Information processing method and electronic device

Abstract

The application discloses an information processing method and an electronic device. The method comprises: obtaining a voice signal collected by a first audio component; analyzing the voice signal to obtain an audio feature; determining that the first electronic device meets a condition based on the audio feature, and emitting a first ultrasonic signal to enable a second electronic device to control a second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal; the condition represents that a sound source uses the first electronic device to speak; the first electronic device is any device in a device set, the second electronic device is another device in the device set except the first electronic device, and the devices in the device set access a same audio session.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to an information processing method and an electronic device. Background Technology

[0002] In many video conferencing or multi-person audio calls, multiple electronic devices may be connected to the same audio session in the same room. When multiple electronic devices connected to the same audio session are in the same room, if a user speaks, an acoustic loop may be formed between the microphones and speakers of multiple electronic devices, which can easily cause echo interference or even feedback, thus affecting the session quality. Summary of the Invention

[0003] On one hand, this application provides an information processing method applied to a first electronic device, comprising:

[0004] Obtain the speech signal collected by the first audio component;

[0005] Analyze the speech signal to obtain audio features;

[0006] Based on the audio characteristics, the first electronic device is determined to meet the conditions and emits a first ultrasonic signal, so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal; meeting the conditions indicates that the sound source is using the first electronic device to speak.

[0007] The first electronic device is any device in the device set, and the second electronic device is any other device in the device set besides the first electronic device. The devices in the device set are connected to the same audio session.

[0008] In one possible implementation, determining that the first electronic device meets the condition based on the audio characteristics and transmitting the first ultrasonic signal includes:

[0009] The transmission interval corresponding to the first electronic device is determined based on the audio characteristics; different transmission intervals represent different times when the electronic device is triggered to emit ultrasonic signals.

[0010] The launch time is randomly selected from the launch interval corresponding to the first electronic device;

[0011] If no second ultrasonic signal emitted by the second electronic device is detected before the emission time arrives, it is determined that the first electronic device meets the condition and emits the first ultrasonic signal at the emission time.

[0012] In another possible implementation, determining the transmission range corresponding to the first electronic device based on the audio features includes at least one of the following:

[0013] In response to the audio features including speech energy, a transmission interval is determined based on the speech energy. The higher the speech energy, the earlier the corresponding transmission interval indicates that the electronic device is triggered to emit an ultrasonic signal.

[0014] In response to the audio features, including the signal-to-noise ratio (SNR), a transmission interval is determined based on the SNR. The higher the SNR, the earlier the corresponding transmission interval indicates that the electronic device is triggered to emit an ultrasonic signal.

[0015] In yet another possible implementation, the information processing method further includes:

[0016] If a second ultrasonic signal emitted by the second electronic device is detected before the emission time arrives, the first audio component of the first electronic device is controlled to be in a non-operating state.

[0017] In another possible implementation, the first audio component controlling the first electronic device is in a non-operating state, including:

[0018] Obtain the session identifier carried in the second ultrasound signal, the session identifier being used to identify the audio session accessed by the second electronic device;

[0019] If the session identifier matches the session identifier of the audio session accessed by the first electronic device, the first audio component of the first electronic device is controlled to be in a non-working state.

[0020] In yet another possible implementation, the information processing method further includes:

[0021] The observation data is sent to the processing module, and the observation data includes at least the audio features; the processing module is used to determine the target electronic device in the device set whose audio component can be in a working state based on the observation data reported by the devices in the device set; wherein, the processing module is the processing unit in the first electronic device, the second electronic device, or the conference server;

[0022] The processing module sends a first control command, which is used to instruct the target electronic device to control the audio component to be in a working state.

[0023] If the first electronic device is the target electronic device indicated in the first control command, control the first audio component to be in a working state;

[0024] If the first electronic device is not the target electronic device indicated in the first control command, control the first audio component to be in a non-operating state.

[0025] In another possible implementation, the first ultrasound signal carries an event identifier, which is used to uniquely identify the first ultrasound signal;

[0026] The observation data also includes the event identifier;

[0027] The processing module determines the target electronic device in the following manner:

[0028] The transmitted observation data is determined to include at least one candidate device of the event identifier;

[0029] Based on the audio characteristics sent by each candidate device, a target electronic device in which the audio component can be in a working state is determined from the candidate devices.

[0030] In another possible implementation, the observation data further includes: device capability information of the first electronic device, the device capability information including: the role information of the first electronic device in the audio session, the type of the first audio component, and at least one of the signal strength and reception time of the first ultrasonic signal received by the first electronic device;

[0031] The step of determining a target electronic device from the candidate devices whose audio components can be operational based on the audio features transmitted by each candidate device includes:

[0032] Based on the audio features and device capability information sent by each candidate device, a comprehensive score for the candidate device is determined. The higher the comprehensive score, the stronger the candidate device's ability to collect and process the speech signal.

[0033] The target electronic device among the candidate devices whose comprehensive score meets the set requirements is identified.

[0034] In yet another possible implementation, the information processing method further includes:

[0035] If the first audio component does not detect a voice signal for a set period of time, it sends a voice end indication to the processing module. The processing module is used to send a second control command to the second electronic device in response to the voice end indication. The second control command is used to instruct the second electronic device to switch the second audio component from a non-working state to a working state.

[0036] In another aspect, this application also provides an electronic device, comprising:

[0037] The first audio component is used to acquire voice signals;

[0038] And, a processor, configured to parse the speech signal to obtain audio features; determine, based on the audio features, that the electronic device meets a condition, and transmit a first ultrasonic signal so that a second electronic device controls a second audio component of the second electronic device to be in a non-operating state based on the first ultrasonic signal; meeting the condition indicates that the sound source is using the electronic device to speak;

[0039] Wherein, the electronic device is any device in the device set, the second electronic device is any other device in the device set besides the electronic device, and the devices in the device set are connected to the same audio session. Attached Figure Description

[0040] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0041] Figure 1 A flowchart illustrating the information processing method provided in this application;

[0042] Figure 2 Another flowchart illustrating the information processing method provided in this application;

[0043] Figure 3 Another flowchart illustrating the information processing method provided in this application;

[0044] Figure 4 A flowchart illustrating the information processing method provided in this application;

[0045] Figure 5 This is an example diagram illustrating a scenario in this application where multiple users in the same room access the same video conference via electronic devices.

[0046] Figure 6 To adopt the scheme of this application, it is necessary to proceed through two stages from Figure 5 An example diagram showing the selection of a speaking device in the scenario shown;

[0047] Figure 7 A schematic diagram of the composition structure of an electronic device provided in this application. Detailed Implementation

[0048] The solution proposed in this application can be applied to audio conversation scenarios such as video conferencing, audio conferencing, and multi-person voice communication to reduce the echo interference or even howling caused by the formation of acoustic loops between multiple electronic devices in the same room during audio conversations, thereby improving the conversation quality of audio conversations.

