Volume adjustment method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a volume adjustment method and device, equipment and a storage medium. The method comprises the following steps: acquiring an environment sound sample of a preset duration, extracting a human voice component from the environment sound sample, and analyzing the human voice component to obtain at least one human voice source; comparing the voiceprint feature corresponding to the human sound source with a set user voiceprint feature; in response to a comparison result that the first human sound source is successfully matched with the user voiceprint feature, determining whether a second human sound source in a dialogue state with the first human sound source exists based on the dialogue scene feature; reducing the volume of the audio playing equipment from an original decibel value to a set target decibel value under the condition that the existence of the second human sound source is confirmed; and in response to the fact that a comparison result that the first human sound source is successfully matched with the user voiceprint feature does not exist, maintaining the volume to be the original decibel value. The user does not need to carry out additional operation on the audio playing equipment, and the user can conveniently join and switch between listening and conversation.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of audio debugging, and in particular to a volume adjustment method, apparatus, device and storage medium. Background Art

[0002] With the rapid development of audio technology, people have an increasing demand for the functions of audio playback devices. Common audio playback devices include smart speakers and smart headphones. At present, the volume of audio playback devices is usually adjusted by users through the buttons on the device or remote control devices. When users use audio playback devices to listen to audio, they often need to have a conversation with people nearby. At this time, users need to manually turn down the volume of the audio playback device to facilitate communication with the other party.

[0003] However, since users may have multiple short conversations at intervals, they need to frequently adjust the volume of the audio playback device, turn off the audio playback device, or directly remove the wearable audio playback device during the communication process, which causes great inconvenience and makes it impossible for users to switch smoothly between listening and conversation, affecting the user experience. Summary of the invention

[0004] The embodiments of the present application provide a volume adjustment method, apparatus, device and storage medium, which solve the problem of frequently adjusting the volume of an audio playback device to adapt to communication due to user conversations, realize intelligent recognition of user conversation scenarios, adaptively reduce the playback volume to a level convenient for conversation, and restore the playback volume after the conversation ends, without the user having to perform additional operations on the audio playback device, thereby facilitating the user to switch between listening and conversation.

[0005] In a first aspect, an embodiment of the present application provides a volume adjustment method, which is applied to an audio playback device, comprising:

[0006] Acquire an ambient sound sample of a preset duration, extract a human voice component from the ambient sound sample, and analyze the human voice component to obtain at least one human voice source;

[0007] Comparing the voiceprint features corresponding to the human voice source with the set user voiceprint features;

[0008] In response to a comparison result that a first human voice source successfully matches the user's voiceprint feature, based on the characteristics of the conversation scene, confirming whether there is a second human voice source in a conversation state with the first human voice source;

[0009] When confirming that the second human voice source exists, reducing the volume of the audio playback device from an original decibel value to a set target decibel value;

[0010] In response to the absence of a successful comparison result showing that the first human voice source matches the user voiceprint feature, maintaining the volume of the audio playback device at the original decibel value.

[0011] Wherein, the confirming whether there is a second human voice source in a dialogue state with the first human voice source based on the dialogue scene characteristics includes:

[0012] Taking the first sound sample corresponding to the first human voice source as a reference, it is determined whether there is a second sound sample that is alternately distributed with the first sound sample on the time axis, and the second sound sample corresponds to a second human voice source.

[0013] Wherein, the audio playback device is an independently arranged physical device, including a camera;

[0014] Accordingly, the determining whether there is a second human voice source in a dialogue state with the first human voice source based on the dialogue scene characteristics includes:

[0015] Acquire a picture taken by the camera, and perform portrait feature recognition on the picture taken to obtain at least one candidate dialogue object;

[0016] Based on the utterance direction of the first human voice source, it is confirmed whether there is a target dialogue object among the candidate dialogue objects that meets the posture characteristics corresponding to the dialogue state, and the target dialogue object corresponds to the second human voice source.

[0017] Wherein, the audio playback device is a wearable device including a camera;

[0018] Accordingly, the determining whether there is a second human voice source in a dialogue state with the first human voice source based on the dialogue scene characteristics includes:

[0019] Acquire a picture taken by the camera, and perform face recognition on the picture taken to obtain at least one dialogue object;

[0020] It is determined whether there is a target dialogue object that meets the face orientation condition and the preset distance range, wherein the target dialogue object corresponds to the second voice source.

