The sound signals collected by the microphone may include user A's voice and surrounding environmental sounds (musical instruments and sounds from other people or objects, etc.). The sound signals collected by the microphone undergo echo cancellation by the AEC unit. The sound signals processed by the AEC unit are further denoised by the ANS unit to remove steady-state noise contained in the sound signals. For example, surrounding environmental sounds include musical instruments and noise from the air conditioner. The ANS unit can remove the noise from the air conditioner, retaining user A's voice and musical instrument sounds. The sound signals processed by the ANS unit are further amplified by the AGC unit through adaptive gain control. The sound signals processed by the AGC unit are further transmitted to AudioFlinger via an audio driver. AudioFlinger can be used to perform mixing, resampling, and sound effect settings on the sound signals. The audio signal processed by AudioFlinger is further recorded by AudioRecord. The recorded audio signal can be reported to the calling application. For example, AudioRecord can report the recorded audio signal to the calling application through the MediaProject interface. The audio signal reported to the calling application can then be converted into electromagnetic waves by the antenna of the first electronic device and radiated out to the second electronic device, so that user B can hear user A's voice and musical instrument sounds through the speaker of the second electronic device.

[0137] For example, in a multi-person conference call scenario, User A and User B use a first electronic device, while User C uses a second electronic device. During the call, User C focuses on the voices of User A and User B, but not on the ambient sounds around User A and User B. In this case, User A or User B can select the noise reduction mode of the first electronic device as ambient sound noise reduction mode through the settings application or mode selection window. Ambient sound noise reduction mode corresponds to audio link ②, which preserves the voices of User A and User B and suppresses ambient noise.

[0138] Specifically, on the first electronic device side, a microphone collects sound signals. The sound signals collected by the microphone may include the voices of user A and user B, as well as ambient sounds (sounds from other people or objects, etc.). The sound signals collected by the microphone undergo echo cancellation by an AEC unit. The sound signals processed by the AEC unit are further denoised by an AI noise reduction unit to remove ambient noise (which cannot be removed from interfering human voices). For example, ambient sounds include the noise from the air conditioner, the voice of user D, and the sound of user D typing on the keyboard. The AI ​​noise reduction unit can remove the noise from the air conditioner and the sound of user D typing on the keyboard, while retaining the voices of user A, user B, and user D (user D's voice can be considered as interfering human voices). The sound signals processed by the AI ​​noise reduction unit are further amplified by an AGC unit using adaptive gain control. The sound signals processed by the AGC unit are then transmitted to AudioFlinger via an audio driver. AudioFlinger can be used to perform mixing, resampling, and sound effect settings on the sound signals. The audio signal processed by AudioFlinger is further recorded by AudioRecord. The recorded audio signal can be reported to the calling application. The audio signal reported to the calling application can then be converted into electromagnetic waves by the antenna of the first electronic device and radiated out to the second electronic device, so that user B can hear the voices of user A, user B and user D through the speaker of the second electronic device.

[0139] For example, in a one-on-one conference call scenario, User A uses a first electronic device, and User B uses a second electronic device. During the call, User B focuses on User A's voice and ignores ambient noise. In this case, User A can select the voiceprint noise reduction mode for the first electronic device through the settings application or mode selection window. If the first electronic device does not store User A's voiceprint information, it needs to learn from User A's voiceprint information before performing voiceprint noise reduction. That is, it needs to execute audio link ③ first, then audio link ④, to preserve User A's voice and suppress ambient noise and interfering voices. In other words, during a call, audio link ③ is executed first in the early stages to complete the self-learning of voiceprint information, and audio link ④ is executed from the completion of voiceprint self-learning until the end of the call. If the first electronic device stores User A's voiceprint information, it can directly execute audio link ④ to preserve User A's voice and suppress ambient noise and interfering voices.

