Voice data processing method, device, electronic device and storage medium
By judging that the user wears a facial mask and performs voice data processing, target voice data with higher clarity is generated, which solves the problem of communication quality decline caused by wearing a facial mask and improves the user experience.
Patent Information
- Application Number
- CN202110907786.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-09
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2041-08-09
AI Technical Summary
When wearing facial masks, the user's communication quality decreases, and the prior art is difficult to effectively improve the clarity of voice data.
By obtaining user call data, it is determined whether the user is wearing a facial mask, and processing it using voice feature parameters or facial image data, improving the clarity of voice data, generating target voice data, and sending it to the second electronic device.
Even if the user wears a facial mask, the second electronic device can receive target voice data with high clarity, effectively improving communication quality and user experience.
Smart Images

Figure CN113674737B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of voice data processing, and specifically relates to a voice data processing method, device, electronic device and storage medium. Background Art
[0002] In daily life and work, users often wear masks or other facial coverings to cover their mouths and noses. In this case, when users talk with other users through electronic devices, the communication quality of the users will be affected. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a voice data processing method, device, electronic device and storage medium to solve the problem of poor communication quality of users.
[0004] In order to solve the above technical problems, this application is implemented as follows:
[0005] In a first aspect, an embodiment of the present application provides a method for processing voice data, the method comprising:
[0006] Acquire call data of a user of the first electronic device when making a call; the call data includes voice data;
[0007] In a case where it is determined according to the call data that the user of the first electronic device is wearing a face covering, the voice data is processed to obtain target voice data; the clarity of the target voice data is greater than the clarity of the voice data;
[0008] The target voice data is sent to a second electronic device.
[0009] In a second aspect, an embodiment of the present application provides a device for processing voice data, the device comprising:
[0010] An acquisition module, configured to acquire call data of a user of the first electronic device when making a call; the call data includes voice data;
[0011] A processing module, configured to process the voice data to obtain target voice data when it is determined according to the call data that the user of the first electronic device wears a face covering; the clarity of the target voice data is greater than the clarity of the voice data;
[0012] The sending module is used to send the target voice data to the second electronic device.
[0013] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.
[0014] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.
[0015] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method described in the first aspect.
[0016] In the embodiment of the present application, by processing the voice data to obtain target voice data with higher clarity when determining that the user of the first electronic device is wearing a facial covering according to the call data of the user of the first electronic device during the call, the target voice data with higher clarity is sent to the second electronic device that is talking to the first electronic device. In this way, even if the user of the first electronic device is wearing a facial covering, the second electronic device can still receive the processed target voice data with higher clarity, thereby effectively improving the communication quality and user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 It is a flowchart of a voice data processing method provided by an embodiment of the present application;
[0018] Figure 2 is a schematic diagram of a user of a first electronic device wearing a facial covering in an embodiment of the present application;
[0019] Figure 3 is another schematic diagram of a user of the first electronic device wearing a facial covering in an embodiment of the present application;
[0020] Figure 4 This is a flow chart of a scenario implementation of the voice data processing method provided in an embodiment of the present application;
[0021] Figure 5 is a structural diagram of a voice data processing device provided by another embodiment of the present application;
[0022] Figure 6 It is a structural diagram of an electronic device provided by yet another embodiment of the present application. DETAILED DESCRIPTION
[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0024] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.
[0025] The following is a detailed description of the voice data processing method provided in the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.
[0026] Figure 1 FIG. 1 is a flow chart of a method for processing voice data provided by an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a method for processing voice data, which may include:
[0027] Step S101, acquiring call data of a user of a first electronic device when making a call; the call data includes voice data.
[0028] Among them, the call data may include voice data and facial image data of the user of the first electronic device. The call data may be call data obtained by the user of the first electronic device when making a voice call or a video call, or may be call data obtained by the user of the first electronic device when sending a voice message.
[0029] Step S102, when it is determined according to the call data that the user of the first electronic device wears a face covering, the voice data is processed to obtain target voice data; the clarity of the target voice data is greater than the clarity of the voice data.
[0030] Among them, the facial covering can be a mask, a mask, a headgear, etc. that will cover the mouth and nose of the user of the first electronic device. In order to facilitate understanding of the solution of the embodiment of the present application, the facial covering is mainly described as a mask below.
