CN113207059B

CN113207059B - Sound parameter determining method and system

Info

Publication number: CN113207059B
Application number: CN202110505712.9A
Authority: CN
Inventors: 陈玮; 张鲲鹏
Original assignee: Hansang Nanjing Technology Co ltd
Current assignee: Hansang Nanjing Technology Co ltd
Priority date: 2020-12-28
Filing date: 2020-12-28
Publication date: 2023-05-16
Anticipated expiration: 2040-12-28
Also published as: CN113115176B; CN113207060B; CN113207059A; CN112312278A; CN113194384A; CN113207060A; CN113207061A; CN113115177A; CN113207062A; CN113115176A; CN112312278B

Abstract

The embodiment of the specification discloses a training method for acoustic parameter configuration models, which comprises the following steps: obtaining a training sample, wherein the training sample at least comprises: one or more of a position of a target sound, a first distance and a first angle between a listening position and the target sound, a position of a placed object in a target space, a material of the placed object, a shape of the placed object, a parameter of the target sound, or an image containing the above information; obtaining a label corresponding to the training sample, wherein the label at least comprises one or more of the tone quality of the target sound or the parameters of the target sound; and training the acoustic parameter configuration model based on the training sample and the label corresponding to the training sample, and ending the training when the trained acoustic parameter configuration model meets the preset condition.

Description

Sound parameter determining method and system

Description of the division

The present application is a divisional application of chinese patent application CN 202011572703.3 entitled "an acoustic parameter determination method and system" filed on 12/28 th 2020.

Technical Field

The present disclosure relates to the field of sound, and in particular, to a method and system for determining acoustic parameters.

Background

With the rapid development of offline service industry, the application of sound equipment is becoming wider and wider. When the audio device is used, a user can obtain better listening experience by adjusting the audio parameters of the audio device. However, most speakers have only basic tuning functions, and various influencing factors, such as environmental factors, position and angle factors, etc., of the speaker are not considered in determining the speaker parameters. In addition, most users do not have the expertise to autonomously adjust acoustic parameters, and the specialized listening environment to accurately determine acoustic parameters. The determination of the acoustic parameters is not comprehensive enough and not accurate enough, and better sound effect is difficult to obtain, so that the listening experience of a user is affected.

Therefore, it is necessary to provide a method and a system for determining acoustic parameters, which improve the comprehensiveness and accuracy of acoustic parameter determination, improve the sound effect of the acoustic, and provide a high-quality listening experience for users.

Disclosure of Invention

One of the embodiments of the present specification provides an acoustic parameter determining method, including: obtaining a panoramic image of a target space in which a target sound is placed, wherein the target sound is provided with an LED lamp, and the panoramic image is obtained by shooting under the condition that the LED lamp is lighted; acquiring a listening position of the target space; analyzing the panoramic image, comprising: identifying the position of the target sound through identifying the shape or the position of the LED lamp of the target sound in the panoramic image; identifying a first distance and a first angle between the listening position and the target sound based on the listening position and the position of the target sound; identifying the position of a placed object in the target space, the size of the target space and wall materials in the target space; based on the analysis result of the panoramic image, determining the gain of the target sound comprises: and inputting the position of the target sound, the first distance and the first angle between the listening position and the target sound, the position of the placed object, the size of the target space and the wall surface material of the target space into a trained sound parameter configuration model, and outputting to obtain the gain of the target sound.

One of the embodiments of the present specification provides an acoustic parameter determination system, the system including: the first acquisition module is used for acquiring a panoramic image of a target space in which a target sound is placed, the target sound is provided with an LED lamp, and the panoramic image is shot under the condition that the LED lamp is lighted; the second acquisition module is used for acquiring the listening position of the target space; an analysis module for analyzing the panoramic image, the analysis module comprising: the first identification module is used for identifying the position of the target sound through identifying the shape or the position of the LED lamp of the target sound in the panoramic image; a second identifying module for identifying a first distance and a first angle between the listening position and the target sound based on the listening position and the position of the target sound; the third identification module is used for identifying the position of the placed object in the target space, the size of the target space and the wall surface material of the target space; a first determining module, configured to determine a gain of the target sound based on an analysis result of the panoramic image, including: and inputting the position of the target sound, the first distance and the first angle between the listening position and the target sound, the position of the placed object, the size of the target space and the wall surface material of the target space into a trained sound parameter configuration model, and outputting to obtain the gain of the target sound.