[0049] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is only for explaining specific embodiments and is not intended to limit the application. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0050] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0051] like Figure 1 The diagram illustrates a flowchart of an information processing method provided in this application. This embodiment is applied to a first electronic device, which can be a mobile phone, laptop, desktop computer, or conference server, etc., without limitation.

[0052] S101, obtain the voice signal collected by the first audio component.

[0053] In this application, an audio component is a component in an electronic device used to acquire audio signals, such as a microphone. For ease of distinction, the audio component of the first electronic device is referred to as the first audio component.

[0054] Among them, voice signal refers to audio signal emitted by user.

[0055] In one example, the presence of a user's voice signal can be determined by identifying the audio volume or audio energy of the audio signal acquired by the first audio component. If the audio volume or audio energy is greater than a set threshold, then the acquired voice signal can be identified.

[0056] In another example, the audio signal collected by the first audio component can be identified based on the Voice Activity Detection (VAD) algorithm to detect whether the audio signal includes user speech. If user speech is detected, the speech signal collected by the first audio component is confirmed and the speech signal collected by the first audio component is obtained.

[0057] S102, Analyze the speech signal to obtain audio features.

[0058] The audio features may include at least one of the features of the speech signal, such as speech energy, signal-to-noise ratio, and speech volume.

[0059] S103, based on the audio characteristics, it is determined that the first electronic device meets the conditions, and a first ultrasonic signal is emitted so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal.

[0060] The condition that the first electronic device satisfies indicates that the sound source uses the first electronic device to speak, that is, it indicates that the user uses the first electronic device as a speaking device in an audio session.

[0061] The first ultrasonic signal is an ultrasonic signal broadcast by the first electronic device. The first ultrasonic signal can be a sound wave signal with a frequency exceeding 20kHz, or the frequency of the ultrasonic signal can be set according to actual needs, without any specific restrictions.

[0062] It is understandable that, since ultrasonic signals are a type of sound wave, and based on their propagation characteristics, ultrasonic waves cannot penetrate walls to continue propagating. Therefore, after the first electronic device emits the first ultrasonic signal, only electronic devices located in the same room as the first electronic device can receive the first ultrasonic signal.

[0063] In this application, the first electronic device is any device in the device set, and the second electronic device is any other device in the device set besides the first electronic device. All devices in the device set are connected to the same audio session. The audio session can be a video conference, an audio conference, or other form of online conference session. It can also be a video call session or an audio call conference between multiple electronic devices, etc., without any specific limitations.

[0064] When both the first and second electronic devices belong to a device cluster, based on the propagation characteristics of ultrasonic signals, if the second electronic device can receive the first ultrasonic signal, then the second electronic device and the first electronic device must be located in the same room. Therefore, the second electronic device is also another electronic device that is connected to the same audio session and is located in the same room as the first electronic device. Based on this, a device cluster can be considered to include all devices connected to the same audio session and located in the same room.

[0065] In this application, the first ultrasonic signal serves to trigger other electronic devices besides the first electronic device to disable their audio components. Correspondingly, if the second electronic device receives the first ultrasonic signal, it will disable its second audio component.

[0066] It is understandable that, considering that the solution of this application is only needed to reasonably control whether each electronic device in the same audio session is a speaking device when a user begins to speak; and that after the first electronic device causes the second audio component of the second electronic device to enter a non-working state by emitting the first ultrasonic signal, the first electronic device no longer needs to continuously identify the audio characteristics of the speech signal. Therefore, the speech signal obtained in this application can also be obtained by detecting that the audio signal collected by the first audio component includes the start point of the speech signal, and then obtaining the speech signal collected by the first audio component and performing subsequent operations. This allows for more timely control of the audio component of the second electronic device to enter a non-working state when a user is speaking indoors. If the audio signal collected by the first audio component includes the speech signal but does not include the start point of the speech signal, then steps S102 and S103 are not required to reduce data processing.

[0067] As can be seen from the above, after obtaining the voice signal collected by the first audio component, if the first electronic device is determined to meet the conditions based on the voice characteristics of the voice signal, it indicates that the sound source needs to use the first electronic device to speak. Therefore, other electronic devices connected to the same audio session and located in the same room as the first electronic device do not need to collect audio signals. Based on this, when the first electronic device meets the conditions, it will emit a first ultrasonic signal. Due to the propagation characteristics of ultrasonic signals, among the electronic devices connected to the same audio session, only the second electronic device located in the same room as the first electronic device can receive the first ultrasonic signal. Upon receiving the first ultrasonic signal, the second electronic device will control its second audio component to be in a non-working state, ensuring that only one electronic device (i.e., the first electronic device) has its audio component working among all the electronic devices connected to the same audio session and located in the same room. This reduces the possibility of acoustic loops forming between the audio components and audio output units of multiple electronic devices in the same room, naturally reducing echo interference and howling, and thus improving the session quality of the audio session.

[0068] Furthermore, unlike using dedicated session control equipment such as conference machines to mute multiple devices in the same audio session, which can result in multiple devices connected to the same audio session but located in different rooms being muted, this application can not only use ultrasonic signals to control the audio component of only one electronic device in the same room to be in working state, reducing the situation of accidental muting across rooms in audio sessions; it can also enable electronic devices in the same room to flexibly control whether their audio components are in working state based on whether the sound source is using the electronic device, avoiding the limitation of only being able to set the audio components of the conference machine or a specific device to be in working state, thus providing greater flexibility.

[0069] In one possible scenario, considering that electronic devices in the same room may not all be connected to the same audio session, to avoid affecting the normal use of other electronic devices in the same room as the first electronic device but not connected to the audio session corresponding to the first electronic device, in this application, the first electronic device may transmit a first ultrasonic signal carrying a first session identifier of the audio session to which the first electronic device is connected. Accordingly, if the second electronic device receives the first ultrasonic signal and determines that the first session identifier matches the second session identifier of the audio session to which the second electronic device is connected, the second electronic device will set its second audio component to a non-operating state.

[0070] In this application, there are several possible ways for the first electronic device to determine whether the condition is met based on audio features. For example, determining whether the first electronic device meets the condition based on audio features could be that the speech energy included in the audio features exceeds a set threshold, or it could be that the speech energy of the speech signals detected by other electronic devices in the device set is obtained, and if the first electronic device has the highest speech energy, it is determined that the first electronic device meets the condition.