[0031] After acquiring the call data of the user of the first electronic device during the call, it can be determined whether the user of the first electronic device is wearing a face covering according to the call data. When it is determined that the user of the first electronic device is wearing a face covering, the voice data of the user of the first electronic device can be processed using an existing sound algorithm to improve the clarity of the voice data, thereby obtaining target voice data with higher clarity.
[0032] Step S103: sending the target voice data to the second electronic device.
[0033] After obtaining the target voice data, the target voice data can be sent to the second electronic device. Compared with voice data, the target voice data has higher clarity. Therefore, the second electronic device can more easily hear the voice of the user of the first electronic device during the call, thereby improving the communication quality.
[0034] In the embodiment of the present application, by processing the voice data to obtain target voice data with higher clarity when determining that the user of the first electronic device is wearing a facial covering according to the call data of the user of the first electronic device during the call, the target voice data with higher clarity is sent to the second electronic device that is talking to the first electronic device. In this way, even if the user of the first electronic device is wearing a facial covering, the second electronic device can still receive the processed target voice data with higher clarity, thereby effectively improving the communication quality and user experience.
[0035] In order to more accurately determine whether the user of the first electronic device is wearing a facial covering, in some embodiments, the call data also includes facial image data of the user of the first electronic device:
[0036] After the above step S101 and before step S102, the voice data processing method may further perform the following steps:
[0037] Based on the voice data and / or the facial image data of the user of the first electronic device, it is determined whether the user of the first electronic device is wearing a facial covering.
[0038] The voice data of the user of the first electronic device may be the voice of the user of the first electronic device collected by the first electronic device when the user of the first electronic device is on a call, or may be the voice collected by the first electronic device when the user of the first electronic device sends a voice message. The facial image data of the user of the first electronic device may be the facial image of the user of the first electronic device captured by the first electronic device. The facial image data may be the facial image obtained when the user of the first electronic device makes a video call. The facial image data may also be based on the settings of the user of the first electronic device, when the user of the first electronic device makes a voice call or sends a voice message, the facial image of the user of the first electronic device is obtained through the camera of the first electronic device, for example, when the user of the first electronic device uses the loudspeaker mode and puts the electronic device in front of the call, the camera can obtain the front facial image of the user of the first electronic device, and when the user of the first electronic device puts the electronic device to the ear for a call, the camera can obtain the side facial image of the user of the first electronic device.
[0039] Determining whether the user of the first electronic device wears a facial covering according to the voice data of the user of the first electronic device may be determining whether the user of the first electronic device wears a facial covering according to voice feature parameters of the voice data of the user of the first electronic device. The voice feature parameters may include clarity, brightness, etc.
[0040] It is understandable that when a user wears a mask, his or her pronunciation may be affected by the mask. Therefore, the sound of a user wearing a mask will be lower and unclear than when the user does not wear a mask. In other words, the clarity and brightness of voice data when wearing a mask are lower than when not wearing a mask. Based on this, a clarity and / or brightness threshold can be preset based on empirical values in combination with actual conditions. When the clarity and / or brightness of the voice data of the user of the first electronic device is less than the threshold, it can be considered that the user of the first electronic device is wearing a mask. Otherwise, it can be considered that the user of the first electronic device is not wearing a mask.
[0041] As a specific example, in order to determine whether the user of the first electronic device wears a facial mask based on the voice feature parameters of the voice data, the existing voice recognition algorithm can be used to extract the voice feature parameters of the acquired voice data. Specifically, the acquired voice data can be segmented into sound signals, and then the voice feature parameters can be extracted using methods such as Linear Prediction Cepstrum (LPCC) or Mel Frequency Cepstrum Coefficient (MFCC), and then it can be determined whether the user of the first electronic device wears a facial mask based on the extracted voice feature parameters.
[0042] In order to prevent the uncertainty of the voice data from affecting the judgment result, this embodiment can also determine whether the user of the first electronic device wears a facial covering according to the facial image data of the user of the first electronic device.
[0043] In a specific example, when determining whether the user of the first electronic device wears a facial covering based on call data, the priority of facial image data may be higher than the priority of voice data. In other words, when the acquired call data includes voice data and facial image data of the user of the first electronic device, it is determined whether the user of the first electronic device wears a facial covering based on the facial image data of the user of the first electronic device.
[0044] In another specific example, considering the situation that the first electronic device may not be able to obtain facial image data, for example, when the user of the first electronic device puts the electronic device in a pocket and uses headphones to make a voice call, it can be determined whether the user of the first electronic device is wearing a facial covering based on the voice data of the user of the first electronic device.