One of the embodiments of the present description provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement a method as above.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is an application scenario diagram of an audio conditioning system shown in accordance with some embodiments of the present description;

FIG. 2 is an exemplary flow chart of a method of determining acoustic parameters according to some embodiments of the present description;

FIG. 3 is an exemplary flow chart of a method of determining acoustic parameters according to further embodiments of the present description;

FIG. 4 is an exemplary flow chart for determining the gain of a target sound according to some embodiments of the present disclosure;

fig. 5 is a block diagram of an acoustic parameter determination system according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is an application scenario diagram of an audio conditioning system according to some embodiments of the present description. In an exemplary application scenario, the sound conditioning system 100 can include a server 110, a processor 120, a storage device 130, a user terminal 140, a network 150.

In some embodiments, the sound adjustment system 100 may be used to determine sound parameters. The sound conditioning system 100 can be applied to various off-line scenes using sound. Such as residential rooms, restaurants, cafes, malls, show stages, movie theatres, etc. The sound conditioning system 100 may determine optimal sound parameters of the sound by implementing the methods and/or processes disclosed herein to provide the user with the best quality listening effect and enhance the user's listening experience.

In some embodiments, the user terminal 140 may obtain multiple images of the scene and/or the listening position input by the user, and determine the optimal sound parameters of the sound after processing the images and the listening position by the server 110. Server 110 may obtain data from storage device 130 or save data to storage device 130 during processing, or may read data from other sources and output data to other target objects via network 150. In some embodiments, the processing operation of determining, at least in part, the acoustic parameters may be performed at the user terminal 140. Operations in this specification may be performed by processor 120 executing program instructions. The foregoing is merely for convenience of understanding, and the system may also be implemented in other possible operating modes.

In some embodiments, a storage device 130 may be included in server 110, user terminal 140, and possibly other system components.

In some embodiments, the processor 120 may be included in the server 110, the user terminal 140, and possibly other system components.

Server 110 may be used to manage resources and process data and/or information from at least one component of the present system or external data sources (e.g., a cloud data center). In some embodiments, the server 110 may be a single server or a group of servers. The server farm may be centralized or distributed (e.g., server 110 may be a distributed system), may be dedicated, or may be serviced concurrently by other devices or systems. In some embodiments, server 110 may be regional or remote. In some embodiments, server 110 may be implemented on a cloud platform or provided in a virtual manner. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

Processor 120 may process data and/or information obtained from other devices or system components. Processor 120 may execute program instructions to perform one or more of the functions described herein based on such data, information, and/or processing results. In some embodiments, processor 120 may include one or more sub-processing devices (e.g., single-core processing devices or multi-core processing devices). By way of example only, the processor 120 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), an editable logic circuit (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

Storage device 130 may be used to store data and/or instructions. Storage device 130 may include one or more storage components, each of which may be a separate device or may be part of another device. In some embodiments, the storage device 130 may include Random Access Memory (RAM), read Only Memory (ROM), mass storage, removable memory, volatile read-write memory, and the like, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state disks, and the like. In some embodiments, the storage device 130 may be implemented on a cloud platform.

Data refers to a digitized representation of information and may include various types such as sound data, binary data, text data, image data, video data, and the like. Instructions refer to programs that may control a device or apparatus to perform a particular function.

User terminal 140 refers to one or more terminal devices or software used by a user. In some embodiments, one or more users of user terminal 140 may be used, including users who directly use the audio listening service, as well as other related users. In some embodiments, the user terminal 140 may be one or any combination of mobile device 140-1, tablet computer 140-2, laptop computer 140-3, desktop computer 140-4, and the like, as well as other input and/or output enabled devices. In some embodiments, mobile device 140-1 may include a wearable device, a smart mobile device, and the like, or any combination thereof. In some embodiments, the smart mobile device may include a smart phone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, a hand-held terminal (POS), or the like, or any combination thereof. In some embodiments, desktop computer 140-4 may be a small computer, television, or the like.

In some embodiments, other mobile devices 140-1 having input and/or output capabilities may include sound control terminals disposed in public or home environments. In some embodiments, the user may refer to a home owner, an audio user, or other service requester.

