A method and device for adjusting sound effects of smart speakers

By obtaining the position of the smart speaker and adjusting the sound effect parameters, combining user input and audio response, the problem of sound effect adjustment of the smart speaker in different environments is solved, and high-quality sound effect output in different home environments is achieved, improving the user experience.

CN113923561BActive Publication Date: 2024-11-08ALIBABA GROUP HOLDING LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010652488.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-08
Publication Date
2024-11-08
Estimated Expiration
2040-07-08

AI Technical Summary

Technical Problem

Smart speakers fail to effectively adjust the sound effects in different home environments, resulting in the inability to achieve preset sound effects and cannot meet users' needs for high-quality sound effects.

Method used

By obtaining the position of the smart speaker in the space, determining the initial EQ sound effects parameters, adjusting the sound effects parameters according to the spatial impact response of the audio, fine-tuning it in combination with user input, and dynamically adjusting the volume to adapt to environmental changes.

Benefits of technology

It realizes that smart speakers achieve preset sound effects in different spatial environments, improve user experience and provide better auditory experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113923561B_ABST
    Figure CN113923561B_ABST
Patent Text Reader

Abstract

The present invention provides a method and device for adjusting the sound effect of a smart speaker, the method comprising: obtaining the position of the smart speaker in space; determining a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset EQ sound effect parameters; obtaining the spatial impact response of the audio played by the smart speaker according to the first EQ sound effect parameter; and determining a second EQ sound effect parameter according to the spatial impact response and the first EQ sound effect parameter. The present invention roughly adjusts the sound effect by obtaining the placement position of the smart speaker, and then fine-tunes the sound effect according to the obtained spatial impact response, so that the smart speaker can achieve the preset sound effect in different spatial environments, allowing users to obtain better auditory experience and improve user experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart speakers, and in particular to a method and device for adjusting sound effects of a smart speaker. Background Art

[0002] With the popularization and development of smart speakers, users have a stronger demand for high-quality sound effects of smart speakers. Since smart speakers have a variety of voice scenarios, such as voice broadcasting, music playing, audiobooks, etc., using the same set of EQ sound effect parameters to process the above different types of audio obviously cannot meet the needs.

[0003] In the prior art, multiple groups of EQ sound effect parameters are usually stored in a smart speaker, and the user selects one of the groups for setting in the setting interface according to his or her preferences, or the smart speaker intelligently selects one of the groups for setting according to the user's direction and / or position.

[0004] However, when smart speakers are applied to home environments, the acoustic environment in the room may be different due to differences in the layout and placement of objects in the room. The methods of adjusting the sound effects of smart speakers in the prior art may not necessarily achieve the preset sound effects in different home environments.

[0005] Therefore, how to provide a method for adjusting the sound effects of a smart speaker so that the smart speaker can achieve preset sound effects in different spatial environments has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0006] An object of the present invention is to provide a method for adjusting the sound effects of a smart speaker, so that the smart speaker can achieve preset sound effects in different spatial environments and improve the user experience.

[0007] In order to achieve the above object, an embodiment of the present invention provides a method for adjusting sound effects of a smart speaker, comprising:

[0008] Obtaining the position of the smart speaker in space;

[0009] Determining a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters;

[0010] Obtaining a spatial impulse response of the audio played by the smart speaker according to the first EQ sound effect parameter;

[0011] A second EQ sound effect parameter is determined according to the spatial impulse response and the first EQ sound effect parameter.

[0012] Furthermore, obtaining the position of the smart speaker in space specifically includes: obtaining a spatial scene image captured by a dual camera of the smart speaker; processing the image using a binocular ranging algorithm to obtain a spatial model and the position of the smart speaker in space.

[0013] Furthermore, determining the first EQ sound effect parameter according to the position specifically includes: obtaining a relative position according to the space model and the position of the smart speaker in the space; obtaining the first EQ sound effect parameter from a preset EQ sound effect parameter table according to the relative position; wherein the preset EQ sound effect parameter table includes a correspondence between multiple groups of EQ sound effect parameters and relative positions.