[0045] In another specific example, in order to more accurately determine whether the user is wearing a facial covering, when the call data includes the voice data and facial image data of the user of the first electronic device, it can be determined whether the user of the first electronic device is wearing a facial covering based on the voice data and the facial image data of the user of the first electronic device. That is, when it is determined that the user of the first electronic device is wearing a facial covering based on the voice data, and it is also determined that the user of the first electronic device is wearing a facial covering based on the facial image data, it can be determined that the user of the first electronic device is wearing a facial covering; when it is determined that the user of the first electronic device is not wearing a facial covering based on either the voice data or the facial image data, it can be determined that the user of the first electronic device is not wearing a facial covering.
[0046] In these embodiments, it is possible to determine whether the user of the first electronic device is wearing a facial covering based on voice data and / or facial image data obtained during a call with the user of the first electronic device. In this way, the problem of inaccurate judgment results based on voice data due to high uncertainty in the voice data can be avoided, and the situation where the electronic device cannot determine whether the user of the first electronic device is wearing a facial covering due to failure to obtain facial image data can be avoided. Therefore, determining whether the user of the first electronic device is wearing a facial covering based on voice data and / or facial image data is more flexible, has a wider applicability, and the obtained judgment result is more accurate.
[0047] In order to avoid distortion of the target voice data, thereby further improving the communication quality and user experience, in some embodiments, the specific implementation of step S102 may include the following steps:
[0048] Inputting the voice data into a preset model; the preset model is trained based on historical call data of a user of the first electronic device, where the historical call data includes historical voice data of the user of the first electronic device when not wearing a face covering and when wearing a face covering;
[0049] The voice data is processed using the preset model to obtain the target voice data.
[0050] The preset model may be trained based on historical call data of the user of the first electronic device. For example, historical voice data when the user is not wearing a face cover and historical voice data when the user is wearing a face cover in the historical call data of the first electronic device may be used as training samples for training, and voice feature parameters of the historical voice data in the training samples may be identified to obtain the preset model.
[0051] When the user of the first electronic device wears a facial cover during a call, which affects the clarity of the voice data, the voice data can be input into a preset model, and the preset model is used to process the voice data, thereby obtaining the voice data corresponding to when the user of the first electronic device does not wear a facial cover. It can be understood that the clarity of the processed voice data is higher than that of the unprocessed voice data, and the processed voice data can be used as the target voice data.
[0052] In these embodiments, considering that the existing sound algorithm is used to process the voice data of the user of the first electronic device, although the clarity can be improved, the processed voice data may be greatly different from the voice of the user of the first electronic device itself, that is, the target voice data may be distorted. Therefore, the voice data can be processed using a preset model trained based on the historical call data of the user of the first electronic device to obtain the target voice data corresponding to the user of the first electronic device when not wearing a facial covering, thereby ensuring the authenticity of the target voice data and further improving the communication quality and user experience.
[0053] In some examples, in order to more accurately determine whether a user is wearing a facial covering, taking into account the voice characteristics of different users, it is also possible to determine whether the user is wearing a facial covering based on the voice data of the user of the first electronic device and a preset model. For example, the voice data can be compared with the historical voice data when the facial covering is not worn and the historical voice data when the facial covering is worn in the historical call data. When the similarity with the historical voice data when the facial covering is not worn is greater than the similarity with the historical voice data when the facial covering is worn, it can be considered that the user of the first electronic device is not wearing a facial covering. Conversely, when the similarity with the historical voice data when the facial covering is not worn is less than the similarity with the historical voice data when the facial covering is worn, it can be considered that the user of the first electronic device is wearing a facial covering.
[0054] In order to more intuitively and accurately determine whether the user is wearing a facial covering, in a specific example, the historical call data may also include historical facial image data of the user of the first electronic device when not wearing a facial covering and when wearing a facial covering. The situation of the user of the first electronic device wearing a facial covering can be first determined based on the historical facial image data. When the user of the first electronic device wears a facial covering, the voice data of the user of the first electronic device at this time is obtained, and the historical voice data of the user of the first electronic device when wearing a facial covering is stored; when the user of the first electronic device does not wear a facial covering, the voice data of the user of the first electronic device at this time is obtained, and the historical voice data of the user of the first electronic device when not wearing a facial covering is stored. Then, the historical voice data of the user of the first electronic device when wearing a facial covering and the historical voice data of the user of the first electronic device when not wearing a facial covering are used as training samples to train a preset model.