[0140] Specifically, assuming the first electronic device does not store user A's voiceprint information, a microphone on the first electronic device side collects sound signals. The sound signals collected by the microphone may include user A's speaking voice and surrounding environmental sounds (sounds from other people or objects, etc.). The sound signals collected by the microphone undergo echo cancellation by the AEC unit. The sound signals processed by the AEC unit are further subjected to adaptive gain amplification by the AGC unit. The sound signals processed by the AGC unit are further transmitted to the voiceprint autonomous learning unit via audio drive. The voiceprint autonomous learning unit extracts voiceprint information from the sound signals, that is, the voiceprint autonomous learning unit can automatically extract user A's voiceprint information based on user A's speaking voice during a call. To ensure call quality during the voiceprint autonomous learning stage, the sound signals after the voiceprint autonomous learning unit are further denoised by the AI ​​noise reduction unit to remove environmental noise (which cannot be removed from interfering human voices), so that user B can also clearly hear user A's speaking voice during the voiceprint autonomous learning stage. For example, ambient sounds include noise from the air conditioner, user C's voice, and the sound of user C typing on the keyboard. The AI ​​noise reduction unit can remove the air conditioner noise and user C's keyboard sounds, retaining the voices of user A and user C (user C's voice can be considered as interfering with human voices). The audio signal processed by the AI ​​noise reduction unit is further transmitted to AudioFlinger, which can be used for mixing, resampling, and sound effect settings. The audio signal processed by AudioFlinger is then recorded by AudioRecord. The recorded audio signal can be reported to the calling application. The audio signal reported to the calling application can then be converted into electromagnetic waves by the antenna of the first electronic device and radiated outwards to the second electronic device. That is, during the voiceprint autonomous learning stage, user B hears the voices of user A and user C through the speaker of the second electronic device.

[0141] After the voiceprint autonomous learning unit completes the extraction of user A's voiceprint information, the voiceprint autonomous learning unit can store user A's voiceprint information in a secure area, and the audio link is switched from audio link ③ to audio link ④.

[0142] On the first electronic device side, a microphone collects sound signals. The sound signals collected by the microphone may include user A's voice and surrounding environmental sounds (sounds from other people or objects, etc.). The sound signals collected by the microphone undergo echo cancellation by an AEC unit. The sound signals processed by the AEC unit are further subjected to adaptive gain amplification by an AGC unit. The sound signals processed by the AGC unit are further transmitted to a voiceprint noise reduction unit via an audio driver. The voiceprint noise reduction unit performs noise reduction processing on the sound signals, removing environmental noise and interfering human voices contained in the sound signals. For example, the voiceprint noise reduction unit can read user A's voiceprint information from a safe area, and perform voiceprint matching processing on the sound signals processed by the AGC unit based on user A's voiceprint information. Matching sound signals are filtered out and sent to AudioFlinger, while non-matching sound signals are filtered out. For example, surrounding environmental sounds include noise from the air conditioner, user C's voice, and the sound of user C typing on the keyboard. The voiceprint noise reduction unit can remove the noise from the air conditioner, the sound of user C typing on the keyboard, and user C's voice, while retaining user A's voice. The audio signal processed by the voiceprint noise reduction unit is further transmitted to AudioFlinger, which can be used for mixing, resampling, and setting sound effects. The audio signal processed by AudioFlinger is then recorded by AudioRecord. The recorded audio signal can be reported to the calling application. The audio signal reported to the calling application can then be converted into electromagnetic waves by the antenna of the first electronic device and radiated outwards to the second electronic device. That is, after the voiceprint self-learning stage, user B will only hear user A's voice through the speaker of the second electronic device.

[0143] In some embodiments, during the voiceprint autonomous learning phase, since the volume of a registrant's (e.g., user A mentioned above) speech is generally louder and longer than that of other interfering voices, the voiceprint autonomous learning unit can extract voiceprint information that is relatively loud and long-lasting in the presence of interfering voices, thereby reducing the possibility that the extracted voiceprint information is from a non-registrant.