[0071] The following explanation uses one possible scenario where the first electronic device meets the conditions as an example. For instance... Figure 2 This illustration shows another flowchart of the information processing method provided in this application, which is applied to a first electronic device. The method of this embodiment may include:

[0072] S201, obtain the voice signal collected by the first audio component.

[0073] S202, Analyze the speech signal to obtain audio features.

[0074] The above two steps can be found in the descriptions of other embodiments, and will not be repeated here.

[0075] S203, determine the transmission range corresponding to the first electronic device based on the audio characteristics.

[0076] Different transmission intervals represent different times when the electronic device is triggered to emit ultrasonic signals.

[0077] For example, each transmission interval can be a time interval used to characterize the selectively transmitted ultrasonic signal, and different transmission intervals correspond to different time intervals. As an optional approach, the time intervals corresponding to different transmission intervals may not overlap in time.

[0078] The transmission interval can be a time interval of duration, which represents the time at which an ultrasonic signal can be transmitted after the current moment. For example, the transmission interval can be [0 milliseconds, 25 milliseconds], representing that an ultrasonic signal can be transmitted at any time between 0 and 25 milliseconds after the current moment.

[0079] The transmission interval can also be a time interval that represents the time when an ultrasonic signal can be emitted. For example, the transmission interval can be [time 1, time 2], which means that an ultrasonic signal can be emitted at any time between time 1 and time 2.

[0080] In one example, determining the transmission interval based on audio features can be based on the correspondence between different audio features and transmission intervals, determining the transmission interval that matches the audio feature, and the transmission interval can be a duration interval.

[0081] In another example, determining the transmission interval based on audio features can also be done by first determining a duration interval based on the audio features, where the duration interval may vary depending on the audio features; then, based on the current time and the duration interval, the transmission interval is determined, which is the time interval for the transmission time. For example, adding the duration interval to the current time yields the time interval for the transmission time.

[0082] Of course, there are other possibilities for determining the specific implementation of the launch zone, and there are no restrictions on this.

[0083] In this embodiment, different audio characteristics may lead to different determined transmission intervals. Specifically, higher audio characteristics indicate higher signal quality of the speech signal, and the determined transmission interval indicates an earlier time when the electronic device is triggered to emit the ultrasonic signal.

[0084] S204, randomly select a transmission time within the transmission interval corresponding to the first electronic device.

[0085] The transmission time is randomly selected from the transmission interval corresponding to the first electronic device, and is the time when the first electronic device is used to transmit the first ultrasonic signal.

[0086] For example, if the transmission interval is a duration interval, and a duration is randomly selected from this interval, then the transmission time is the current time delayed by that duration. For instance, if the transmission interval is [0 milliseconds, 50 milliseconds], and a randomly selected transmission time is 20 milliseconds, then the first ultrasonic signal will be transmitted 20 milliseconds after the current time.

[0087] For example, the launch interval is a time interval, and the launch time selected from the launch interval can be any specific time point within that time interval.

[0088] S205, if the second ultrasonic signal emitted by the second electronic device is not detected before the emission time arrives, it is determined that the first electronic device meets the condition, and emits the first ultrasonic signal at the emission time, so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal.

[0089] In this application, the first electronic device is any device in the device set, and the second electronic device is any other device in the device set besides the first electronic device. All devices in the device set are connected to the same audio session. Furthermore, since ultrasonic signals cannot penetrate indoor walls, if the first electronic device detects a second ultrasonic signal emitted by the second electronic device, it indicates that the second electronic device and the first electronic device are in the same indoor space.

[0090] Among them, meeting the condition indicates that the sound source uses the first electronic device to speak.

[0091] It is understood that the first electronic device can be any device in the device set. Therefore, for any device connected to the same audio session, the device can use the scheme of this application to determine the time when it emits an ultrasonic signal. Based on this, if the second electronic device does not emit a second ultrasonic signal before the emission time corresponding to the first electronic device arrives, it means that before the emission time arrives, other devices in the same room as the first electronic device in the device set have not yet determined themselves as speaking devices as sound sources. In this case, the first electronic device can determine itself as a speaking device as a sound source and notify each second electronic device in the device set of this information by emitting a first ultrasonic signal. This causes the audio components of other electronic devices in the device set to be in a non-working state, ensuring that only one device's audio component is working among the devices connected to the same audio session and in the same room, reducing the risk of acoustic loops formed by devices in the same room.

[0092] Furthermore, in this embodiment, after the first electronic device determines the transmission interval based on the audio characteristics of the collected voice signal, it randomly selects a transmission time from the transmission interval. In this way, even if the audio characteristics of the voice signals collected by two electronic devices are similar, causing the two electronic devices to determine the same transmission interval, the possibility of the two electronic devices corresponding to the same transmission time can be reduced by randomly selecting a transmission time in the transmission interval. This can reduce the situation where multiple electronic devices send ultrasonic signals at the same time due to the same or similar audio characteristics of the voice signals collected by different electronic devices. Naturally, this can reduce the situation where multiple devices in the same room may be identified as speaking devices for audio conversations due to multiple electronic devices sending ultrasonic signals at the same time. This can further reduce the situation where multiple devices in the same room are used as speaking devices, causing echo interference or even howling. Naturally, this can improve the conversation quality of audio conversations.

[0093] In this embodiment, the audio features can be varied, and correspondingly, the methods for determining the transmission interval can also vary. For example, in one possible implementation, determining the transmission interval based on the audio features can include at least one of the following:

[0094] In response to audio features including speech energy, a transmission interval is determined based on the speech energy; wherein, the higher the speech energy, the earlier the corresponding transmission interval indicates the time when the electronic device is triggered to emit an ultrasonic signal;

[0095] In response to audio characteristics including signal-to-noise ratio (SNR), a transmission interval is determined based on the SNR. The higher the SNR, the earlier the corresponding transmission interval indicates that the electronic device is triggered to emit an ultrasonic signal.

[0096] Speech energy can be the instantaneous intensity or loudness of a speech signal. The speech energy of a speech signal can be characterized by the sum of squares of the amplitudes of the speech signal over a period of time.

[0097] In one example, multiple voice energy levels can be pre-configured, with different voice energy ranges corresponding to different voice energy levels, and different voice energy levels can correspond to different transmission ranges.

[0098] For example, let's take the time interval corresponding to the launch interval as an example:

[0099] Speech energy levels can be categorized into high, medium, and low energy levels. For example, a speech energy value exceeding 60 is considered a high energy level; a value between 30 and 60 is considered a medium energy level; and a value below 30 is considered a low energy level.

[0100] Among them, the emission range corresponding to the high energy level can be [0 milliseconds, 50 milliseconds];

[0101] The emission interval corresponding to the medium energy level can be [50 milliseconds, 100 milliseconds];

[0102] The emission interval corresponding to the low energy level can be [100 milliseconds, 150 milliseconds].