[0021] The step of reducing the volume of the audio playback device from an original decibel value to a set target decibel value includes:

[0022] Determine the minimum decibel value corresponding to the first human voice sound source and the second human voice sound source;

[0023] Subtract the preset decibel difference from the minimum decibel value to obtain a target decibel value;

[0024] The volume of the audio playback device is reduced from an original decibel value to the target decibel value.

[0025] Before obtaining the sound field samples of the preset time period, the method further includes:

[0026] Receive and store at least one user voiceprint feature.

[0027] In a second aspect, an embodiment of the present application provides a volume adjustment device, which is applied to an audio playback device, including:

[0028] An environmental human voice confirmation unit, used to obtain an environmental sound sample of a preset duration, extract a human voice component from the environmental sound sample, and analyze the human voice component to obtain at least one human voice source;

[0029] A voice comparison unit, used to compare the voiceprint feature corresponding to the voice source with the set user voiceprint feature;

[0030] a conversation voice confirmation unit, configured to confirm whether there is a second voice source in a conversation state with the first voice source based on the characteristics of the conversation scene in response to a comparison result that the first voice source successfully matches the user's voiceprint feature;

[0031] a volume reduction unit, configured to reduce the volume of the audio playback device from an original decibel value to a set target decibel value when confirming that the second human voice source exists;

[0032] The volume maintaining unit is used to maintain the volume of the audio playback device at the original decibel value in response to the absence of a comparison result that shows that the first human voice source matches the user voiceprint feature successfully.

[0033] The dialogue voice confirmation unit includes:

[0034] The sound sample confirmation module is used to determine whether there is a second sound sample that is alternately distributed with the first sound sample on the time axis, using the first sound sample corresponding to the first human voice source as a reference, and the second sound sample corresponds to a second human voice source.

[0035] Wherein, the audio playback device is an independently arranged physical device, including a camera;

[0036] Accordingly, the dialogue voice confirmation unit includes:

[0037] A portrait feature recognition module, used to obtain the shooting picture of the camera, and perform portrait feature recognition on the shooting picture to obtain at least one candidate dialogue object;

[0038] The first dialogue object confirmation module is used to confirm whether there is a target dialogue object that meets the posture characteristics corresponding to the dialogue state among the candidate dialogue objects based on the sound direction of the first human voice sound source, and the target dialogue object corresponds to the second human voice sound source.

[0039] Wherein, the audio playback device is a wearable device including a camera;

[0040] Accordingly, the dialogue voice confirmation unit includes:

[0041] A face recognition module, used to obtain the shooting picture of the camera, and perform face recognition on the shooting picture to obtain at least one dialogue object;

[0042] The second dialogue object confirmation module is used to determine whether there is a target dialogue object that meets the face orientation condition and the preset distance range, and the target dialogue object corresponds to the second voice source.

[0043] Wherein, the volume reduction unit comprises:

[0044] A minimum decibel confirmation module, used to confirm the minimum decibel values ​​corresponding to the first human voice sound source and the second human voice sound source;

[0045] A target decibel confirmation module, used for obtaining a target decibel value by subtracting a preset decibel difference from the minimum decibel value;

[0046] The volume adjustment module is used to reduce the volume of the audio playback device from an original decibel value to the target decibel value.

[0047] It also includes a voiceprint feature presetting unit for receiving and storing at least one user voiceprint feature.

[0048] In a third aspect, an embodiment of the present application provides an audio playback device, which includes: a camera; a microphone; a sound-emitting device; one or more processors; and a storage device configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the volume adjustment method described in any one of the embodiments of the present application.

[0049] In a fourth aspect, an embodiment of the present application provides a non-volatile storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the volume adjustment method described in any one of the embodiments of the present application when executed by a computer processor.