[0144] In some embodiments, for electronic devices that support smart assistants, the electronic device generally stores the user's voiceprint information used to wake up the smart assistant, for example, the user's voiceprint information extracted based on repeated readings of fixed phrases (such as "Hello YOYO"). This voiceprint information can also be stored in a secure area as voiceprint information used in the voiceprint noise reduction mode, i.e., without needing to extract the user's voiceprint information through audio link ③. Since the voiceprint information used to wake up the smart assistant is extracted in recording mode, while audio link ③ extracts voiceprint information from the sound signal processed by the AEC unit and AGC unit, there are certain differences between the user's voiceprint information extracted by the two. Furthermore, since the voiceprint noise reduction unit of audio link ④ also performs noise reduction processing on the sound signal processed by the AEC unit and AGC unit, using the voiceprint information extracted by audio link ③ will result in a better noise reduction effect for the voiceprint noise reduction unit of audio link ④ compared to using the voiceprint information used to wake up the smart assistant.

[0145] It is understood that the above software structure is merely exemplary and does not constitute a limitation on the software structure of electronic devices. In other embodiments, electronic devices may have more or fewer structures, and this application does not impose any limitations on this.

[0146] To more intuitively understand the process by which the various software modules work together to achieve different noise reduction modes in electronic devices, the following uses the interaction diagrams shown in Figures 7-9 as an example to illustrate the sound signal processing process of electronic devices under different noise reduction modes.

[0147] Figure 7 shows the interaction flow of each software and hardware module in the noise reduction off mode.

[0148] 701: The call application responds to the user's actions by displaying the call interface and the mode selection window.

[0149] In some embodiments, a calling application may refer to an application capable of voice or video calls. The calling application may display a call interface in response to user actions on its interface.

[0150] As shown in Figure 4A, when the call application displays the call interface, it can also display the mode selection window. Alternatively, the scene recognition module in the application framework layer can display the mode selection window.

[0151] After the mode selection window is displayed, users can set the noise reduction mode of the electronic device during a call through the mode selection window.

[0152] 702: Microphone collects sound signals.

[0153] 703: The microphone sends the sound signal to the AEC unit.

[0154] In some embodiments, the sound signals captured by the microphone may include the voice of the user speaking and ambient sounds (sounds made by other people or objects, etc.).

[0155] 704: The AEC unit performs echo cancellation on the sound signal captured by the microphone.

[0156] In some embodiments, the AEC unit may employ relevant echo cancellation algorithms to cancel the echo of the sound signal acquired by the microphone.

[0157] 705: In noise cancellation off mode, the AEC unit sends the echo-cancelled audio signal to the ANS unit.

[0158] For example, the electronic device can set the noise reduction mode to noise reduction off mode in response to the user's operation on the call noise reduction mode interface shown in Figure 3A, or the operation on the mode selection window 107 shown in Figure 4B.

[0159] 706: The ANS unit performs noise reduction processing on the audio signal.

[0160] In some embodiments, the ANS unit performs noise reduction processing on the audio signal, which can remove steady-state environmental noise contained in the audio signal.

[0161] 707: The ANS unit sends the noise-reduced audio signal to the AGC unit.

[0162] 708: The AGC unit performs adaptive gain amplification of the audio signal.

[0163] In some embodiments, the AGC unit performs adaptive gain amplification on the sound signal, using different gains to amplify sound signals of different intensities, so that the intensity of the sound signal after processing by the AGC unit remains at a relatively stable level.

[0164] 709: The AGC unit sends the amplified sound signal to the audio driver.

[0165] 710: The audio driver sends the amplified sound signal to AudioFligner.

[0166] In some embodiments, the audio driver may simply forward the received audio signal without performing any additional processing on the audio signal.

[0167] 711: AudioFligner performs audio processing on sound signals.

[0168] In some embodiments, audio processing may include one or more of the following: mixing, resampling, sound effects settings, etc.

[0169] 712: AudioFligner sends the processed audio signal to AudioRecord.