[0103] It is evident that the higher the speech energy level, the shorter the delay time of the ultrasonic signal transmission represented by the corresponding transmission interval, meaning that the time when the electronic device is triggered to transmit the ultrasonic signal is earlier.

[0104] It is understandable that the higher the speech energy of the voice signal detected by the electronic device, the earlier the determined transmission interval represents the time when the electronic device emits the ultrasonic signal. Therefore, after randomly selecting the transmission time based on the transmission area, the probability that the electronic device will receive the ultrasonic signal emitted by other electronic devices at the corresponding transmission time is lower. This makes it more likely that the electronic device with higher voice energy will be able to emit the ultrasonic signal. Naturally, this also makes it more likely that the electronic device with higher voice energy will be used as the speaking device in the audio conversation. This is beneficial for the electronic device with higher voice energy emitted by the sound source to be used as the speaking device, which can improve the conversation effect of the audio conversation.

[0105] The signal-to-noise ratio (SNR) is the ratio between the power of the effective speech signal and the power of the background noise. Determining the transmission interval based on SNR is similar to determining it based on speech energy, and will not be elaborated further. Since a higher SNR in the speech signal detected by an electronic device indicates an earlier time when the electronic device emits the ultrasonic signal, an electronic device with a higher SNR in its speech signal acquisition has a higher probability of emitting the ultrasonic signal. This naturally makes electronic devices capable of acquiring high SNR speech signals more likely to be identified as speaking devices in audio conversations, thus improving the conversational quality.

[0106] In one example, in the above embodiment, if a second ultrasonic signal emitted by a second electronic device is detected before the emission time corresponding to the first electronic device arrives, the first audio component of the first electronic device can be controlled to be in a non-operating state.

[0107] As described above, if the second ultrasonic signal emitted by the second electronic device is detected before the emission time corresponding to the first electronic device arrives, it indicates that before the emission time corresponding to the first electronic device arrives, other devices connected to the audio session and located in the same room as the first electronic device have already identified themselves as the speaking device of the sound source. In this case, to avoid multiple devices in the same room simultaneously acting as speaking devices and forming an acoustic loop in the same audio session, the first electronic device in this application will not identify itself as the speaking device of the sound source. Moreover, in response to receiving the second ultrasonic signal, the first electronic device will control its first audio component to be in a non-operating state, so that only one device among multiple devices in the same room can act as the speaking device in the audio session.

[0108] Furthermore, to prevent the first electronic device from receiving ultrasonic signals emitted by other electronic devices that are not connected to the audio session (such as an electronic device connected to another audio session or an electronic device that has not received any audio session mistakenly emitting an ultrasonic signal), which would cause the first electronic device to mistakenly set its first audio component to a non-working state, i.e., cross-audio session interference or misoperation, the second ultrasonic signal emitted by the second electronic device in this application will also carry a session identifier, which is used to identify the audio session that the second electronic device is connected to.

[0109] Correspondingly, the first electronic device can obtain the session identifier carried in the second ultrasonic signal. If the session identifier carried in the second ultrasonic signal is consistent with the session identifier of the audio session accessed by the first electronic device, it indicates that the second electronic device and the first electronic device are accessed by the same audio session, and the first electronic device will control the first audio component to be in a non-working state.

[0110] It is understood that in any of the above embodiments of this application, each device in the device set can determine the speaking device (i.e., the device whose audio component needs to be in working state) based on the detected audio characteristics, and use ultrasonic signals to control the audio components of other devices other than the speaking device to be in a non-working state. Through this process, a unique speaking device can be determined relatively quickly from multiple devices that are connected to the same audio session and belong to the same room, so as to achieve "quick mute" of other devices other than the unique speaking device in the room.

[0111] For ease of distinction and description, the process of determining the speaking device (such as the first electronic device or the second electronic device that transmits the second ultrasonic signal) that meets the conditions through any of the above embodiments is referred to as the rapid mute phase.

[0112] While the rapid mute phase can quickly identify the electronic device as the speaking device within the device set and disable the audio components of other electronic devices, relying solely on a single device to determine its own speaking status based on its own acquired audio characteristics may not be a reliable method for selection. Therefore, to more effectively select the electronic device capable of capturing higher-quality audio signals as the speaking device, a re-selection phase can be implemented after the rapid mute phase.

[0113] During the re-selection phase, a processing module can combine information such as audio characteristics collected by various electronic devices connected to the audio session and located in the same room to comprehensively determine the most suitable electronic device for collecting the voice source.

[0114] The following is combined Figure 3 Please provide an explanation. For example... Figure 3 This illustrates another flowchart of the information processing method provided in this application. The method in this embodiment may include:

[0115] S301, obtain the voice signal collected by the first audio component.

[0116] S302, parse the speech signal to obtain audio features.

[0117] S303, based on the audio characteristics, it is determined that the first electronic device meets the conditions, and a first ultrasonic signal is emitted so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal.

[0118] Among them, meeting the condition indicates that the sound source uses the first electronic device to speak.

[0119] The first electronic device is any device in the device set, and the second electronic device is any other device in the device set besides the first electronic device. The devices in the device set are connected to the same audio session.

[0120] The specific implementation of steps S301 to S303 above can be found in the relevant descriptions of the previous embodiments, and will not be repeated here.

[0121] It is understandable that the above steps S301 to S303 are the operations performed by the first electronic device in the "rapid mute phase". Through the above steps S301 and S303, the first electronic device can be initially identified as the speaking device, so as to achieve relatively efficient control that only one electronic device's audio component is in working state among the electronic devices connected to the audio session in the same room, that is, to achieve rapid mute.

[0122] Of course, this embodiment is illustrated by taking the determination of the first electronic device meeting the conditions based on audio characteristics as an example. If the first electronic device does not meet the conditions based on audio characteristics, the first electronic device responds to the second ultrasonic signal emitted by the second electronic device and controls the first audio component to be in a non-working state. This situation also applies to this embodiment, and will not be elaborated further.

[0123] S304, sends observation data to the processing module.

[0124] The processing module is a processing unit within a first electronic device, a second electronic device, or a conference server. The conference server can be a device used to improve the quality of the audio session or a device used to enable access to the audio session. The conference server can belong to a device cluster or be located outside of a device cluster; there are no restrictions on this.

[0125] For example, the processing unit in the first electronic device, the second electronic device, or the conference server can be pre-configured as the processing module, or the processing unit can be determined by negotiation between the first electronic device and the devices in the device set as the processing module, without any specific restrictions.

[0126] The observation data includes at least the audio features obtained by the first electronic device based on the speech signal.