[0055] In this way, the accuracy of the training samples can be guaranteed, and in subsequent calls, when determining whether the user of the first electronic device is wearing a facial covering based on the preset model, the judgment result can be more accurate. Therefore, it can be ensured that when the user of the first electronic device wears a facial covering, the voice data can be processed more timely and accurately, thereby improving the communication quality and user experience.
[0056] In order to improve the flexibility of voice data processing, in some embodiments, when it is determined according to the call data that the user of the first electronic device is wearing a face covering, the voice data processing method may further perform the following steps:
[0057] Output prompt information; the prompt information is used to prompt the clarity of the user voice data of the first electronic device is affected by the facial obstruction.
[0058] When it is detected that the user of the first electronic device is wearing a facial covering, a prompt message may be output to prompt the user of the first electronic device that the clarity of voice data is affected by the facial covering, and the user of the first electronic device may decide whether to remove the facial covering.
[0059] In some embodiments, there may be two situations when the user of the first electronic device wears a facial covering. Figure 2 As shown, the user of the first electronic device wears a mask, and the mask has a smooth curve around the mouth. In this case, it means that the user of the first electronic device wears the mask correctly, and the communication quality is less affected. Figure 3 As shown, the user of the first electronic device wears a mask, and the mask has a depression at the mouth. In this case, it means that the user of the first electronic device wears the mask incorrectly, which has a greater impact on the communication quality and the clarity of the voice data is lower.
[0060] The historical call data may also include voice data when the face covering is not worn, voice data when the face covering is worn correctly, and voice data when the face covering is worn incorrectly. These voice data are used as training samples to train a preset model.
[0061] In subsequent calls, the situation of the user of the first electronic device wearing a facial covering can be obtained based on the call data, and different steps can be performed according to different situations. For example, when it is determined that the user of the first electronic device is not wearing a mask, the acquired voice data can be sent directly to the second electronic device without processing; when it is determined that the user of the first electronic device wears the mask correctly, a prompt message can be output, or no prompt can be given, and the voice data can be directly processed to obtain target voice data with higher clarity, and then the target voice data can be sent to the second electronic device; when it is determined that the user of the first electronic device wears the mask incorrectly, a prompt message can be output to remind the user of the first electronic device to wear the mask correctly or take off the mask. After the user of the first electronic device wears the mask correctly, the voice data can be processed to obtain target voice data with higher clarity, and then the target voice data can be sent to the second electronic device.
[0062] In these embodiments, when the communication quality is affected by the user of the first electronic device wearing a facial covering, in addition to processing the voice data to improve the clarity, a prompt message can also be output to remind the user that the clarity of the current voice data is affected by the facial covering, resulting in lower communication quality. In this way, the user of the first electronic device can choose whether to remove the facial covering to eliminate the impact, or to eliminate the impact by processing the voice data, thereby making the voice data processing more flexible.
[0063] In order to further improve the flexibility of voice data processing, in some embodiments, the output prompt message may include:
[0064] Acquiring geographic location information of the first electronic device;
[0065] If the geographical location information does not belong to the target geographical location, output a prompt message; or,
[0066] When the geographic location information belongs to the target geographic location, prompt information is output, and the prompt information is also used to prompt the user of the first electronic device to keep wearing the face covering.
[0067] The target geographical location may be a public place with a large flow of people, such as a large shopping mall.
[0068] The geographic location information of the first electronic device can be obtained in combination with existing positioning algorithms such as GPS. When the geographic location information does not belong to the target geographic location and the user of the first electronic device wears a facial covering, a prompt message can be output to prompt the user of the first electronic device that the clarity of the voice data is affected by the facial covering. At this time, the user of the first electronic device can decide whether to remove the facial covering.
[0069] In some examples, when the geographic location information belongs to the target geographic location, no prompt may be output, that is, when the geographic location information belongs to a public place, the user of the first electronic device may not be prompted that the clarity of the voice data is affected by the facial obstruction. At this time, the voice data can be directly processed to obtain target voice data with higher clarity and then sent to the second electronic device.
[0070] In other examples, when the geographic location information belongs to the target geographic location and the user of the first electronic device wears a facial covering, a prompt message may be output, and the prompt message may be used to prompt the user of the first electronic device to keep wearing the facial covering in addition to prompting the user of the first electronic device that the clarity of voice data is affected by the facial covering. That is, when the geographic location information belongs to a public place, the user of the first electronic device may be prompted to keep wearing the facial covering.