The above examples are only intended to illustrate the broad scope of the user terminal 140 devices and not to limit the scope thereof.

Network 150 may connect components of the system and/or connect the system with external resource components. Network 150 enables communication between the various components and with other components external to audio conditioning system 100 to facilitate the exchange of data and/or information. In some embodiments, network 150 may be any one or more of a wired network or a wireless network. For example, the network 150 may include a cable network, a fiber optic network, a telecommunications network, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC), an intra-device bus, an intra-device line, a cable connection, and the like, or any combination thereof. The network connection between the parts can be in one of the above-mentioned ways or in a plurality of ways. In some embodiments, the network may be a point-to-point, shared, centralized, etc. variety of topologies or a combination of topologies. In some embodiments, network 150 may include one or more network access points. For example, network 150 may include wired or wireless network access points, such as base stations and/or network switching points 150-1, 150-2, …, through which one or more components entering and exiting sound conditioning system 100 may connect to network 150 to exchange data and/or information.

Fig. 2 is an exemplary flowchart of a sound parameter determination method according to some embodiments of the present description. As shown in fig. 2, the process 200 may be performed by the processor 120.

Step 210, an image of a target space in which a target sound is placed is acquired. In some embodiments, step 210 may be performed by the first acquisition module 510.

The target sound means a sound device of which parameters are to be determined. In some embodiments, the target sound may include one or more speakers, or sound devices arranged in various combinations. In some embodiments, the target sound may be a combination of one or more sounds in a home theater. For example, the target sound may include one or more of 2 front speakers, 2 rear speakers, 1 center surround speaker, 1 subwoofer speaker. Also for example, 5.1 sound.

The target space is the space where the scene of the target sound is placed. Such as a living room of a residence, a waiting area of a restaurant, a projection hall of a movie theater, etc.

In some embodiments, the image may be a plurality of images of the target space described above. Wherein at least two of the plurality of images may contain one or more identical elements. For example, a reference line containing the same object or a portion thereof and/or the same target space, etc.

Panoramic images refer to wide-angle images that exist in the form of photographs. The panoramic image may display information of the target space and/or objects therein. For example, the panoramic image may reflect information such as a placement position of the target sound in the target space, positions of other objects in the target space, and a size of the target space. In some embodiments, a processing device (e.g., processor 120) may analyze the above information of the panoramic image and determine parameters of the target sound based on the analysis results. For more details on determining parameters of the target sound according to the analysis result of the panoramic image, refer to fig. 3 and the related description thereof, and are not repeated here.

The first acquisition module 510 may acquire an image of a target space in which a target sound is placed in various ways. In some embodiments, the first obtaining module 510 may obtain, from the user terminal 140 via the network 150, an image of a target space in which the target sound is placed. For example, the user terminal 140 may capture an image by an image capturing device (e.g., a camera) for acquisition by the first acquisition module 510 in a network transmission manner. In some embodiments, the user may take multiple images of the target space in which the target sound is placed through the user terminal 140. Wherein at least two of the plurality of captured images may contain at least one identical element to facilitate calculation of the size of the target space from the plurality of images.

In some embodiments, the first obtaining module 510 may obtain an image of the target space in which the target sound is placed from the server 110. For example, the user may upload the captured image to the server 110 for acquisition by the first acquisition module 510. In some embodiments, the first acquisition module 510 may acquire an image of a target space in which the target sound is placed from the storage device 130. For example, the user may store the captured image in the storage device 130 for retrieval by the first retrieval module 510. In some embodiments, the first acquisition module 510 may acquire images pre-stored in a memory space of the network 150. For example, the first acquisition module 510 may acquire images in cloud storage.

Step 220, obtaining the listening position of the target space. In some embodiments, step 220 may be performed by the second acquisition module 520.

Listening position refers to the position where the user is listening to the target sound. The listening position may be one or more. In some embodiments, the listening position may be a real-time position of the user in the target space. The real-time location may be a coordinate location where the user is located in a spatial coordinate system at the current time. By way of example only, where the first moment of time has a coordinate position of a user in the target space and the second moment of time has a coordinate position of B in the target space, then both the real-time position a and the real-time position B are listening positions of the user.