[0170] 713: AudioRecord records audio signals.

[0171] 714: AudioRecord sends the recorded audio signal to the calling application.

[0172] Figure 8 shows the interaction flow of each software and hardware module in the ambient sound noise reduction mode.

[0173] 801: The call application responds to the user's actions by displaying the call interface and the mode selection window.

[0174] The interaction flow 801 of this application embodiment is similar to the interaction flow 701 of the previous embodiment. To avoid repetition, it will not be described again here.

[0175] 802: Microphone collects sound signals.

[0176] 803: The microphone sends the sound signal to the AEC unit.

[0177] The interaction flow 803 of this application embodiment is similar to the interaction flow 703 of the previous embodiment. To avoid repetition, it will not be described again here.

[0178] 804: The AEC unit performs echo cancellation on the sound signal captured by the microphone.

[0179] The interaction flow 804 of this embodiment is similar to the interaction flow 704 of the previous embodiment. To avoid repetition, it will not be described again here.

[0180] 805: In ambient noise reduction mode, the AEC unit sends the echo-cancelled sound signal to the AI ​​noise reduction unit.

[0181] For example, the electronic device can set the noise reduction mode of the electronic device to ambient sound noise reduction mode in response to the user's operation on the call noise reduction mode interface shown in Figure 3A, or the operation on the mode selection window 107 shown in Figure 4B.

[0182] 806: The AI ​​noise reduction unit performs noise reduction processing on the audio signal.

[0183] In some embodiments, the AI ​​noise reduction unit performs noise reduction processing on the sound signal, which can remove both steady-state and non-steady-state environmental noise contained in the sound signal.

[0184] 807: The AI ​​noise reduction unit sends the noise-reduced audio signal to the AGC unit.

[0185] 808: The AGC unit performs adaptive gain amplification of the audio signal.

[0186] The interaction flow 808 of this embodiment is similar to the interaction flow 708 of the previous embodiment. To avoid repetition, it will not be described again here.

[0187] 809: The AGC unit sends the amplified sound signal to the audio driver.

[0188] 810: The audio driver sends the amplified sound signal to AudioFligner.

[0189] 811: AudioFligner performs audio processing on sound signals.

[0190] The interaction flow 811 of this embodiment is similar to the interaction flow 711 of the previous embodiment. To avoid repetition, it will not be described again here.

[0191] 812: AudioFligner sends the processed audio signal to AudioRecord.

[0192] 813: AudioRecord records audio signals.

[0193] 814: AudioRecord sends the recorded audio signal to the calling application.

[0194] Figure 9 shows the interaction flow of each software and hardware module in the voiceprint noise reduction mode. Figure 9 is illustrated using the example that the user's voiceprint information is not stored in the safe area of ​​the electronic device.

[0195] 901: The call application responds to the user's actions by displaying the call interface and the mode selection window.

[0196] The interaction flow 901 of this application embodiment is similar to the interaction flow 701 of the aforementioned embodiment. To avoid repetition, it will not be described again here.

[0197] 902: Microphone collects sound signals.

[0198] 903: The microphone sends the sound signal to the AEC unit.

[0199] The interaction flow 903 of this application embodiment is similar to the interaction flow 703 of the aforementioned embodiment. To avoid repetition, it will not be described again here.

[0200] 904: The AEC unit performs echo cancellation on the sound signal captured by the microphone.

[0201] The interaction flow 904 of this application embodiment is similar to the interaction flow 704 of the previous embodiment. To avoid repetition, it will not be described again here.

[0202] 905: In voiceprint noise reduction mode, the AEC unit sends the echo-cancelled audio signal to the AGC unit.

[0203] For example, the electronic device can set the noise reduction mode of the electronic device to voiceprint noise reduction mode in response to the user's operation on the call noise reduction mode interface shown in Figure 3A, or the operation on the mode selection window 107 shown in Figure 4B.

[0204] 906: The AGC unit performs adaptive gain amplification processing on the audio signal.