[0127] It is understandable that when the first electronic device emits the first ultrasonic signal, it indicates that each electronic device connected to the same audio session and belonging to the same room as the first electronic device has a need to determine the speaking device. The first electronic device can be any electronic device in the device set, and the first electronic device can also receive the first ultrasonic signal emitted by itself. Based on this, any electronic device in the device set (i.e., the first electronic device and the second electronic device) can send observation data to the processing module in response to receiving the first ultrasonic signal.

[0128] Specifically, in this embodiment, taking the first electronic device emitting a first ultrasonic signal as an example, if the first electronic device is not determined to meet the conditions based on audio characteristics, then the first electronic device can receive the second ultrasonic signal emitted by the second electronic device. In this case, in order to further accurately determine the electronic device suitable for activating the audio component, the first electronic device can also send observation data to the processing module after receiving the second ultrasonic signal. Of course, other devices in the device set will also send observation data to the processing module after receiving the second ultrasonic signal.

[0129] Accordingly, the processing module is used to determine the target electronic device whose audio component can be operational based on the observation data reported by the devices in the device set. For example, the processing module can determine the device with the highest audio signal quality or whose audio signal quality meets the requirements as the target electronic device based on the audio features reported by each device in the device set; the specific implementation is not limited.

[0130] Furthermore, the observation data transmitted by the first electronic device also includes: device capability information of the first electronic device. This device capability information includes: the role information of the first electronic device in the audio session, the type of the first audio component, and at least one of the signal strength and reception time of the first ultrasonic signal received by the first electronic device.

[0131] Among them, role information is used to characterize the role of the user of the first electronic device in the audio session. For example, role information can be divided into meeting initiator, meeting host, and meeting participant.

[0132] The type of audio component is used to characterize the voice acquisition performance of the audio component. For example, the types of audio components are divided into built-in audio components, external audio components, audio components with dual microphones, and audio components with a single microphone.

[0133] In this embodiment, taking the first electronic device transmitting a first ultrasonic signal as an example, the device capability information of the first electronic device may include the signal strength and / or reception time of the first ultrasonic signal received by the first electronic device. It is understood that if the first electronic device does not transmit the first ultrasonic signal, but instead receives a second ultrasonic signal transmitted by a second electronic device, then the device capability information may be the signal strength and / or reception time of the second ultrasonic signal received by the first electronic device.

[0134] Correspondingly, the observation data sent to the processing module by other devices in the device set may also include the device's capability information, such as the device's role in the audio session, the type of audio component in the device, and at least one of the signal strength and reception time of the first ultrasonic signal (or the second ultrasonic signal) received by the device, which will not be elaborated further.

[0135] Based on this, the processing module can be used to determine the target electronic device in the device set whose audio components can be in a working state, based on the audio characteristics and device capability information reported by the devices in the device set.

[0136] S305, receive the first control command sent by the processing module.

[0137] The first control command is used to instruct a target electronic device to control the audio components to be in a working state. For example, the first control command carries the device identifier of the target electronic device.

[0138] It should be noted that the processing module only returns the first control command to devices that have sent it observation data; it does not return the first control command to devices that have not sent it observation data. Furthermore, since only electronic devices that receive the first ultrasonic signal (or the second ultrasonic signal) will send observation data to the processing module, only devices connected to the audio session and located in the same room will receive the first control command.

[0139] S306, if the first electronic device is the target electronic device indicated in the first control command, control the first audio component to be in working state.

[0140] S307, if the first electronic device is not the target electronic device indicated in the first control command, control the first audio component to be in a non-operating state.

[0141] In this embodiment, steps S304 to S307 above belong to the "re-optimization stage".

[0142] It is understood that this embodiment is illustrated by taking the first audio component of the first electronic device as being in the working state during the "rapid microphone muting stage". In this case, if the target electronic device for which the audio component can be in the working state is determined by the processing module in the "re-optimization stage" is the first electronic device, then the first electronic device can maintain the first audio component in the working state. If the target electronic device determined by the processing module is not the first electronic device, then the first electronic device needs to set the first audio component from the working state to the non-working state.

[0143] Of course, the second electronic device in the device set will also receive the first control command, and can also control its second audio to be in a working state or a non-working state based on the control command.

[0144] As can be seen from the above, in this embodiment, after the first electronic device determines that it meets the conditions based on audio characteristics and emits a first ultrasonic signal, causing the second audio component of the second electronic device to be in a non-working state, the first electronic device will also send observation data to the processing module. The processing module will re-determine the target electronic device as the speaking device (i.e., the audio component can be in a working state) based on the audio characteristics in the observation data sent by each device in the device cluster, and send a first control command to re-control the other electronic devices in the device cluster, except for the target electronic device, to be in a non-working state, thereby realizing a more reasonable determination of the speaking device by comprehensively considering the audio characteristics of all devices in the device cluster.

[0145] It is understood that the processing module can be a first electronic device, a second electronic device, or other devices not located in the same room as the first electronic device. Based on this, the first electronic device and other devices in the device set can establish a communication connection with the processing module via a wireless local area network or other means. For example, if the first electronic device and other devices in the device set establish wireless communication with the processing module via WiFi, the first electronic device can send the observation data to the processing module via the WiFi network.

[0146] Based on this, in addition to receiving observation data sent by each device that is connected to the audio session and is in the same room, the processing module may also receive observation data sent by devices that are connected to the audio session but are not in the same room. Based on this, in order to identify each device belonging to the same room, the first ultrasonic signal emitted by the first electronic device may also carry an event identifier, which is used to uniquely identify the first ultrasonic signal.

[0147] Accordingly, the observation data sent by the first electronic device to the processing module may also include the event identifier. Furthermore, the observation data sent by other devices in the device set to the processing module may also include the event identifier. Based on this, the processing module can determine at least one candidate device whose sent observation data includes the event identifier; and based on the audio characteristics sent by each candidate device, determine a target electronic device from among the candidate devices whose audio component can be operational.

[0148] It is understandable that since the observation data sent by the candidate devices all include the event identifier, it means that the candidate devices are all devices that can receive the first ultrasonic signal. This also means that the at least one candidate device can include the first electronic device and the device that is in the same room as the first electronic device and connected to the same audio session. Based on this, the processing module can determine the target electronic device from the at least one candidate device, thus identifying the unique target electronic device for turning on the audio component from the devices connected to the same audio session and in the same room.

[0149] It is understandable that the ultrasonic signal emitted by the electronic device is different after each round of the user's voice. Therefore, identifying the first ultrasonic signal by an event identifier can also help distinguish the different rounds of the user's voice in the audio session, so as to avoid confusing the audio features of different rounds of voice signals detected by different devices in the same room, which could lead to the incorrect identification of the target electronic device.