[0014] Furthermore, obtaining the spatial impulse response of the audio played by the smart speaker according to the first EQ sound effect parameters specifically includes: obtaining the audio signal played according to the first EQ sound effect parameters and received by the MIC array of the smart speaker; and extracting the spatial impulse response according to the audio signal.

[0015] Furthermore, determining the second EQ sound effect parameter based on the spatial impulse response and the first EQ sound effect parameter specifically includes: obtaining a spatial frequency response based on the spatial impulse response; comparing the spatial frequency response with a preset spatial frequency response to obtain a compensation factor at each frequency point; and adjusting the first EQ sound effect parameter based on the compensation factor to obtain the second EQ sound effect parameter.

[0016] Furthermore, after determining the second EQ sound effect parameter, the method further includes: adjusting the second EQ sound effect parameter according to a user input to obtain a third sound effect parameter.

[0017] Furthermore, the method also includes: detecting whether there is a person in the captured image and whether the person is close to or far away from the smart speaker; and when the person is close to the smart speaker, reducing the volume of the smart speaker, and when the person is far away from the smart speaker, increasing the volume of the smart speaker.

[0018] The embodiment of the present invention further provides a smart speaker sound effect adjustment device, comprising:

[0019] A position acquisition module, used to obtain the position of the smart speaker in space;

[0020] A first adjustment module, configured to determine a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters;

[0021] A spatial impulse response acquisition module, used to acquire the spatial impulse response of the audio played by the smart speaker according to the first EQ sound effect parameter;

[0022] The second adjustment module is used to determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter.

[0023] Furthermore, the position acquisition module is specifically used to: obtain the spatial scene image taken by the dual cameras of the smart speaker; use the binocular ranging algorithm to process the image to obtain the spatial model and the position of the smart speaker in the space.

[0024] Furthermore, the first adjustment module is specifically used to: obtain the relative position according to the spatial model and the position of the smart speaker in the space; obtain the first EQ sound effect parameter from a preset EQ sound effect parameter table according to the relative position; wherein the preset EQ sound effect parameter table includes a correspondence between multiple sets of EQ sound effect parameters and relative positions.

[0025] Furthermore, the spatial impulse response acquisition module is specifically used to: obtain the audio signal received by the MIC array of the smart speaker and played according to the first EQ sound effect parameter; and extract the spatial impulse response according to the audio signal.

[0026] Furthermore, the second adjustment module is specifically used to: obtain a spatial frequency response based on the spatial impulse response; compare the spatial frequency response with a preset spatial frequency response to obtain a compensation factor at each frequency point; adjust the first EQ sound effect parameter according to the compensation factor to obtain the second EQ sound effect parameter.

[0027] Furthermore, the device also includes a third adjustment module, which is used to adjust the second EQ sound effect parameter according to the user's input to obtain a third sound effect parameter.

[0028] Furthermore, the device also includes a volume adjustment module, which is used to detect whether there is a person in the captured image and whether the person is close to or far away from the smart speaker; and when the person is close to the smart speaker, reduce the volume of the smart speaker, and when the person is far away from the smart speaker, increase the volume of the smart speaker.

[0029] An embodiment of the present invention also provides a computer program product, including computer program instructions, which, when executed by a processor, are used to implement the aforementioned smart speaker sound effect adjustment method.

[0030] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the aforementioned smart speaker sound effect adjustment method is implemented.

[0031] The beneficial effect of the present invention is as follows: the present invention roughly adjusts the sound effect by obtaining the placement position of the smart speaker, and then fine-tunes the sound effect according to the obtained spatial impact response, so that the smart speaker can achieve the preset sound effect in different spatial environments, allowing users to obtain a better auditory experience and enhance user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0033] Figure 1 This is a method flow chart of embodiment 1 of the present invention.

[0034] Figure 2 This is a method flow chart of Embodiment 2 of the present invention.

[0035] Figure 3 This is a device block diagram of embodiment 3 of the present invention.