[0071] In this embodiment, the geographic location information of the first electronic device can be combined to determine whether the geographic location information belongs to the target geographic location. When the geographic location information does not belong to the target geographic location, the user of the first electronic device is prompted that the clarity of the current voice data is affected by the facial obstruction. Alternatively, when the geographic location information belongs to the target geographic location, the user of the first electronic device is prompted to keep wearing the facial obstruction. In this way, the output prompt information can be applied to more scenarios according to actual needs, thereby expanding the scope of application of voice data processing and increasing the flexibility of voice data processing.
[0072] In some examples, when the user of the first electronic device is not wearing a facial covering and the geographic location information belongs to the target geographic location, prompt information may be output, and the prompt information may be used to prompt the user of the first electronic device to wear a facial covering. For example, when the user of the first electronic device is on a call, the geographic location information of the first electronic device is obtained, and when it is determined based on the call data that the user of the first electronic device is not wearing a facial covering and the geographic location information belongs to the target geographic location, the user of the first electronic device is prompted to wear a facial covering.
[0073] In order to facilitate understanding of the voice data processing method provided by the above embodiment, the above voice data processing method is described below using a specific scenario embodiment. Figure 4 A flow chart of a scenario implementation of the above-mentioned voice data processing method is shown.
[0074] like Figure 4 As shown, the application scenario of this scenario embodiment may be that when a first electronic device is talking to a second electronic device, the user of the first electronic device wears a facial cover, which affects the clarity of voice data and leads to poor communication quality. The scenario embodiment may specifically include the following steps:
[0075] Step S401, determining whether the user of the first electronic device wears a facial covering based on facial image data. The facial image data may be collected by a camera of the first electronic device when the user of the first electronic device is on a call. The facial image data may include a facial image of the user of the first electronic device wearing a facial covering and a facial image of the user of the first electronic device not wearing a facial covering.
[0076] Step S402: Acquire historical voice data of a user of the first electronic device when the user is wearing a face cover and when the user is not wearing a face cover.
[0077] Step S403: Use historical voice data of the user of the first electronic device when wearing a face cover and when not wearing a face cover as training samples to obtain a preset model through training.
[0078] Step S404: Acquire call data of a user of the first electronic device during a call. The call data may include voice data of the user of the first electronic device.
[0079] Step S405, determining whether the user of the first electronic device wears a facial covering according to the call data, specifically, determining whether the user of the first electronic device wears a facial covering according to the voice data and a preset model. The call data may also include facial image data of the user of the first electronic device, and in this case, determining whether the user of the first electronic device wears a facial covering may also be performed according to the facial image data. If yes, perform step S406; if no, perform step S408.
[0080] Step S406: Process the voice data to obtain target voice data.
[0081] Step S407: sending the target voice data to the second electronic device.
[0082] Step S408: sending the voice data to the second electronic device.
[0083] This scenario embodiment determines whether the user of the first electronic device wears a facial cover according to the call data of the user of the first electronic device during the call, and processes the voice data when the user of the first electronic device wears the facial cover to obtain target voice data with higher clarity, and sends the target voice data with higher clarity to the second electronic device. In this way, even if the user of the first electronic device wears a facial cover, the second electronic device can still receive the processed target voice data with higher clarity, thereby effectively improving the communication quality and user experience.
[0084] It should be noted that the voice data processing method provided in the embodiment of the present application can be executed by a voice data processing device, or by a control module in the voice data processing device for executing the loaded voice data processing method. In the embodiment of the present application, the voice data processing method provided in the embodiment of the present application is described by taking the voice data processing device executing the loaded voice data processing method as an example.
[0085] Figure 5 is a structural diagram of a voice data processing device provided by another embodiment of the present application, such as Figure 5 As shown, the speech data processing device 500 may include:
[0086] The acquisition module 501 is used to acquire the call data of the user of the first electronic device when the user is talking on the phone; the call data includes voice data;
[0087] The processing module 502 is used to process the voice data to obtain target voice data when it is determined according to the call data that the user of the first electronic device wears a face covering; the clarity of the target voice data is greater than the clarity of the voice data;
[0088] The sending module 503 is used to send the target voice data to the second electronic device.