[0050] In the embodiment of the present application, by obtaining an ambient sound sample of a preset duration, extracting a human voice component from the ambient sound sample, and analyzing the human voice component to obtain at least one human voice source; then the voiceprint feature corresponding to the human voice source is compared with the set user voiceprint feature; then in response to the comparison result that the first human voice source successfully matches the user voiceprint feature, based on the characteristics of the conversation scene, confirm whether there is a second human voice source in a conversation state with the first human voice source; then, in the case of confirming that there is a second human voice source, reduce the volume of the audio playback device from the original decibel value to the set target decibel value; finally, in response to the comparison result that there is no successful match between the first human voice source and the user voiceprint feature, maintain the volume of the audio playback device at the original decibel value. Intelligent recognition of the user's conversation scene is achieved, adaptively reducing the playback volume to a level that is convenient for conversation, and restoring the playback volume after the conversation ends, without the user having to perform additional operations on the audio playback device, so that the user can switch between listening and conversation conveniently. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a volume adjustment method provided in an embodiment of the present application;

[0052] Figure 2 is a schematic diagram of an alternating distribution of dialogue sound samples provided in an embodiment of the present application;

[0053] Figure 3 This is a schematic diagram of confirming a conversation partner by combining a camera's captured image provided by an embodiment of the present application;

[0054] Figure 4 It is a schematic diagram of another method of confirming a conversation partner by combining a camera's shooting picture provided by an embodiment of the present application;

[0055] Figure 5 is a structural schematic diagram of a volume adjustment device provided in an embodiment of the present application;

[0056] Figure 6 It is a structural schematic diagram of an audio playback device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0058] The volume adjustment method provided in the embodiment of the present application is applicable to an audio playback device equipped with a processor module. Specifically, the audio playback device can be an independently set audio device, such as a Bluetooth speaker, a vertical speaker, etc., or a wearable audio device, such as a Bluetooth headset, a Bluetooth neckband, etc., which is not limited in the embodiment of the present application. In the volume adjustment method provided in the embodiment of the present application, the execution subject of each step can be a processor module of the audio playback device. The processor module has data calculation, processing and storage capabilities, and can complete the data processing process involved in the volume adjustment method. The several application scenarios listed above are only exemplary and explanatory. In actual applications, the volume adjustment method can also be used in audio output in other scenarios. The present application aims to provide a volume adjustment method, device, equipment and storage medium to solve the problem of frequent adjustment of the volume of the audio playback device to adapt to communication due to user conversations.

[0059] Figure 1 This is a flow chart of a volume adjustment method provided in an embodiment of the present application. The volume adjustment method provided in this embodiment can be implemented by an audio playback device equipped with a processor. Of course, electronic devices that can achieve the same function are also within the scope of protection of this application. The following description takes the processor of the audio playback device as an example to implement the volume adjustment method. Figure 1 , the volume adjustment method specifically includes:

[0060] Step S101: Acquire an ambient sound sample of a preset duration, extract a human voice component from the ambient sound sample, and analyze the human voice component to obtain at least one human voice source.

[0061] It is worth noting that the environmental sound sample refers to the collection of various sounds in the natural environment, including human voice, traffic noise, natural sound, etc. The method of obtaining the environmental sound sample of the preset duration can be to collect the environmental sound periodically according to the preset duration through the sound receiving device of the audio playback device, and provide it to the processor. The processor can extract the human voice component from the environmental sound sample through different analysis methods. For example, the time domain analysis method can be used to extract the human voice component through technical means such as filtering, envelope detection and peak detection; for another example, the frequency domain analysis method can be used. Since the frequency of the human voice signal is usually concentrated between 500-2000Hz, the environmental sound sample can be converted into a frequency domain representation by fast Fourier transform or wavelet transform, and then the human voice component can be extracted; for another example, the pre-built human voice signal model is used to fit and estimate the environmental sound signal after noise removal. Of course, multiple analysis methods can also be used in combination, and this application is not limited here. After the processor obtains the vocal component, it can further analyze and separate the voices of multiple speakers. For example, deep learning-based vocal separation technology, such as Deep Speaker Embeddings, Speaker Diarization and Non-Negative Matrix Factorization and other deep learning algorithms, can better dissociate the vocal components by combining neural network training to obtain at least one vocal sound source. It can be understood that the speaking objects corresponding to the vocal sound source may include the user himself, the dialogue object with the user, and other speakers.

[0062] Step S102: Compare the voiceprint feature corresponding to the human voice source with the set user voiceprint feature.