[0036] Figure 4 This is a device block diagram of embodiment 4 of the present invention. DETAILED DESCRIPTION

[0037] In order to facilitate those skilled in the art to understand and implement the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] Embodiment 1

[0039] See also Figure 1 , Embodiment 1 of the present invention provides a method for adjusting sound effects of an intelligent speaker, the method comprising:

[0040] S101. Obtain the position of the smart speaker in space.

[0041] In this step, the dual cameras configured on the smart speaker can be used to perform binocular visual ranging to obtain a spatial model, and then the images taken by the dual cameras are matched with the spatial model to obtain the position of the smart speaker in space.

[0042] It is also possible to use multiple ranging devices configured on the smart speaker. The multiple ranging devices can be set at different positions inside the speaker to measure the distance to different sides of the speaker. In other words, the position and distance of the obstacle can be located in three-dimensional space to obtain a model of the space where the speaker is currently located and the position of the speaker in the space.

[0043] For example, laser ranging can be performed by a laser sensor configured on the smart speaker to obtain spatial point cloud data, thereby obtaining a spatial model, and then using a matching algorithm to obtain the position of the smart speaker in the space. Alternatively, ultrasonic ranging, infrared ranging, etc. can be used. Since binocular vision ranging, laser ranging, ultrasonic ranging, and infrared ranging are all existing technologies, the present invention will not be described in detail.

[0044] Preferably, step S101 specifically includes the following steps:

[0045] S1011. Obtain spatial scene images captured by the dual cameras of the smart speaker.

[0046] S1012. Process the image using a binocular ranging algorithm to obtain a spatial model and the position of the smart speaker in space.

[0047] Since smart speakers are usually placed in a home environment, the binocular distance measurement algorithm can be used to measure the distance of each obstacle in the space and establish a space model. Then, the images taken by the dual cameras are matched with the space model to obtain the position of the smart speaker in the space model. For example, the spatial coordinate value of the smart speaker can be obtained.

[0048] S102. Determine a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters.

[0049] Preferably, step S102 specifically includes the following steps:

[0050] S1021. Obtain a relative position according to the space model and the position of the smart speaker in the space.

[0051] S1022. Obtain the first EQ sound effect parameter from a preset EQ sound effect parameter table according to the relative position, wherein the preset EQ sound effect parameter table includes a correspondence between multiple groups of EQ sound effect parameters and relative positions.

[0052] Step S102 can achieve coarse adjustment of the sound effects of the smart speaker.

[0053] S103: Obtain a spatial impact response of the audio played by the smart speaker according to the first EQ sound effect parameters.

[0054] Preferably, step S103 specifically includes the following steps:

[0055] S1031. Obtain an audio signal received by the MIC array of the smart speaker and played according to the first EQ sound effect parameter.

[0056] S1032: Extract a spatial impulse response h(t) according to the audio signal.

[0057] S104: Determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter.

[0058] Preferably, step S104 specifically includes the following steps:

[0059] S1041. Obtain a spatial frequency response according to the spatial impulse response.

[0060] S1042: Compare the spatial frequency response with a preset spatial frequency response to obtain a compensation factor at each frequency point.

[0061] S1041. Adjust the first EQ sound effect parameter according to the compensation factor to obtain the second EQ sound effect parameter.

[0062] Step S104 can achieve fine-tuning of the sound effects of the smart speaker.

[0063] After determining the second EQ sound effect parameter, the output audio signal is filtered using the second EQ sound effect parameter so that the output of the smart speaker achieves a preset sound effect in the current acoustic environment.

[0064] Embodiment 2

[0065] See also Figure 2 , Embodiment 2 of the present invention provides a method for adjusting the sound effect of an intelligent speaker, the method comprising:

[0066] S201. Obtain the position of the smart speaker in space.

[0067] S202. Determine a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters.

[0068] S203: Obtain a spatial impact response of the audio played by the smart speaker according to the first EQ sound effect parameters.

[0069] S204: Determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter.