In some embodiments, the listening position may be a common position of the user in the target space. The common location may be a location where the user is often present in the target space. Taking home theater scenes as an example, the common location may be a sitting location of the user. Taking a restaurant service scene as an example, the common location may be a location of the user in a restaurant waiting area, or may be a location of the user in a dining area of the restaurant. It should be noted that the object position used by the user in the above scene may also be determined as the listening position. For example, a coordinate position at a certain sofa in a home theater, a restaurant waiting area, or a certain chair in a restaurant dining area is determined as a listening position to improve the accuracy of determining the listening position. In some embodiments, the second acquisition module 520 may acquire the listening position of the target space in a variety of ways. In some embodiments, the processor 120 may obtain the listening position of the target space from an image (e.g., panoramic image) stored by the storage device 130. For example, the processor 120 may determine one or more common locations of the user in the target space from the panoramic image and determine the common locations as listening locations in the target space. As another example, the processor 120 may automatically identify the listening position by analyzing layout information of the panoramic image, or analyzing the position of certain specific items (e.g., tables, seats, etc.) in the panoramic image. For more details on the layout information of the target space, reference may be made to step 230 and the description thereof, and will not be repeated here.

In some embodiments, the second acquisition module 520 may also acquire the listening position of the target space through the user terminal 140. For example, the second obtaining module 520 may obtain the real-time location of the user terminal 140 in the target space from the server 110 through the network 150, and determine the real-time location as the listening position of the target space. As another example, the second acquisition module 520 may acquire the listening position entered by the user terminal 140 or clicked in the application interface from the server 110 via the network 150. Taking a home theater scene as an example, a user may obtain a prompt for capturing an image through an application program of the user terminal 140, capture one or more images of the current scene through a camera of the user terminal 140, upload the captured images to the application program, and input or click at least one listening position in the application program for the user to obtain according to the images.

Step 230, identifying layout information of the target space based on the image. In some embodiments, step 230 may be performed by analysis module 530.

The layout information refers to object-related information laid out in the target space. In some embodiments, the layout information may include, but is not limited to, a location of the target sound, a distance between the listening location and the target sound, a location of a placeholder in the target space, a material of the placeholder, a shape of the placeholder, a size of the target space, a standing wave of the target space, reverberation of the target space, sensitivity of the target sound, a gain formula of the target sound, and the like.

In some embodiments, the analysis module 530 may identify layout information of the target space in a variety of ways. In some embodiments, the analysis module 530 may identify layout information of the target space through a machine learning model and/or in conjunction with a correlation algorithm. Among other things, the machine learning model may include, but is not limited to, convolutional neural network (Convolutional Neural Networks, CNN), long Short-Term Memory (LSTM) model, and the like. The correlation algorithm may include, but is not limited to LayoutNet, flat2Layout, E2P, geometric algorithm, depth information algorithm, and the like. For more details on identifying layout information of the target space, reference may be made to fig. 3 and its related description, which are not repeated here.

The position of the target sound is the placement position of the target sound in the target space. In some embodiments, the analysis module 530 may identify the location of the target sound by image recognition techniques. In some embodiments, the analysis module 530 may extract a feature of the target sound from the image by convolving the neural network (Convolutional Neural Networks, CNN), where the feature is the location of the target sound in the image. For more details regarding the location of the identified target sound, reference may be made to fig. 3 and its associated description, which are not repeated here.

In some embodiments, the analysis module 530 may identify the distance between the listening position and the target sound in a variety of ways. In some embodiments, the analysis module 530 may identify the distance between the listening position and the target sound by image recognition techniques. In some embodiments, the analysis module 530 may extract features of the target sound and the listening position from the scene image through a convolutional neural network (Convolutional Neural Networks, CNN), determine a baseline between the two according to the features, and determine an actual length of the baseline corresponding in the real scene by combining the proportions of the images, and determine the actual length as a distance between the listening position and the target sound.

In some embodiments, a processing device (e.g., processor 120) may calculate the difference in coordinates of the two in the target space to derive the distance between the listening position and the target sound. For more details on identifying the distance between the listening position and the target sound, reference may be made to fig. 3 and its associated description, which is not repeated here.