[0063] Among them, the voiceprint feature refers to the voice feature parameter that can uniquely characterize and identify the identity of the speaker, including the speaker's speaking style, accent, tone, speaking speed, etc. The processor can use a digital signal processing algorithm to extract the voiceprint feature of each human voice source and convert it into a corresponding feature vector. Combined with the feature vector corresponding to the user voiceprint feature set in advance, it is classified, clustered or matched through machine learning or pattern recognition algorithm to obtain a comparison result. The user voiceprint feature is the user information stored in the audio playback device in advance by the user. It can be understood that when the user enters a conversation state while using the audio playback device to listen to the sound, the user's own voice will inevitably appear. Therefore, it is first necessary to confirm that the user's own voice can be matched in at least one human voice source, and then continue to determine whether there is a conversation object. Optionally, the user can import the user voiceprint feature into the audio playback device in advance, and the processor receives and stores at least one user voiceprint feature. It can be understood that when there are multiple users of the audio playback device, the audio playback device can adjust the volume to adapt to the conversation state of multiple users by recording multiple user voiceprint features.

[0064] Step S103: in response to a comparison result that a first human voice source successfully matches the user's voiceprint feature, based on the characteristics of the conversation scene, confirm whether there is a second human voice source that is in a conversation state with the first human voice source.

[0065] Specifically, confirming the existence of a first human voice source that matches the user's voiceprint features in at least one human voice source indicates that the user of the audio playback device is in a vocal state, but the user's vocal state may correspond to different purposes. For example, the user may be singing along or reciting alone, or the user may be in a conversation with others. Therefore, it is necessary to further confirm whether there is a second human voice source that is in a conversation with the first human voice source based on the dialogue scene characteristics, which is equivalent to confirming whether the user has a dialogue object. Among them, the dialogue scene characteristics can be considered from different aspects such as the sound distribution characteristics of the dialogue process and the posture characteristics of the dialogue object.

[0066] In one embodiment, based on the sound distribution characteristics of the conversation process in the conversation scene characteristics, determining whether there is a second human voice source in a conversation state with the first human voice source specifically includes:

[0067] Taking the first sound sample corresponding to the first human voice source as a reference, it is determined whether there is a second sound sample that is alternately distributed with the first sound sample on the time axis, and the second sound sample corresponds to the second human voice source.

[0068] It is understandable that, during a conversation, the characteristic of a conversation between a user and another person should be a back-and-forth communication method, and the user's voice and the voice of the conversation partner will basically not overlap. The corresponding data distribution characteristics are that the first sound sample corresponding to the first human voice source and the second sound sample corresponding to the second human voice source satisfy the law of alternating distribution on the time axis. For example, Figure 2 As shown, currently acquired is an environmental sound sample of preset duration T, and a first sound sample S1 corresponding to a first human voice source and a second sound sample S2 corresponding to a second human voice source are confirmed, wherein the sound data of the first sound sample S1 are distributed in time periods t1-t2, t3-t4 and t5-t6, and the sound data of the second sound sample S2 are distributed in time periods t2-t3, t4-t5 and t6-t7. By arranging the aforementioned multiple time periods in chronological order, it can be known that the first sound sample S1 and the second sound sample S2 are alternately distributed, which meets the sound distribution characteristics of the dialogue process, and thus it can be confirmed that there is a second human voice source that is in a dialogue state with the first human voice source.

[0069] In addition, if we consider using the posture characteristics of the conversation object to determine whether there is a second human voice source in a conversation state with the first human voice source, we can achieve this by adding a camera to the audio playback device. Specifically, since the physical form of the audio playback device includes stand-alone and wearable, generally speaking, the stand-alone audio playback device will be placed near the user facing the user, and the camera it carries can capture the posture information of the two parties in the conversation, while the wearable audio playback device can only capture the posture information of the conversation object because it is worn on the user. Based on this, different recognition and judgment strategies can be set for different types of audio playback devices.

[0070] In one embodiment, the audio playback device is an independently set physical device including a camera, then based on the posture characteristics of the dialogue object in the dialogue scene characteristics, confirming whether there is a second human voice source in a dialogue state with the first human voice source specifically includes:

[0071] The camera captures the image and performs portrait feature recognition on the image to obtain at least one candidate dialogue object; based on the direction of the first voice source, confirm whether there is a target dialogue object among the candidate dialogue objects that meets the posture features corresponding to the dialogue state, and the target dialogue object corresponds to the second voice source.