[0070] S205: Adjust the second EQ sound effect parameter according to the user's input to obtain a third sound effect parameter.

[0071] Step S205 is an optional step. Specifically, the user can fine-tune the second EQ sound effect parameter through the application (APP) setting interface of the smart terminal (such as a smart phone) connected to the smart speaker to obtain the third EQ sound effect parameter. The user can also fine-tune the second EQ sound effect parameter through the UI interface on the smart speaker to obtain the third EQ sound effect parameter.

[0072] After determining the third EQ sound effect parameter, the output audio signal is filtered using the third EQ sound effect parameter so that the output of the smart speaker achieves a preset sound effect in the current acoustic environment.

[0073] S206. Adjust the volume of the smart speaker according to the distance between the user and the smart speaker.

[0074] Step S206 is an optional step. Specifically, it can detect from the captured image whether there is a person and whether the person is close to or far away from the smart speaker; and when the person is close to the smart speaker, the volume of the smart speaker is reduced, and when the person is far away from the smart speaker, the volume of the smart speaker is increased.

[0075] The method for obtaining the trend of the change in the distance between the user and the smart speaker in step S206 can be to judge by the change in size of the face or other parts of the human body in the pictures taken by the camera at two moments, or by the sensing signal of the infrared sensor on the smart speaker, or by the change in the depth of field of the picture taken by the camera on the smart speaker, which is not specifically limited in the present invention.

[0076] Embodiment 3

[0077] See also Figure 3 , Embodiment 3 of the present invention provides a smart speaker sound effect adjustment device 300, the device comprising:

[0078] The position acquisition module 301 is used to obtain the position of the smart speaker in space.

[0079] The first adjustment module 302 is used to determine a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters.

[0080] The spatial impulse response acquisition module 303 is used to obtain the spatial impulse response of the audio played by the smart speaker according to the first EQ sound effect parameters.

[0081] The second adjustment module 304 is configured to determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter.

[0082] Preferably, the position acquisition module 301 is specifically used to: obtain the spatial scene image taken by the dual cameras of the smart speaker; use a binocular ranging algorithm to process the image to obtain a spatial model and the position of the smart speaker in space.

[0083] Preferably, the first adjustment module 302 is specifically used to: obtain the relative position according to the spatial model and the position of the smart speaker in the space; obtain the first EQ sound effect parameter from a preset EQ sound effect parameter table according to the relative position; wherein the preset EQ sound effect parameter table includes a correspondence between multiple groups of EQ sound effect parameters and relative positions.

[0084] Preferably, the spatial impulse response acquisition module 303 is specifically used to: acquire the audio signal played according to the first EQ sound effect parameter and received by the MIC array of the smart speaker; and extract the spatial impulse response according to the audio signal.

[0085] Preferably, the second adjustment module 304 is specifically used to: obtain a spatial frequency response according to the spatial impulse response; compare the spatial frequency response with a preset spatial frequency response to obtain a compensation factor at each frequency point; adjust the first EQ sound effect parameter according to the compensation factor to obtain the second EQ sound effect parameter.

[0086] Embodiment 4

[0087] See also Figure 4 , Embodiment 4 of the present invention provides a smart speaker sound effect adjustment device 400, the device comprising:

[0088] The position acquisition module 401 is used to obtain the position of the smart speaker in space.

[0089] The first adjustment module 402 is used to determine a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters.

[0090] The spatial impulse response acquisition module 403 is used to obtain the spatial impulse response of the audio played by the smart speaker according to the first EQ sound effect parameters.

[0091] The second adjustment module 404 is configured to determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter.

[0092] The third adjustment module 405 is used to adjust the second EQ sound effect parameter according to the user's input to obtain a third sound effect parameter.

[0093] The volume adjustment module 406 is used to detect whether there is a person in the captured image and whether the person is close to or far away from the smart speaker; and when the person is close to the smart speaker, reduce the volume of the smart speaker, and when the person is far away from the smart speaker, increase the volume of the smart speaker.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes of the aforementioned method embodiments and will not be repeated here.