[0205] 907: The AGC unit sends the amplified sound signal to the audio driver.

[0206] 908: The audio driver sends the amplified sound signal to the voiceprint autonomous learning unit.

[0207] 909: The voiceprint autonomous learning unit extracts the user's voiceprint information from the sound signal.

[0208] In some embodiments, the voiceprint autonomous learning unit can employ relevant voiceprint extraction algorithms to extract the user's voiceprint information from the audio signal. If the audio signal includes the voices of multiple speakers (the user's voice and interfering voices), the user's speaking volume is generally louder and longer than the volume of other interfering voices. The voiceprint autonomous learning unit can use the voiceprint information with relatively loud volume and relatively long duration as the user's voiceprint information.

[0209] 910: The voiceprint autonomous learning unit sends the amplified sound signal to the AI ​​noise reduction unit.

[0210] The interaction flow 910 and interaction flow 909 in this embodiment can be executed in parallel.

[0211] 911: The AI ​​noise reduction unit performs noise reduction processing on the audio signal.

[0212] In some embodiments, the voiceprint autonomous learning unit generally needs to extract the user's voiceprint information based on a sound signal of a preset duration. For example, the sound signal of the preset duration contains the user's voice for 40 seconds. To ensure the call quality during the voiceprint autonomous learning stage, the sound signal after the voiceprint autonomous learning unit is further denoised by an AI noise reduction unit to remove steady-state and non-steady-state environmental noise contained in the sound signal.

[0213] 912: The AI ​​noise reduction unit sends the noise-reduced audio signal to AudioFligner.

[0214] 913: AudioFligner performs audio processing on sound signals.

[0215] The interaction flow 913 of this application embodiment is similar to the interaction flow 711 of the aforementioned embodiment. To avoid repetition, it will not be described again here.

[0216] 914: AudioFligner sends the processed audio signal to AudioRecord.

[0217] 915: AudioRecord records audio signals.

[0218] 916: AudioRecord sends the recorded audio signal to the calling application.

[0219] 917: The voiceprint self-learning unit stores the user's voiceprint information in a secure area.

[0220] It is understandable that if the secure area of ​​the electronic device stores the user's voiceprint information, interaction processes 908 to 917 can be omitted.

[0221] 918: The audio driver sends the amplified sound signal to the voiceprint noise reduction unit.

[0222] In some embodiments, after the voiceprint autonomous learning unit stores the user's voiceprint information in a secure area, the voiceprint autonomous learning unit can send a notification message to the audio driver. Based on the notification message, the audio driver can switch the sound signal from being sent to the voiceprint autonomous learning unit to being sent to the voiceprint noise reduction unit.

[0223] Alternatively, other software modules can instruct the audio driver to switch the sound signal from being sent to the voiceprint self-learning unit to being sent to the voiceprint noise reduction unit.

[0224] 919: The voiceprint noise reduction unit reads the user's voiceprint information from the secure area and performs noise reduction processing on the sound signal based on the user's voiceprint information.

[0225] In some embodiments, the voiceprint noise reduction unit can perform voiceprint matching processing on the sound signal based on the user's voiceprint information. The matched sound signals are filtered out and sent to AudioFlinger, while the unmatched sound signals are filtered out.

[0226] 920: The audio signal is processed by the AudioFligner noise reduction unit.

[0227] 921: AudioFligner performs audio processing on sound signals.

[0228] The interaction flow 921 of this embodiment is similar to the interaction flow 711 of the previous embodiment. To avoid repetition, it will not be described again here.

[0229] 922: AudioFligner sends the processed audio signal to AudioRecord.

[0230] 923: AudioRecord records audio signals.

[0231] 924: AudioRecord sends the recorded audio signal to the calling application.