[0072] Specifically, when it is confirmed that the first human voice source successfully matches the user's voiceprint feature, the processor can obtain the camera's shooting picture at that moment, and perform portrait feature recognition on the shooting picture to obtain at least one candidate dialogue object, wherein the portrait feature recognition can include using a semantic segmentation model based on deep learning, such as FCN, U-Net, Mask R-CNN, etc., to perform portrait segmentation to distinguish multiple candidate dialogue objects, and extract the posture features of each candidate dialogue object, such as the standing position, body orientation, and distance between the candidate dialogue objects, wherein the extraction of posture features can be through the key point detection of the candidate dialogue object, semantic segmentation based on deep learning, instance segmentation, or human posture estimation model, etc., which is not limited in this application. Then, the processor can locate the target area where the candidate dialogue object is located based on the sound direction of the first human voice source, and confirm whether there is a target dialogue object with posture features that meet the dialogue state corresponding to the target area.

[0073] For example, Figure 3 As shown, the user sets up a Bluetooth speaker 301 equipped with a camera 302 indoors. When the Bluetooth speaker 301 is in a music playing state, the user starts a conversation with other people in the room. Then, the processor of the Bluetooth speaker 301 can preliminarily locate the user's voice direction based on the first voice source, that is, the user's voice; then, based on the captured image obtained by the camera 302, the portrait feature is recognized, and in combination with the voice direction, the posture feature of the person in the voice direction is recognized. When it is recognized that there are two dialogue parties with their faces or bodies facing each other, and the distance between the two dialogue parties is within a preset distance range, for example, less than 1m, it can be considered that the user is in a conversation state and there is a second voice source with which to have a conversation. Therefore, the processor can adjust the volume of the Bluetooth speaker 301 to the set target decibel value to adapt to the user's conversation volume. It can be understood that the volume adjustment method provided in the embodiment of the present application can be applied to indoor environments equipped with independent audio devices, such as living rooms, rooms, conference rooms, etc. The independent audio device can automatically identify the user's conversation scene and adaptively adjust the volume to a decibel level suitable for the conversation, so as to facilitate the user to switch smoothly between listening and conversation.

[0074] In another embodiment, the audio playback device is a wearable device including a camera. Then, based on the posture characteristics of the dialogue object in the dialogue scene characteristics, confirming whether there is a second human voice source in a dialogue state with the first human voice source includes:

[0075] The captured image of the camera is obtained, and face recognition is performed on the captured image to obtain at least one dialogue object; and it is determined whether there is a target dialogue object that meets the face orientation condition and the preset distance range, and the target dialogue object corresponds to the second human voice source.

[0076] Specifically, when it is confirmed that the first human voice source successfully matches the user's voiceprint feature, the processor can obtain the camera's shooting picture at that moment, and perform portrait feature recognition on the shooting picture to obtain at least one candidate dialogue object. It can be understood that in the scenario where the user uses a wearable device, the camera can only capture the dialogue object communicating with the user, so the dialogue object in the camera shooting direction can be recognized by face recognition, and by extracting key features of the detected face, it is determined whether the face is facing the camera, or whether the proportion of the detected face part to the complete face meets the preset proportion, such as 80% to 100%. At the same time, it is also necessary to calculate the distance between the candidate dialogue object and the user through the preset mapping relationship based on the proportion and position of the face size to the shooting picture, and determine whether it meets the preset distance range, such as 0 to 1.5 meters. It can be understood that if the preset distance range is exceeded, it can be considered that the user and the candidate dialogue object cannot communicate normally, and the user will further adjust the distance, thereby comprehensively combining the face orientation condition and the judgment result of the preset distance range to determine whether the target dialogue object exists. For example, Figure 4 As shown, when face recognition is performed on the captured image and it is confirmed that there is a candidate dialogue object whose face is facing the camera direction and whose distance from the user falls within a preset distance range, the candidate dialogue object is the target dialogue object.

[0077] Step S104: when it is confirmed that there is a second human voice source, the volume of the audio playback device is reduced from the original decibel value to a set target decibel value.

[0078] It can be understood that confirming the existence of a second human voice source is equivalent to confirming that the user is in a conversation state. In order to ensure that the playback volume of the user's audio playback device will not affect the user's conversation, and at the same time, the user does not need to adjust the volume, the processor can automatically reduce the volume of the audio playback device from the original decibel value to the set target decibel value, where the original decibel value is the decibel value used by the user for listening, and the target decibel value can be a fixed setting, or it can be dynamically adapted based on the decibel values ​​of the sounds of the two parties in the conversation, and this application is not limited to this.

[0079] In a specific implementation process, the process of reducing the volume of the audio playback device from the original decibel value to the set target decibel value may include:

[0080] Confirm the minimum decibel value corresponding to the first human voice sound source and the second human voice sound source; subtract the preset decibel difference from the minimum decibel value to obtain a target decibel value; and reduce the volume of the audio playback device from the original decibel value to the target decibel value.