[0095] The embodiment of the present invention further discloses a computer program product, including computer program instructions, which are used to implement the methods of embodiments 1 to 5 when the instructions are executed by a processor.

[0096] The embodiment of the present invention further discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the methods of embodiments one to five are implemented.

[0097] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the methods, devices and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart and block diagram can represent a module, a program segment or a portion of a code, containing one or more computer executable instructions for implementing logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. It should also be noted that each box or combination of boxes in the block diagram and flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0098] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0099] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. The above embodiments are merely examples for illustration and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications may be made based on the above description, and these changes or modifications will be obvious and fall within the scope of protection of the present invention.

Claims

1. A method for adjusting sound effects of an intelligent speaker, characterized in that: The method comprises: Obtaining the position of the smart speaker in space; Determining a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters; Acquire an audio signal received by the MIC array of the smart speaker and played according to the first EQ sound effect parameter; extracting a spatial impulse response according to the audio signal; Determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter; Adjust the second EQ sound effect parameter according to the user's input to obtain a third EQ sound effect parameter; Adjusting the volume of the smart speaker according to a distance change trend between the user and the smart speaker, wherein the distance change trend includes the user moving away from the smart speaker or the user moving closer to the smart speaker; The determining of the second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter specifically includes: Obtaining a spatial frequency response according to the spatial impulse response; Comparing the spatial frequency response with a preset spatial frequency response to obtain a compensation factor at each frequency point; The first EQ sound effect parameter is adjusted according to the compensation factor to obtain the second EQ sound effect parameter.

2. The method of claim 1, wherein: The obtaining of the position of the smart speaker in space specifically includes: Obtaining a spatial scene image captured by the dual cameras of the smart speaker; The image is processed using a binocular ranging algorithm to obtain a spatial model and the position of the smart speaker in space.

3. The method of claim 2, wherein: The determining of the first EQ sound effect parameter according to the position specifically includes: Acquire a relative position according to the space model and the position of the smart speaker in the space; According to the relative position, obtaining the first EQ sound effect parameter from a preset EQ sound effect parameter table; The preset EQ sound effect parameter table includes a correspondence between multiple groups of EQ sound effect parameters and relative positions.

4. The method according to any one of claims 1 to 3, wherein: The method also includes: detecting whether a person exists and whether the person is close to or far away from the smart speaker from the captured image; and when the person is close to the smart speaker, reducing the volume of the smart speaker, and when the person is far away from the smart speaker, increasing the volume of the smart speaker.

5. An intelligent speaker sound effect adjustment device, characterized in that: The device comprises: A position acquisition module, used to obtain the position of the smart speaker in space; A first adjustment module, configured to determine a first EQ sound effect parameter according to the position, wherein the first EQ sound effect parameter is one of a plurality of preset groups of EQ sound effect parameters; A spatial impulse response acquisition module, used to acquire an audio signal played according to the first EQ sound effect parameter and received by the MIC array of the smart speaker, and extract a spatial impulse response according to the audio signal; A second adjustment module, configured to determine a second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter; A third adjustment module, used to adjust the second EQ sound effect parameter according to the user's input to obtain a third EQ sound effect parameter; A volume adjustment module, configured to adjust the volume of the smart speaker according to a distance change trend between the user and the smart speaker, wherein the distance change trend includes the user moving away from the smart speaker or the user moving closer to the smart speaker; The determining of the second EQ sound effect parameter according to the spatial impulse response and the first EQ sound effect parameter specifically includes: Obtaining a spatial frequency response according to the spatial impulse response; Comparing the spatial frequency response with a preset spatial frequency response to obtain a compensation factor at each frequency point; The first EQ sound effect parameter is adjusted according to the compensation factor to obtain the second EQ sound effect parameter.

6. A computer program product, comprising computer program instructions, which, when executed by a processor, are used to implement the smart speaker sound effect adjustment method as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, which, when executed, implements the smart speaker sound effect adjustment method as described in any one of claims 1-4.