[0089] In the embodiment of the present application, by processing the voice data to obtain target voice data with higher clarity when determining that the user of the first electronic device is wearing a facial covering according to the call data of the user of the first electronic device during the call, the target voice data with higher clarity is sent to the second electronic device that is talking to the first electronic device. In this way, even if the user of the first electronic device is wearing a facial covering, the second electronic device can still receive the processed target voice data with higher clarity, thereby effectively improving the communication quality and user experience.
[0090] In some embodiments, the call data may also include facial image data of the user of the first electronic device:
[0091] The speech data processing device 500 may further include:
[0092] The determination module is used to determine whether the user of the first electronic device wears a facial covering according to the voice data and / or the facial image data of the user of the first electronic device.
[0093] In these embodiments, whether the user of the first electronic device is wearing a facial covering can be determined based on the voice data and / or facial image data obtained when the user of the first electronic device is on a call. In this way, the problem of inaccurate judgment results based on voice data due to high uncertainty in voice data can be avoided, and the situation where the electronic device cannot determine that the user of the first electronic device is wearing a facial covering due to the inability to obtain facial image data can be avoided. Therefore, determining whether the user of the first electronic device is wearing a facial covering based on voice data and / or facial image data is more flexible, has a wider applicability, and the judgment result obtained is more accurate.
[0094] In some embodiments, the processing module 502 may include:
[0095] A first input unit, configured to input voice data into a preset model; the preset model is trained based on historical call data of a user of the first electronic device, the historical call data including historical voice data of the user of the first electronic device when not wearing a face covering and when wearing a face covering;
[0096] The processing unit is used to process the voice data using a preset model to obtain target voice data.
[0097] In these embodiments, considering that the existing sound algorithm is used to process the voice data of the user of the first electronic device, although the clarity can be improved, the processed voice data may be greatly different from the voice of the user of the first electronic device itself, that is, the target voice data may be distorted. Therefore, the voice data can be processed using a preset model trained based on the historical call data of the user of the first electronic device to obtain the target voice data corresponding to the user of the first electronic device when not wearing a facial covering, thereby ensuring the authenticity of the target voice data and further improving the communication quality and user experience.
[0098] In some embodiments, the voice data processing apparatus may further include:
[0099] The output module is used to output prompt information; the prompt information is used to prompt the user of the first electronic device that the clarity of call data is affected by the facial obstruction.
[0100] In these embodiments, when the communication quality is affected by the user of the first electronic device wearing a facial covering, in addition to processing the voice data to improve the clarity, a prompt message can also be output to remind the user that the clarity of the current voice data is affected by the facial covering, resulting in lower communication quality. In this way, the user of the first electronic device can choose whether to remove the facial covering to eliminate the impact, or to eliminate the impact by processing the voice data, thereby making the voice data processing more flexible.
[0101] In some embodiments, the output module may include:
[0102] An acquiring unit, configured to acquire geographic location information of the first electronic device;
[0103] an output unit, configured to output prompt information when the geographical location information does not belong to the target geographical location; or
[0104] When the geographic location information belongs to the target geographic location, prompt information is output, and the prompt information is also used to prompt the user of the first electronic device to keep wearing the face covering.
[0105] In this embodiment, the geographic location information of the first electronic device can be combined to determine whether the geographic location information belongs to the target geographic location. When the geographic location information does not belong to the target geographic location, the user of the first electronic device is prompted that the clarity of the current voice data is affected by the facial obstruction. Alternatively, when the geographic location information belongs to the target geographic location, the user of the first electronic device is prompted to keep wearing the facial obstruction. In this way, the output prompt information can be applied to more scenarios according to actual needs, thereby expanding the scope of application of voice data processing and increasing the flexibility of voice data processing.
[0106] The voice data processing device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.
[0107] The voice data processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.
[0108] The speech data processing device provided in the embodiment of the present application can achieve Figures 1 to 4 To avoid repetition, the various processes implemented by the voice data processing device in the method embodiment are not described here.
[0109] Optionally, an embodiment of the present application also provides an electronic device, including a processor 610, a memory 609, and a program or instruction stored in the memory 609 and executable on the processor 610. When the program or instruction is executed by the processor 610, each process of the above-mentioned voice data processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0110] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.
[0111] Figure 6 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.
[0112] The electronic device 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, and a processor 610.
[0113] Those skilled in the art will appreciate that the electronic device 600 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 610 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 6 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.