[0232] Referring to Figure 10, the first electronic device 100 involved in the embodiments of this application will be described below. The first electronic device 100 in the embodiments of this application can be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), large screen, smart TV, netbook, as well as cellular phone, personal digital assistant (PDA), augmented reality (AR) / virtual reality (VR) device, etc., including a microphone and display screen. The specific form of this electronic device is not particularly limited in the embodiments of this application. Please refer to Figure 10, which is a schematic diagram of the structure of the first electronic device 100 provided in the embodiments of this application. It can be understood that the second electronic device 200 may have the same or different structure as the first electronic device 100.

[0233] The first electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0234] Microphone 170C is used to acquire sound signals. Audio module 170 is used to perform echo cancellation on the acquired sound signal, noise reduction on the echo-cancelled sound information, and adaptive gain amplification on the noise-reduced sound signal. For example, audio module 170 may include an AEC unit, an ANS unit, an AI noise reduction unit, and an AGC unit. The AEC unit is used to perform echo cancellation on the acquired sound signal, the ANS unit and the AI ​​noise reduction unit are used to perform noise reduction on the echo-cancelled sound information, and the AGC unit is used to perform adaptive gain amplification on the noise-reduced sound signal.

[0235] In some embodiments, the call scenario may include a handheld call mode, a headset call mode, and a hands-free call mode. The speaker 170A can be used to play the other party's voice in hands-free call mode. The receiver 170B can be used to play the other party's voice in handheld call mode. The headset jack 170D is used to connect a headset, enabling the playback of the other party's voice through the connected headset in headset call mode.

[0236] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the first electronic device 100. In other embodiments of this application, the first electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0237] In addition, an operating system runs on top of the aforementioned components. Examples include Apple's iOS operating system, Google's Android open-source operating system, and Microsoft's Windows operating system.

[0238] Processor 110 may include one or more processing units, such as application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0239] For example, the processor 110 can be used to autonomously learn voiceprint information, store the learned voiceprint information in a secure area, and retrieve the voiceprint information stored in the secure area for noise reduction processing to suppress environmental noise and interference with human voices. The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0240] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory can store instructions or data that the processor 110 has just used or that are being used repeatedly. If the processor 110 needs to use the instructions or data again, it can retrieve them directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves system efficiency.

[0241] In some embodiments, the processor 110 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0242] The wireless communication function of the first electronic device 100 can be implemented through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor, and baseband processor.

[0243] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the first electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with a tuning switch.

[0244] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the first electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0245] The wireless communication module 160 can provide solutions for wireless communication applications on the first electronic device 100, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0246] In some embodiments, antenna 1 of the first electronic device 100 is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, enabling the first electronic device 100 to communicate with networks and other devices via wireless communication technology. The wireless communication technology may include Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time-Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technologies, etc. The GNSS may include the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), the BeiDou Navigation Satellite System (BDS), the Quasi-Zenith Satellite System (QZSS), and / or satellite-based augmentation systems (SBAS).

[0247] The first electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0248] The display screen 194 is used to display images, videos, etc. The display screen 194 can also be used to display a call interface, mode selection window, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a minimized display, a microLED, a micro-OLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the first electronic device 100 may include one or N display screens 194, where N is a positive integer greater than 1. In this embodiment, the display screen 194 can be a touch screen, that is, the display screen 194 integrates a touch sensor 180K.

[0249] Internal memory 121 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM). The RAM may include static random-access memory (SRAM), dynamic random-access memory (DRAM), synchronous dynamic random-access memory (SDRAM), double data rate synchronous dynamic random-access memory (DDR SDRAM, such as fifth-generation DDR SDRAM, generally referred to as DDR5 SDRAM), etc.; the NVM may include disk storage devices and flash memory.

[0250] Flash memory can be classified according to its operating principle, including NOR FLASH, NAND FLASH, 3D NAND FLASH, etc.; according to the level of storage cell potential, including single-level cell (SLC), multi-level cell (MLC), triple-level cell (TLC), quad-level cell (QLC), etc.; and according to storage specifications, including universal flash storage (UFS) and embedded multimedia card (eMMC), etc.