The placed object refers to an object placed in a target space, such as furniture or decorations such as sofas, tables and chairs, curtains, hanging pictures, and the like. In some embodiments, the analysis module 530 may identify the location of the placements by image recognition techniques. In some embodiments, the analysis module 530 may extract a feature of the placeholder from the image by convolving the neural network (Convolutional Neural Networks, CNN), the location of the feature in the image being the location of the placeholder. In some embodiments, the convolutional neural network may extract the features of the placements through a preset algorithm. For example, SSD algorithm (Single Shot MultiBox Detector).

The material, shape and size of the placements may influence the parameters of the target sound. For example, a placement of sound absorbing material can absorb sound waves of the target sound, and thus reduce sound parameters such as sound quality and volume of the target sound. For another example, irregularly shaped or large sized placements may obstruct the sound wave transmission of the target sound, thereby weakening sound parameters such as surround sound and stereo sound of the target sound.

Standing waves are composite waves in which two sine waves having the same wavelength, period, frequency and wave speed travel in opposite directions and interfere with each other. Standing waves in the target space attenuate some of the sound waves emitted by the target sound, thereby reducing the listening experience of the user. The standing wave of the target space is related to the size of the target space. For example, the larger the size of the target space, the smaller the critical frequency of the standing wave of the target space, and the smaller the influence of the standing wave on the target sound.

Reverberation refers to the acoustic phenomenon in which sound continues after sound source articulation ceases. The reverberation of the target space affects the sound quality of the target sound. The reverberation of the target space is related to the size of the target space and the material of the target space.

The sensitivity of the target sound is the magnitude of the signal voltage at the input when the power amplifier of the sound reaches full power output. The greater the signal voltage, the lower the sensitivity. The sensitivity of sound is typically used to reflect the sound size of the subjective perception of the human ear. The sensitivity of the sound is high, the user feels that the sound of the sound is larger, but the tone quality of the sound is damaged due to the excessively high sensitivity, so that the sensitivity of the sound is controlled in a reasonable range to bring high-quality listening experience to the user.

The gain formula of the target sound equipment refers to a formula used in the process of determining the gain of the target sound equipment. In some embodiments, the gain formula for the target sound may be a maximum voltage capacity formula for determining the target sound. Wherein the target sound can be protected by determining the maximum voltage capacity of the target sound.

Step 240, determining parameters of the target sound based on the layout information, wherein the parameters comprise gains of the target sound. In some embodiments, step 240 may be performed by the first determination module 540.

The gain of the target sound is the signal amplification of the target sound. For example, a smaller output voltage is amplified by an amplifier to become an amplification ratio of a larger output voltage.

In some embodiments, the first determining module 540 may determine a plurality of candidate gains of the target sound according to the layout information, and determine the gain of the target sound from the plurality of candidate gains. The gain of the target sound can determine that the target sound obtains better tone quality improvement under the same volume. In some embodiments, the gain of the target audio may be determined, adjusted by a corresponding Equalizer (EQ).

In some embodiments, the parameters of the target sound may include, but are not limited to, the gain of the target sound, the output power of the target sound, the delay of the target sound, and the like. In some embodiments, the first determination module 540 may determine the parameters of the target sound in a variety of ways. In some embodiments, the first determination module 540 may determine the parameters of the target sound based on a machine learning model. In some embodiments, the first determination module 540 may determine the parameters of the target sound by the initial parameters of the target sound. In some embodiments, the initial parameters of the target sound may include, but are not limited to, one or more of a gain of the target sound, an output power of the target sound, and a delay of the target sound. In some embodiments, the first determination module 540 may determine the parameters of the target sound based on the initial parameters of the target sound and/or the analysis result of the panoramic image.

For more details on determining the parameters of the target sound, reference may be made to fig. 3 and 4 and their related descriptions, which are not repeated here.

The layout information of the target space affects the parameters of the target sound. For example, if there are a large number of things placed around the target sound, the sound wave transmission of the target sound is hindered, and the listening effect of the user is affected. Therefore, the parameters of the target sound can be more comprehensively and accurately determined by identifying the layout information of the target space, so that a better listening effect is provided for the user.

Fig. 3 is an exemplary flowchart of an acoustic parameter determination method according to further embodiments of the present description. As shown in fig. 3, the process 300 may be performed by the processor 120.

Step 310, a panoramic image of a target space in which a target sound is placed is acquired. In some embodiments, step 310 may be performed by the first acquisition module 510.