[0114] The processor 610 is configured to:
[0115] Acquire call data of a user of the first electronic device when making a call; the call data includes voice data;
[0116] When it is determined according to the call data that the user of the first electronic device is wearing a face covering, the voice data is processed to obtain target voice data; the clarity of the target voice data is greater than the clarity of the voice data;
[0117] The target voice data is sent to the second electronic device.
[0118] In the embodiment of the present application, by processing the voice data to obtain target voice data with higher clarity when determining that the user of the first electronic device is wearing a facial covering according to the call data of the user of the first electronic device during the call, the target voice data with higher clarity is sent to the second electronic device that is talking to the first electronic device. In this way, even if the user of the first electronic device is wearing a facial covering, the second electronic device can still receive the processed target voice data with higher clarity, thereby effectively improving the communication quality and user experience.
[0119] In some embodiments, the call data may also include facial image data of the user of the first electronic device:
[0120] The processor 610 may also be used to:
[0121] Based on the voice data and / or the facial image data of the user of the first electronic device, it is determined whether the user of the first electronic device is wearing a facial covering.
[0122] In these embodiments, it is possible to determine whether the user of the first electronic device is wearing a facial covering based on voice data and / or facial image data obtained during a call with the user of the first electronic device. In this way, the problem of inaccurate judgment results based on voice data due to high uncertainty in the voice data can be avoided, and the situation where the electronic device cannot determine whether the user of the first electronic device is wearing a facial covering due to failure to obtain facial image data can be avoided. Therefore, determining whether the user of the first electronic device is wearing a facial covering based on voice data and / or facial image data is more flexible, has a wider applicability, and the obtained judgment result is more accurate.
[0123] In some embodiments, the processor 610 may also be configured to:
[0124] Inputting the voice data into a preset model; the preset model is trained based on historical call data of a user of the first electronic device, where the historical call data includes historical voice data of the user of the first electronic device when not wearing a face covering and when wearing a face covering;
[0125] The voice data is processed using the preset model to obtain the target voice data.
[0126] In these embodiments, considering that the existing sound algorithm is used to process the voice data of the user of the first electronic device, although the clarity can be improved, the processed voice data may be greatly different from the voice of the user of the first electronic device itself, that is, the target voice data may be distorted. Therefore, the voice data can be processed using a preset model trained based on the historical call data of the user of the first electronic device to obtain the target voice data corresponding to the user of the first electronic device when not wearing a facial covering, thereby ensuring the authenticity of the target voice data and further improving the communication quality and user experience.
[0127] In some embodiments, the processor 610 may also be configured to:
[0128] Output prompt information; the prompt information is used to prompt the user of the first electronic device that the clarity of call data is affected by the facial obstruction.
[0129] In these embodiments, when the communication quality is affected by the user of the first electronic device wearing a facial covering, in addition to processing the voice data to improve the clarity, a prompt message can also be output to remind the user that the clarity of the current voice data is affected by the facial covering, resulting in lower communication quality. In this way, the user of the first electronic device can choose whether to remove the facial covering to eliminate the impact, or to eliminate the impact by processing the voice data, thereby making the voice data processing more flexible.
[0130] In some embodiments, the processor 610 may also be configured to:
[0131] Acquiring geographic location information of the first electronic device;
[0132] If the geographical location information does not belong to the target geographical location, output a prompt message; or,
[0133] When the geographic location information belongs to the target geographic location, prompt information is output, and the prompt information is also used to prompt the user of the first electronic device to keep wearing the face covering.
[0134] In this embodiment, the geographic location information of the first electronic device can be combined to determine whether the geographic location information belongs to the target geographic location. When the geographic location information does not belong to the target geographic location, the user of the first electronic device is prompted that the clarity of the current voice data is affected by the facial obstruction. Alternatively, when the geographic location information belongs to the target geographic location, the user of the first electronic device is prompted to keep wearing the facial obstruction. In this way, the output prompt information can be applied to more scenarios according to actual needs, thereby expanding the scope of application of voice data processing and increasing the flexibility of voice data processing.