[0081] It is understandable that the setting of the target decibel value can be adapted to the decibel values ​​of the sounds of the two parties in the conversation. The preset decibel difference can be reduced with reference to the minimum decibel value corresponding to the first voice source and the second voice source. This can not only ensure that the listening state does not affect the user's conversation, but also adaptively control the amplitude of the sound reduction, which is convenient for rapid recovery after the user's conversation ends.

[0082] Step S105: In response to the absence of a successful comparison result showing that the first human voice source matches the user's voiceprint feature, maintaining the volume of the audio playback device at the original decibel value.

[0083] It is worth noting that when there is no first human voice source that successfully matches the user's voiceprint feature, there are two possible situations: first, the user of the audio playback device does not make a sound, and the human voice component in the ambient sound sample comes from the surrounding conversation. At this time, the processor should maintain the volume of the audio playback device at the original decibel value; second, after the user completes the conversation, the processor obtains the most recent ambient sound sample of the preset time and cannot confirm the first human voice source that matches the user's voiceprint feature, then the volume of the audio playback device is maintained at the original decibel value. In this way, the audio playback device can automatically adjust the playback volume, which is effective and convenient.

[0084] In the above, by obtaining an ambient sound sample of a preset duration, extracting the human voice component from the ambient sound sample, and analyzing the human voice component to obtain at least one human voice source; then the voiceprint feature corresponding to the human voice source is compared with the set user voiceprint feature; then in response to the comparison result that the first human voice source successfully matches the user voiceprint feature, based on the characteristics of the conversation scene, confirm whether there is a second human voice source in a conversation state with the first human voice source; then, in the case of confirming that there is a second human voice source, reduce the volume of the audio playback device from the original decibel value to the set target decibel value; finally, in response to the comparison result that there is no successful match between the first human voice source and the user voiceprint feature, maintain the volume of the audio playback device at the original decibel value. Intelligent recognition of the user's conversation scene is achieved, adaptively reducing the playback volume to a level that is convenient for conversation, and restoring the playback volume after the conversation ends, without the user having to perform additional operations on the audio playback device, so that the user can switch between listening and conversation conveniently.

[0085] Figure 5 This is a schematic diagram of the structure of a volume adjustment device provided in an embodiment of the present application. Figure 5The volume adjustment device includes an environment human voice confirmation unit 101, a human voice comparison unit 102, a dialogue human voice confirmation unit 103, a volume reduction unit 104, and a volume maintenance unit 105.

[0086] The environmental human voice confirmation unit 101 is used to obtain an environmental sound sample of a preset duration, extract a human voice component from the environmental sound sample, and analyze the human voice component to obtain at least one human voice source;

[0087] A human voice comparison unit 102, used to compare the voiceprint feature corresponding to the human voice source with the set user voiceprint feature;

[0088] A conversation voice confirmation unit 103 is used to confirm whether there is a second voice source in a conversation state with the first voice source based on the characteristics of the conversation scene in response to a comparison result that the first voice source successfully matches the user's voiceprint feature;

[0089] The volume reduction unit 104 is used to reduce the volume of the audio playback device from an original decibel value to a set target decibel value when confirming that the second human voice source exists;

[0090] The volume maintaining unit 105 is configured to maintain the volume of the audio playback device at the original decibel value in response to the absence of a successful comparison result showing that the first human voice source matches the user voiceprint feature.

[0091] Based on the above-mentioned embodiment, the dialogue voice confirmation unit 103 includes:

[0092] The sound sample confirmation module is used to determine whether there is a second sound sample that is alternately distributed with the first sound sample on the time axis, using the first sound sample corresponding to the first human voice source as a reference, and the second sound sample corresponds to a second human voice source.

[0093] Based on the above-mentioned embodiment, the audio playback device is an independently arranged physical device, including a camera;

[0094] Correspondingly, the dialogue voice confirmation unit 103 includes:

[0095] A portrait feature recognition module, used to obtain the shooting picture of the camera, and perform portrait feature recognition on the shooting picture to obtain at least one candidate dialogue object;

[0096] The first dialogue object confirmation module is used to confirm whether there is a target dialogue object that meets the posture characteristics corresponding to the dialogue state among the candidate dialogue objects based on the sound direction of the first human voice sound source, and the target dialogue object corresponds to the second human voice sound source.