[0251] The random access memory can be directly read and written by the processor 110. It can be used to store executable programs (such as machine instructions) of the operating system or other running programs, as well as user and application data.

[0252] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 110.

[0253] The external memory interface 120 can be used to connect to external non-volatile memory, thereby expanding the storage capacity of the first electronic device 100. The external non-volatile memory communicates with the processor 110 through the external memory interface 120 to perform data storage functions.

[0254] The call methods described in the above embodiments can all be implemented in the first electronic device 100 having the above hardware structure.

[0255] This embodiment also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on the first electronic device 100, the first electronic device 100 performs the aforementioned related method steps to implement the call method in the above embodiment.

[0256] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement the call method in the above embodiment.

[0257] This embodiment also provides a chip system coupled to a memory. The chip system is used to read and execute computer programs stored in the memory to implement the call method in the above embodiment.

[0258] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0259] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0260] The unit described as a separate component may or may not be physically separate. The component shown as a unit can be one physical unit or multiple physical units, that is, it can be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0261] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0262] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0263] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A communication method applied to an electronic device, characterized in that, The method includes: In response to the user's first operation, a call interface and a first window are displayed. The first window includes a first control and a second control. The first control is used to indicate a first noise reduction mode, and the second control is used to indicate a second noise reduction mode. The first control is in a first state, and the second control is in a second state. In response to a second operation by the user on the second control, the second control is set to the first state, the first control is set to the second state, and the electronic device is set to the second noise reduction mode.

2. The call method as described in claim 1, characterized in that, The first window includes a first state and a second state. When the first window is in the first state, the first window displays the first control and the second control. When the first window is in the second state, the first window displays the control that is in the first state.

3. The call method as described in claim 1 or 2, characterized in that, The response to a second user operation on the second control, wherein the second control is set to the first state, the first control is set to the second state, and the electronic device is set to the second noise reduction mode, includes: In response to a second operation by the user on the second control, the second control is switched from the second state to the first state, the first control is switched from the first state to the second state, and the electronic device is switched from the first noise reduction mode to the second noise reduction mode.

4. The call method as described in any one of claims 1 to 3, characterized in that, The first state is the selected state, and the second state is the unselected state.

5. The call method as described in any one of claims 1 to 4, characterized in that, The electronic device is equipped with a preset application, which includes an interface for displaying a call noise reduction mode for the first control and the second control.

6. The call method as described in claim 5, characterized in that, The call noise reduction mode interface also includes a third control, which indicates whether the electronic device stores voiceprint information. When the electronic device stores voiceprint information, the third control is in a third state. When the electronic device does not store voiceprint information, the third control is in a fourth state, which is different from the fourth state.

7. The call method as described in claim 6, characterized in that, The method further includes: When the electronic device stores voiceprint information, in response to a third operation by the user on the third control, the voiceprint information stored in the electronic device is deleted.

8. The call method as described in claim 5, characterized in that, The call noise reduction mode interface also includes a fourth control, which is used to indicate the recording of voiceprint information. The method further includes: In response to the user's fourth operation on the fourth control, the system collects the user's spoken audio, extracts voiceprint information from the audio, and stores the extracted voiceprint information.

9. The call method as described in claim 5, characterized in that, The call noise reduction mode interface also includes a fifth control, which is used to display the declaration content of extracting voiceprint information. The method further includes: In response to the user's fifth operation on the fifth control, an interface displaying the declaration content of the extracted voiceprint information is shown.

10. The call method as described in claim 9, characterized in that, The second control being set to the first state in response to a second user operation on the second control includes: In response to a second user action on the second control, a second window is displayed, the second window including a sixth control; In response to the user's sixth operation on the sixth control, the second control is set to the first state.

11. The call method as described in claim 10, characterized in that, The second window also includes hyperlink text corresponding to the fifth control, and the method further includes: In response to the user's seventh action on the hyperlink text, an interface displaying the declaration content of the extracted voiceprint information is shown.