[0150] The processing module can determine the specific implementation of the target electronic device based on the observation data of each candidate device, and there are multiple possible implementations, without any restrictions.

[0151] In one possible scenario, where the observation data sent by the first electronic device includes audio features and device capability information, the processing module can determine the comprehensive score of each candidate device based on the audio features and device capability information sent by each candidate device. A higher comprehensive score indicates a stronger ability of the candidate device to acquire and process speech signals. Correspondingly, the target electronic device can be identified among the candidate devices whose comprehensive scores meet set requirements. For example, the candidate device with the highest comprehensive score can be identified as the target electronic device, or a candidate device with a comprehensive score exceeding a set value can be identified as the target electronic device.

[0152] The device capability information of the first electronic device includes: the role information of the first electronic device in the audio session, the type of the first audio component, and at least one of the signal strength and reception time of the first ultrasonic signal received by the first electronic device. For details, please refer to the relevant introduction above, which will not be repeated here.

[0153] The comprehensive score for determining candidate devices can be determined according to a set scoring rule, without specific restrictions. For ease of understanding, this will be illustrated using audio features, including the speech energy of the speech signal, and in conjunction with one implementation method:

[0154] For each candidate device, a role score is determined based on its role information, with different roles corresponding to different role scores. The equivalent signal strength is determined based on the reception time and signal strength of the first ultrasonic signal received by the candidate device. A longer reception time relative to the current moment corresponds to a higher equivalent signal strength; conversely, a higher signal strength corresponds to a higher equivalent signal strength. Similarly, a sound pickup capability score is determined based on the type of audio component used by the candidate device, with different types of audio components corresponding to different sound pickup capability scores.

[0155] Based on this, the overall score of the candidate device can be calculated using the following formula:

[0156] ;

[0157] Here, Elocal represents the speech energy included in the audio features transmitted by the candidate device; RSS represents the equivalent signal strength of the candidate device; Capability represents the candidate device's sound pickup capability score; and RolePriority represents the candidate device's role score. w1, w2, w3, and w4 represent different weight values, which can be set as needed.

[0158] To facilitate understanding of the interaction process between the first electronic device, the second electronic device, and the processing module, the following example illustrates the process with the processing module deployed on a third electronic device, which can be the first electronic device, the second electronic device, or the aforementioned conference server.

[0159] To facilitate description and provide a clear understanding of the specific implementation of the first electronic device when it receives the second ultrasonic signal emitted by the second electronic device, the following example illustrates how the first electronic device receives the second ultrasonic signal emitted by the second electronic device before reaching its corresponding emission time. Figure 4 An explanation will be provided. Furthermore, for easier and more intuitive understanding, [the following will be explained]. Figure 4 In this embodiment, the audio features parsed from the speech signal are used as an example to illustrate the speech energy of the speech signal.

[0160] like Figure 4 This illustration shows a flowchart of an information processing method provided in this application. The method in this embodiment may include:

[0161] S401, the first electronic device determines the speech signal collected by the first audio component and obtains the speech energy of the speech signal.

[0162] S402, the first electronic device determines the first transmission interval corresponding to the first electronic device based on the voice energy.

[0163] Different transmission intervals represent different times when the electronic device is triggered to emit ultrasonic signals. For ease of distinction, the transmission interval determined by the first electronic device is called the first transmission interval, and the transmission interval determined by the second electronic device is called the second transmission interval.

[0164] S403, the first electronic device randomly selects a first transmission time within the first transmission interval.

[0165] S404, the second electronic device determines the second transmission interval based on the speech energy of the speech signal collected by the second audio component, and randomly selects the second transmission time from the second transmission interval.

[0166] It is understandable that there can be multiple electronic devices connected to the same audio session and located in the same room, but these multiple electronic devices can be either the first electronic device or the second electronic device, which will not be elaborated here.

[0167] In this embodiment, the example is taken as the second launch time necessarily being earlier than the first launch time.

[0168] For example, if the second electronic device detects that the voice energy is higher than that detected by the first electronic device, and relative to the first transmission interval, the second transmission interval represents the earlier the time of triggering the transmission of the ultrasonic signal, then the second transmission time selected from the second transmission interval must be earlier than the first transmission time selected from the first transmission interval.

[0169] For example, the first and second launch intervals may belong to the same launch interval, but the randomly selected second launch time is earlier than the first launch time. (Combined) Figure 5 illustrate, Figure 5 This diagram illustrates a scenario where multiple users in the same room access the same video conference via electronic devices.

[0170] Assume the first electronic device is Figure 5 User A uses an electronic device, and a certain second electronic device is... Figure 5 The electronic devices used by user B in Figure 5 User A's electronic device detected a voice energy of 75, while User B's electronic device detected a voice energy of 80. Based on this, the voice energy detected by both electronic devices belongs to the high energy level, so the corresponding transmission range of both electronic devices belongs to the range of [0 mm, 50 ms].

[0171] However, User A's electronic device selects a first transmission time of 35 milliseconds from the transmission range corresponding to the high energy level, meaning User A's electronic device can only transmit the first ultrasonic signal 35 milliseconds after the current moment. User B's electronic device, on the other hand, selects a second transmission time of 10 milliseconds from the transmission range corresponding to the same high energy level, meaning User B's electronic device needs to transmit the second ultrasonic signal 10 milliseconds after the current moment. Therefore, User B's electronic device will inevitably transmit the ultrasonic signal earlier.

[0172] In addition, by Figure 5It can be seen that other users' electronic devices can also be connected to the same audio session and be located in the same room. In this embodiment, other electronic devices can also be regarded as the first electronic device. For example, if user C's electronic device detects a voice energy of 25, its determined transmission interval is [100 milliseconds, 150 milliseconds], and the transmission time selected from this transmission interval is 120 milliseconds, then user C will inevitably receive the second ultrasonic signal transmitted by user B's electronic device before reaching its corresponding transmission time.

[0173] It is understandable that the specific process by which the second electronic device determines the second launch time is similar to the process by which the first electronic device determines the first launch time, and will be repeated here.

[0174] It should be noted that step S404 can be executed synchronously with steps S401 to S403.

[0175] S405, if the second electronic device does not receive the first ultrasonic signal before the second transmission time, it is determined that the second electronic device meets the conditions, and transmits the second ultrasonic signal at the second transmission time, and controls the second audio component to be in working state.

[0176] In this application, the second ultrasonic signal may carry a second session identifier of the audio session accessed by the second electronic device and a target event identifier for identifying the second ultrasonic signal.

[0177] S406, the first electronic device receives the second ultrasonic signal before the first transmission time is reached. If the session identifier in the second ultrasonic signal is identified as the session identifier of the audio session accessed by the first electronic device, the first audio component is controlled to be in a non-working state.