[0097] Based on the above-mentioned embodiment, the audio playback device is a wearable device including a camera;

[0098] Correspondingly, the dialogue voice confirmation unit 103 includes:

[0099] A face recognition module, used to obtain the shooting picture of the camera, and perform face recognition on the shooting picture to obtain at least one dialogue object;

[0100] The second dialogue object confirmation module is used to determine whether there is a target dialogue object that meets the face orientation condition and the preset distance range, and the target dialogue object corresponds to the second voice source.

[0101] Based on the above embodiment, the volume reduction unit 104 includes:

[0102] A minimum decibel confirmation module, used to confirm the minimum decibel values ​​corresponding to the first human voice sound source and the second human voice sound source;

[0103] A target decibel confirmation module, used for obtaining a target decibel value by subtracting a preset decibel difference from the minimum decibel value;

[0104] The volume adjustment module is used to reduce the volume of the audio playback device from an original decibel value to the target decibel value.

[0105] Based on the above embodiment, it further includes a voiceprint feature presetting unit for receiving and storing at least one user voiceprint feature.

[0106] In the above, by obtaining an ambient sound sample of a preset duration, extracting the human voice component from the ambient sound sample, and analyzing the human voice component to obtain at least one human voice source; then the voiceprint feature corresponding to the human voice source is compared with the set user voiceprint feature; then in response to the comparison result that the first human voice source successfully matches the user voiceprint feature, based on the characteristics of the conversation scene, confirm whether there is a second human voice source in a conversation state with the first human voice source; then, in the case of confirming that there is a second human voice source, reduce the volume of the audio playback device from the original decibel value to the set target decibel value; finally, in response to the comparison result that there is no successful match between the first human voice source and the user voiceprint feature, maintain the volume of the audio playback device at the original decibel value. Intelligent recognition of the user's conversation scene is achieved, adaptively reducing the playback volume to a level that is convenient for conversation, and restoring the playback volume after the conversation ends, without the user having to perform additional operations on the audio playback device, so that the user can switch between listening and conversation conveniently.

[0107] Figure 6 A schematic diagram of the structure of an audio playback device provided in an embodiment of the present application is shown in FIG. Figure 6As shown, the audio playback device includes a processor 201, a memory 202, an input device 203, an output device 204 and a communication device 205; the number of processors 201 in the audio playback device can be one or more. Figure 6 A processor 201 is taken as an example; the processor 201 memory 201, input device 203, output device 204 and communication device 205 in the audio playback device can be connected by a bus or other means, Figure 6 The example of connecting through bus is taken in the following.

[0108] The memory 202, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the volume adjustment method in the embodiment of the present invention (for example, the environmental human voice confirmation unit 101, the human voice comparison unit 102, the dialogue human voice confirmation unit 103, the volume reduction unit 104, and the volume maintenance unit 105). The processor 201 executes various functional applications and data processing of the audio playback device by running the software programs, instructions and modules stored in the memory 202, that is, implements the above-mentioned volume adjustment method.

[0109] The memory 202 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the audio playback device, etc. In addition, the memory 202 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 202 may further include a memory remotely arranged relative to the processor 201, and these remote memories may be connected to the audio playback device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0110] The input device 203 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the audio playback device, such as a microphone or other sound receiving device, and a camera or other image acquisition sensor. The output device 204 in this solution can be a sound device, and can also have a sound output device or other display device.

[0111] The above-mentioned audio playback device includes a volume adjustment device, which can be used to execute any volume adjustment method and has corresponding functions and beneficial effects.

[0112] The embodiment of the present application also provides a storage medium containing computer executable instructions, which are used to execute a volume adjustment method when executed by a computer processor, the volume adjustment method comprising: obtaining an environmental sound sample of a preset duration, extracting a human voice component from the environmental sound sample, and parsing the human voice component to obtain at least one human voice source; comparing the voiceprint feature corresponding to the human voice source with the set user voiceprint feature; in response to the comparison result that there is a successful match between the first human voice source and the user voiceprint feature, based on the characteristics of the dialogue scene, confirming whether there is a second human voice source in a dialogue state with the first human voice source; in the case of confirming that there is the second human voice source, reducing the volume of the audio playback device from the original decibel value to the set target decibel value; in response to the absence of a successful match between the first human voice source and the user voiceprint feature, maintaining the volume of the audio playback device at the original decibel value. When the computer program is executed by the processor, it can also implement the relevant operations in other volume adjustment methods provided in any embodiment of the present application, and has corresponding functions and beneficial effects.