[0135] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned voice data processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0136] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0137] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned voice data processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0138] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0139] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0140] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0141] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. A method for processing speech data, characterized in that: The method comprises: Acquire call data of a user of the first electronic device when making a call; the call data includes voice data; determining, based on the voice data, whether a user of the first electronic device is wearing a facial covering; In a case where it is determined according to the call data that the user of the first electronic device is wearing a face covering, the voice data is processed to obtain target voice data; the clarity of the target voice data is greater than the clarity of the voice data; sending the target voice data to a second electronic device; The determining, according to the voice data, whether the user of the first electronic device wears a facial covering comprises: When the clarity and / or brightness of the voice data is less than a preset threshold, it is determined that the user of the first electronic device wears a facial covering, and when the clarity and / or brightness of the voice data is not less than the preset threshold, it is determined that the user of the first electronic device does not wear a facial covering; Alternatively, the voice data is segmented into sound signals, and voice feature parameters are extracted from the segmented voice data using a linear prediction cepstrum technique or a Mel-frequency cepstrum coefficient, and whether the user of the first electronic device wears a facial covering is determined based on the voice feature parameters.
2. The method according to claim 1, characterized in that The call data also includes facial image data of the user of the first electronic device: After acquiring the call data of the user of the first electronic device during the call, and before determining, based on the call data, that the user of the first electronic device is wearing a face covering, processing the voice data to obtain the target voice data, the method further includes: Determine whether the user of the first electronic device wears a facial covering based on the voice data of the user of the first electronic device and / or the facial image data.
3. The method according to claim 1, characterized in that: The processing of the voice data to obtain target voice data includes: Inputting the voice data into a preset model; the preset model is trained based on historical call data of a user of the first electronic device, the historical call data including historical voice data of the user of the first electronic device when not wearing a face covering and when wearing a face covering; The preset model is used to process the speech data to obtain target speech data.
4. The method according to any one of claims 1 to 3, characterized in that: In the case where it is determined according to the call data that the user of the first electronic device is wearing a facial covering, the method further includes: Output prompt information; the prompt information is used to prompt the user of the first electronic device that the clarity of the voice data is affected by the facial obstruction.
5. The method according to claim 4, characterized in that The output prompt information includes: Acquiring geographic location information of the first electronic device; If the geographical location information does not belong to the target geographical location, outputting prompt information; or, In the case where the geographic location information belongs to the target geographic location, prompt information is output, and the prompt information is also used to prompt the user of the first electronic device to keep wearing the facial covering.
6. A speech data processing device, characterized in that: The device comprises: An acquisition module, configured to acquire call data of a user of the first electronic device when making a call; the call data includes voice data; a determination module, configured to determine whether a user of the first electronic device is wearing a facial covering according to the voice data; A processing module, configured to process the voice data to obtain target voice data when it is determined according to the call data that the user of the first electronic device wears a face covering; the clarity of the target voice data is greater than the clarity of the voice data; A sending module, used for sending the target voice data to a second electronic device; The determination module is specifically used for: When the clarity and / or brightness of the voice data is less than a preset threshold, it is determined that the user of the first electronic device wears a facial covering, and when the clarity and / or brightness of the voice data is not less than the preset threshold, it is determined that the user of the first electronic device does not wear a facial covering; Alternatively, the voice data is segmented into sound signals, and voice feature parameters are extracted from the segmented voice data using a linear prediction cepstrum technique or a Mel-frequency cepstrum coefficient, and whether the user of the first electronic device wears a facial covering is determined based on the voice feature parameters.
7. The device according to claim 6, characterized in that The call data also includes facial image data of the user of the first electronic device: The device also includes: The determination module is used to determine whether the user of the first electronic device wears a facial covering according to the voice data of the user of the first electronic device and / or the facial image data.
8. The device according to claim 6, characterized in that The processing module comprises: An input unit, configured to input the voice data into a preset model; the preset model is trained based on historical call data of a user of the first electronic device, the historical call data comprising historical voice data of the user of the first electronic device when not wearing a face covering and when wearing a face covering; The processing unit is used to process the voice data using the preset model to obtain target voice data.
9. The device according to any one of claims 6 to 8, characterized in that: The device also includes: The output module is used to output prompt information; the prompt information is used to prompt the user of the first electronic device that the clarity of the call data is affected by the facial obstruction.
10. The device according to claim 9, characterized in that The output module comprises: an acquiring unit, configured to acquire geographic location information of the first electronic device; an output unit, configured to output prompt information if the geographical location information does not belong to the target geographical location; or In the case where the geographic location information belongs to the target geographic location, prompt information is output, and the prompt information is also used to prompt the user of the first electronic device to keep wearing the facial covering.
11. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the voice data processing method as described in any one of claims 1 to 5.