12. The call method as described in claim 10, characterized in that, The method further includes: In the second noise reduction mode, the user's speaking audio is collected, voiceprint information is extracted from the audio, and the extracted voiceprint information is stored.

13. The call method as described in claim 12, characterized in that, The method further includes: If the extracted voiceprint information is inconsistent with the voiceprint information stored in the electronic device, a third window is displayed, which includes information suggesting that the user switch to a noise reduction mode.

14. The call method as described in any one of claims 1 to 13, characterized in that, The electronic device includes a display screen and a camera. The display screen has a punch-hole area corresponding to the camera. The first window is displayed in a first area of ​​the display screen, and the first area includes the punch-hole area.

15. The call method as described in any one of claims 1 to 13, characterized in that, The electronic device includes a display screen and a camera. The display screen has a punch-hole area corresponding to the camera. The first window is displayed in a first area of ​​the display screen, which does not include the punch-hole area.

16. The call method as described in any one of claims 1 to 15, characterized in that, The first operation includes answering a phone call or making a phone call.

17. The call method as described in any one of claims 1 to 16, characterized in that, The call interface includes a cellular network-based call interface or an Internet Protocol Voice over IP (VoIP)-based call interface.

18. The call method as described in any one of claims 1 to 17, characterized in that, The first window partially overlaps with the call interface.

19. The call method as described in any one of claims 1 to 17, characterized in that, The method further includes: In response to the user's eighth action, a notification bar is displayed, the notification bar including the first window.

20. The call method as described in any one of claims 1 to 9, characterized in that, The electronic device includes a microphone. The first noise reduction mode corresponds to a first audio signal processing link, and the second noise reduction mode corresponds to a second audio signal processing link. When the first control is in the first state, the electronic device uses the first audio signal processing link to process the audio signal collected by the microphone. When the second control is in the first state, the electronic device switches from using the first audio signal processing link to using the second audio signal processing link to process the audio signal collected by the microphone.

21. The call method as described in claim 20, characterized in that, Both the first audio signal processing link and the second audio signal processing link include any of the following links, and the first audio signal processing link and the second audio signal processing link are different: The sound signals collected by the microphone are sequentially processed by echo cancellation, automatic noise suppression (ANS) and adaptive gain amplification. The sound signals collected by the microphone are sequentially processed by echo cancellation, AI noise reduction, and adaptive gain amplification. The sound signals collected by the microphone are sequentially processed by echo cancellation, adaptive gain amplification, and voiceprint noise reduction.

22. The call method as described in claim 21, characterized in that, Before sequentially performing echo cancellation, adaptive gain amplification, and voiceprint noise reduction on the sound signal acquired by the microphone, the method further includes: The sound signal collected by the microphone is sequentially processed by echo cancellation, adaptive gain amplification, and AI noise reduction, and preset voiceprint information is extracted from the sound signal after adaptive gain amplification. Store the preset voiceprint information in a secure area.

23. The call method as described in claim 22, characterized in that, The process of sequentially performing echo cancellation, adaptive gain amplification, and voiceprint noise reduction on the sound signal acquired by the microphone includes: After storing the preset voiceprint information in the secure area, the sound signal collected by the microphone is sequentially processed by echo cancellation, adaptive gain amplification, and voiceprint noise reduction, with the voiceprint noise reduction being performed based on the preset voiceprint information.

24. An electronic device, characterized in that, The electronic device includes a microphone, a display screen, a memory, and a processor; The microphone, the display screen, and the memory are all coupled to the processor; The memory is used to store program instructions; The processor is configured to read the program instructions stored in the memory to implement the call method as described in any one of claims 1 to 23.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the call method as described in any one of claims 1 to 23.

26. A computer program product comprising computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, the call method as described in any one of claims 1 to 23 is implemented.

27. A chip system, characterized in that, The chip system is coupled to a memory, and the chip system is used to read and execute a computer program stored in the memory to implement the call method as described in any one of claims 1 to 23.

Images