[0113] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products.

[0114] Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0115] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0116] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0118] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A volume adjustment method, applied to an audio playback device, characterized in that: include: Acquire an ambient sound sample of a preset duration, extract a human voice component from the ambient sound sample, and analyze the human voice component to obtain at least one human voice source; Comparing the voiceprint features corresponding to the human voice source with the set user voiceprint features; In response to a comparison result that a first human voice source successfully matches the user's voiceprint feature, based on the characteristics of the conversation scene, confirming whether there is a second human voice source in a conversation state with the first human voice source; When confirming that the second human voice source exists, reducing the volume of the audio playback device from an original decibel value to a set target decibel value; In response to the absence of a successful comparison result showing that the first human voice source matches the user voiceprint feature, maintaining the volume of the audio playback device at the original decibel value.

2. The volume adjustment method according to claim 1, characterized in that: The determining, based on the dialogue scene characteristics, whether there is a second human voice source in dialogue with the first human voice source includes: Taking the first sound sample corresponding to the first human voice source as a reference, it is determined whether there is a second sound sample that is alternately distributed with the first sound sample on the time axis, and the second sound sample corresponds to a second human voice source.

3. The volume adjustment method according to claim 1, characterized in that: The audio playback device is an independently arranged physical device, including a camera; Accordingly, the determining whether there is a second human voice source in a dialogue state with the first human voice source based on the dialogue scene characteristics includes: Acquire a picture taken by the camera, and perform portrait feature recognition on the picture taken to obtain at least one candidate dialogue object; Based on the utterance direction of the first human voice source, it is confirmed whether there is a target dialogue object among the candidate dialogue objects that meets the posture characteristics corresponding to the dialogue state, and the target dialogue object corresponds to the second human voice source.

4. The volume adjustment method according to claim 1, characterized in that: The audio playback device is a wearable device, including a camera; Accordingly, the determining whether there is a second human voice source in a dialogue state with the first human voice source based on the dialogue scene characteristics includes: Acquire a picture taken by the camera, and perform face recognition on the picture taken to obtain at least one dialogue object; It is determined whether there is a target dialogue object that meets the face orientation condition and the preset distance range, wherein the target dialogue object corresponds to the second voice source.

5. The volume adjustment method according to any one of claims 1 to 4, characterized in that: The step of reducing the volume of the audio playback device from an original decibel value to a set target decibel value includes: Determine the minimum decibel value corresponding to the first human voice sound source and the second human voice sound source; Subtract the preset decibel difference from the minimum decibel value to obtain a target decibel value; The volume of the audio playback device is reduced from an original decibel value to the target decibel value.

6. The volume adjustment method according to any one of claims 1 to 4, characterized in that: Before obtaining the sound field samples of the preset time period, the method further includes: Receive and store at least one user voiceprint feature.

7. A volume adjustment device, applied to an audio playback device, characterized in that: include: An environmental human voice confirmation unit, used to obtain an environmental sound sample of a preset duration, extract a human voice component from the environmental sound sample, and analyze the human voice component to obtain at least one human voice source; A voice comparison unit, used to compare the voiceprint feature corresponding to the voice source with the set user voiceprint feature; a conversation voice confirmation unit, configured to confirm whether there is a second voice source in a conversation state with the first voice source based on the characteristics of the conversation scene in response to a comparison result that the first voice source successfully matches the user's voiceprint feature; a volume reduction unit, configured to reduce the volume of the audio playback device from an original decibel value to a set target decibel value when confirming that the second human voice source exists; The volume maintaining unit is used to maintain the volume of the audio playback device at the original decibel value in response to the absence of a comparison result that shows that the first human voice source matches the user voiceprint feature successfully.

8. An audio playback device, characterized in that: The audio playback device comprises: microphone; Sound-generating device; one or more processors; The storage device is configured to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the volume adjustment method described in any one of claims 1, 2, 5, and 6.

9. The audio playback device according to claim 8, characterized in that: The audio playback device also includes: A camera, wherein the one or more processors are used to implement the volume adjustment method according to any one of claims 1 to 6.

10. A non-volatile storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are configured to execute the volume adjustment method according to any one of claims 1 to 6.

Images