[0178] It is understandable that since the second transmission time of the second electronic device is earlier than the first transmission time, the second electronic device will inevitably transmit the second ultrasonic signal first. When the first electronic device receives the second ultrasonic signal, it will set its first audio component to a non-working state and will no longer need to perform the operation of sending the first ultrasonic signal.

[0179] It is understandable that if the second session identifier in the second ultrasonic signal is not the first session identifier of the audio session accessed by the first electronic device, it means that the current second ultrasonic signal is not an ultrasonic signal sent by another electronic device accessing the same audio session as the first device. In this case, in order to avoid mistakenly shutting down its own first audio component, the first electronic device can ignore the second ultrasonic signal.

[0180] S407, the first electronic device sends observation data to the third electronic device.

[0181] The observation data includes the speech energy of the speech signal collected by the first electronic device, the device capability information of the first electronic device, the first session identifier of the audio session accessed by the first electronic device, and the event identifier carried by the second ultrasonic signal. The device capability information includes at least one of the following: the role of the first electronic device in the audio session, the type of the first audio component, and the signal strength and reception time of the second ultrasonic signal received by the first electronic device.

[0182] S408, the second electronic device sends observation data to the third electronic device.

[0183] The observation data includes the speech energy of the speech signal collected by the second electronic device, the device capability information of the second electronic device, the second session identifier of the audio session accessed by the second electronic device, and the event identifier corresponding to the second ultrasonic signal. The device capability information includes at least one of the following: the role of the second electronic device in the audio session, the type of the second audio component, and the signal strength and reception time of the second ultrasonic signal received by the second electronic device.

[0184] It is understandable that since the first electronic device and the second electronic device are connected to the same audio session, the first session identifier and the second session identifier are the same.

[0185] S409, the third electronic device, based on the observation data sent by each electronic device, identifies each electronic device with the same session identifier and the same event identifier as a candidate device, and obtains at least one candidate device that is connected to the same audio conference and is in the same room.

[0186] S410, the third electronic device determines a target electronic device from at least one candidate device whose audio component can be in a working state based on the audio characteristics and device capability information sent by each candidate device.

[0187] For example, based on the audio characteristics and device capability information sent by each candidate device, a comprehensive score of the candidate device is determined. The higher the comprehensive score, the stronger the candidate device's ability to collect and process the voice signal. The target electronic device among the candidate devices whose comprehensive score meets the set requirements (e.g., the highest comprehensive score) is determined.

[0188] It is understandable that the process by which the third electronic device determines the target electronic device can be found in the previous introduction on the determination of the target electronic device by the processing module, and will not be repeated here.

[0189] S411, the third electronic device broadcasts a first control command to control the operating status of the audio single component in the first electronic device and the second electronic device.

[0190] The first control command indicates the device identifier of the at least one candidate device and whether each candidate device is the target electronic device.

[0191] In this embodiment, the target electronic device is taken as the first electronic device. The first control command may include different electronic devices and status indicators for whether the audio component in the electronic device is in a working state. For example, if the audio component is in a working state, it is represented by 1, and the audio component is in a non-working state, then the first control command can indicate that the status indicator corresponding to the second electronic device is 1, and the status indicator corresponding to other electronic devices is 0.

[0192] S412, the first electronic device switches the first audio component from a non-working state to a working state based on the first control command.

[0193] S413, the second electronic device switches the second audio component from an active state to a non-active state based on the first control command.

[0194] Of course, if the target electronic device is not the first electronic device, but the second electronic device, then after receiving the control command, the first electronic device can keep its first audio component in a non-working state; after receiving the first control command, the second electronic device can also keep its second audio component in a working state.

[0195] To facilitate intuitive understanding, combined with Figure 5 and Figure 6 Please provide an explanation. Figure 6 It shows in Figure 5 The example diagram shows the target electronic device selected using the "re-optimization phase" in the scenario shown.

[0196] Depend on Figure 5 As can be seen from the introduction, in Figure 5 In this scenario, the audio components of user B's electronic device are determined to be in working order through a rapid microphone muting phase.

[0197] by Figure 6 The following example illustrates how the processing module combines observation data from each electronic device to determine its overall score. Figure 6 As can be seen, the processing module, by combining the observation data sent by each electronic device, determines that the comprehensive score of user A's electronic device is 78 points, the comprehensive score of user B's electronic device is 85 points, and the comprehensive score of the conference server is 90 points. Therefore, the third electronic device can instruct user B's electronic device to switch its audio component to a non-working state and instruct the conference server to switch its audio component to a working state.

[0198] It is understood that in any of the above embodiments of this application, when the first electronic device emits the first ultrasonic signal, the first audio component of the first electronic device will necessarily be in a working state. If a user uses the first electronic device to make a speech, there may be situations where other users make speeches through other devices. Therefore, in order to avoid affecting the speeches of other users, it is necessary to promptly restore the audio components of other devices in the device set to a working state.

[0199] Based on this, if the first audio component fails to detect a voice signal for a set duration, the first electronic device will also send a voice end indication to the processing module. In this case, the processing module, in response to the voice end indication, sends a second control command to the second electronic device, wherein the second control command instructs the second electronic device to switch the second audio component from a non-operating state to an operating state.

[0200] If the first audio component fails to detect a voice signal for a set duration, it indicates that the sound source has stopped inputting the voice signal, meaning the speech has ended. For example, the VAD algorithm can detect the end point of the voice signal, and once the end point is detected, a voice end indication is sent to the processing module.

[0201] In particular, in order for the processing module to accurately identify each second electronic device, the voice end indication may also carry a conference identifier of the audio conference accessed by the first electronic device and an event identifier for representing the first ultrasound signal. Based on this, the processing module can identify the device corresponding to the historically received observation data containing the conference identifier and event identifier as the second electronic device.

[0202] To help you understand the benefits of this application, we will use a set of data to illustrate the point below.

[0203] The following shows the time consumed by performing different actions in the two stages after adopting the scheme of this application, the total time consumed by each of the two stages, and the total time consumed by the two stages.

[0204]

[0205] The main actions in each stage of the table above are the actions that the device needs to perform at that stage. For example, detecting speech energy is the operation of obtaining the speech energy of the speech signal in the previous stage, and the others are similar and will not be described in detail.

[0206] Here, "ideal" refers to the time required in ideal environments or scenarios with minimal interference, such as LAN conferencing. It can also be considered the time required in scenarios like cloud conferencing. The conservative estimate represents the maximum time required in complex scenarios.

[0207] Combining the table above with an analysis and comparison of the duration of echo interference in different audio conversation scenarios, we can find that:

[0208] In a local area network (LAN) conferencing scenario, the time required for echo interference or howling to form is usually 200-400ms. However, the solution proposed in this application can ensure that only one speaking device is retained in the same room during the same conference within 70-150ms. That is, the response time of this solution is 70-150ms, which can suppress the formation of acoustic loops before echo interference or howling occurs.

[0209] In cloud conferencing scenarios, the time required for echo interference or howling to form is usually 600-1200ms. However, the solution proposed in this application can ensure that only one speaking device is retained in the same room during the same meeting within 120-300ms. That is, the response time of this solution is 120-300ms, which can suppress the formation of acoustic loops before echo interference or howling occurs.

[0210] Moreover, in some meetings with extreme delays, the time required for echo interference or feedback to form is usually greater than 1.5 seconds. However, the solution proposed in this application can keep only one speaking device in the same room during the same meeting within 300-700ms, and can also suppress the formation of acoustic loops before echo interference or feedback occurs.

[0211] This application also provides an electronic device in its embodiments. For example... Figure 7 As shown, it illustrates a schematic diagram of the composition structure of the electronic device, which includes at least a processor 701 and a first audio component 702;

[0212] The first audio component 702 is used to acquire voice signals;

[0213] And, processor 701, configured to parse the speech signal to obtain audio features; determine that the electronic device meets a condition based on the audio features, and transmit a first ultrasonic signal so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal; meeting the condition indicates that the sound source is using the electronic device to speak;

[0214] Wherein, the electronic device is any device in the device set, the second electronic device is any other device in the device set besides the electronic device, and the devices in the device set are connected to the same audio session.

[0215] For details regarding the specific operation of the processor, please refer to the relevant description on the first electronic device side in the previous method embodiments, which will not be repeated here.

[0216] In one example, the electronic device may also include a memory 703 for storing programs required by the processor to perform operations.

[0217] Of course, the electronic device may also include other components such as the display unit 704, without limitation.

[0218] This application also provides a computer program product, including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the information processing methods provided in this application.

[0219] This application also provides a computer-readable storage medium that carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the information processing methods provided in this application.

[0220] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0221] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0222] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0223] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. An information processing method, applied to a first electronic device, comprising: Obtain the speech signal collected by the first audio component; Analyze the speech signal to obtain audio features; Based on the audio characteristics, the first electronic device determines that the condition is met and transmits a first ultrasonic signal so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal. The condition is met to indicate that the sound source uses the first electronic device to speak; The first electronic device is any device in the device set, and the second electronic device is any other device in the device set besides the first electronic device. The devices in the device set are connected to the same audio session.

2. The information processing method according to claim 1, wherein determining that the first electronic device meets the condition based on the audio features and transmitting the first ultrasonic signal comprises: The transmission range corresponding to the first electronic device is determined based on the audio characteristics; Different transmission intervals indicate different times when electronic devices are triggered to emit ultrasonic signals; The launch time is randomly selected from the launch interval corresponding to the first electronic device; If no second ultrasonic signal emitted by the second electronic device is detected before the emission time arrives, it is determined that the first electronic device meets the condition and emits the first ultrasonic signal at the emission time.

3. The information processing method according to claim 2, wherein determining the transmission interval corresponding to the first electronic device based on the audio features includes at least one of the following: In response to the audio features including speech energy, a transmission interval is determined based on the speech energy. The higher the speech energy, the earlier the corresponding transmission interval indicates that the electronic device is triggered to emit an ultrasonic signal. In response to the audio features, including the signal-to-noise ratio (SNR), a transmission interval is determined based on the SNR. The higher the SNR, the earlier the corresponding transmission interval indicates that the electronic device is triggered to emit an ultrasonic signal.

4. The information processing method according to claim 2 further includes: If a second ultrasonic signal emitted by the second electronic device is detected before the emission time arrives, the first audio component of the first electronic device is controlled to be in a non-operating state.

5. The information processing method according to claim 4, wherein controlling the first audio component of the first electronic device to be in a non-operating state includes: Obtain the session identifier carried in the second ultrasound signal, the session identifier being used to identify the audio session accessed by the second electronic device; If the session identifier matches the session identifier of the audio session accessed by the first electronic device, the first audio component of the first electronic device is controlled to be in a non-working state.

6. The information processing method according to any one of claims 1 to 5, further comprising: The observation data is sent to the processing module, and the observation data includes at least the audio features. The processing module is used to determine the target electronic device in the device set whose audio component can be in a working state based on the observation data reported by the devices in the device set; wherein, the processing module is the processing unit in the first electronic device, the second electronic device, or the conference server; The processing module sends a first control command, which is used to instruct the target electronic device to control the audio component to be in a working state. If the first electronic device is the target electronic device indicated in the first control command, control the first audio component to be in a working state; If the first electronic device is not the target electronic device indicated in the first control command, control the first audio component to be in a non-operating state.

7. The information processing method according to claim 6, wherein the first ultrasonic signal carries an event identifier, the event identifier being used to uniquely identify the first ultrasonic signal; The observation data also includes the event identifier; The processing module determines the target electronic device in the following manner: The transmitted observation data is determined to include at least one candidate device of the event identifier; Based on the audio characteristics sent by each candidate device, a target electronic device in which the audio component can be in a working state is determined from the candidate devices.

8. The information processing method according to claim 7, wherein the observation data further includes: The device capability information of the first electronic device includes: the role information of the first electronic device in the audio session, the type of the first audio component, and at least one of the signal strength and reception time of the first ultrasonic signal received by the first electronic device. The step of determining a target electronic device from the candidate devices whose audio components can be operational based on the audio features transmitted by each candidate device includes: Based on the audio features and device capability information sent by each candidate device, a comprehensive score for the candidate device is determined. The higher the comprehensive score, the stronger the candidate device's ability to collect and process the speech signal. The target electronic device among the candidate devices whose comprehensive score meets the set requirements is identified.

9. The information processing method according to claim 1, further comprising: If the first audio component does not detect a voice signal for a set period of time, it sends a voice end indication to the processing module. The processing module is used to send a second control command to the second electronic device in response to the voice end indication. The second control command is used to instruct the second electronic device to switch the second audio component from a non-working state to a working state.

10. An electronic device, comprising: The first audio component is used to acquire voice signals; And a processor, used to parse the speech signal to obtain audio features; Based on the audio characteristics, the electronic device is determined to meet the conditions and emits a first ultrasonic signal, so that the second electronic device controls the second audio component of the second electronic device to be in a non-working state based on the first ultrasonic signal; meeting the conditions indicates that the sound source is using the electronic device to speak. Wherein, the electronic device is any device in the device set, the second electronic device is any other device in the device set besides the electronic device, and the devices in the device set are connected to the same audio session.

Images