In some embodiments, the target sound has one or more LED lights. The LED lamp may be a function indicator lamp of the target sound, or may be an appearance decorative lamp of the target sound.

In some embodiments, the panoramic image is captured with the LED lights illuminated. The LED lamp in the on state can be not influenced by the light brightness degree in the target space, so that the display effect of higher resolution and clear outline in the panoramic image is achieved. Thus, it may help the processing device (e.g., processor 120) better identify the location of the target sound, facilitating subsequent overall, accurate determination of parameters of the target sound.

In some embodiments, the first acquisition module 510 may acquire a plurality of images of the target space from the mobile terminal. The mobile terminal may be a user terminal 140. In some embodiments, the mobile terminal may capture multiple images of the target space through an image capture device (e.g., a camera). In some embodiments, the multiple images may come from different locations in the target space. For example, the user may take a plurality of images containing the same element of the target space at different positions in the target space, or select one or several images with the best shooting quality from the images for the first acquisition module 510 to acquire. In some embodiments, multiple images may be taken from the same location in the target space. For example, a user may take multiple images at different angles at the same location in the target space for acquisition by the first acquisition module 510.

In some embodiments, the first obtaining module 510 may obtain the plurality of images stored by the mobile terminal from the storage device 130 or from a cloud storage space through the network 150. In some embodiments, the first acquisition module 510 may obtain the panoramic image based on a plurality of images. In some embodiments, the first obtaining module 510 may perform permutation and combination on the multiple images of the target space through an image processing device (for example, the processor 120), and splice the multiple images meeting the conditions in the permutation and combination, to obtain a panoramic image of the target space.

In some embodiments, the first obtaining module 510 may obtain the panoramic image photographed or stored by the mobile terminal from the storage device 130 or from the cloud storage through the network 150.

For more details on acquiring panoramic images, see fig. 2 and its associated description, which are not repeated here.

Step 320, obtaining the listening position of the target space. In some embodiments, step 320 may be performed by the second acquisition module 520.

In some embodiments, the second acquisition module 520 may acquire the listening position entered by the user from the mobile terminal. In some embodiments, the listening position entered by the user to the mobile terminal may comprise a plurality of types. For example, the user's usual listening position clicks on a listening position or a favorite listening position, etc. In some embodiments, the listening position input by the user to the mobile terminal may be one or a plurality of listening positions. The types of the plurality of listening positions can be the same or a plurality of listening positions.

In some embodiments, the second acquisition module 520 may acquire the listening position of the user input from the storage device 130, or from a cloud storage space through the network 150. In some embodiments, the processing device (e.g., processor 120) may record the listening position entered by the user to the mobile terminal and store it in the storage device 130 in the form of historical data from which the second acquisition module 520 may acquire the listening position entered by the user. For more details on acquiring a listening position entered by a user from a mobile terminal, reference may be made to fig. 2 and its related description, which are not repeated here.

As can be seen from the above description, the second obtaining module 520 may obtain multiple listening positions and multiple listening positions input to the mobile terminal by the user more quickly without identifying the panoramic image, so that the sound parameters can be more comprehensively and more accurately determined by the listening positions, and a better listening experience is provided for the user.

And step 330, analyzing the panoramic image. In some embodiments, step 330 may be performed by analysis module 530. In some embodiments, step 330 may further comprise the following steps.

Step 331, identifying the position of the target sound by identifying the shape or position of the LED lamp of the target sound in the panoramic image. In some embodiments, step 331 may be performed by the first identification module 531.

The LED lamp of the target sound can help the first recognition module 531 to accurately recognize the target sound from the panoramic image of the target space. In some embodiments, the first recognition module 531 may recognize the shape of the LED lamp of the target sound. In some embodiments, the first recognition module 531 may recognize the shape of the LED lamp according to preset parameters of the LED lamp. The preset parameters may include the size of the pattern LED lamp of the LED lamp, the color of the LED lamp, and the like. In some embodiments, the processing device (e.g., the processor 120) may extract features of the LED lamp from the panoramic image based on preset parameters of the LED lamp, and the first recognition module 531 may recognize the shape of the LED lamp according to the features. In some embodiments, a processing device (e.g., processor 120) may identify the shape of the LED lamp through a machine learning model based on the panoramic image of the target space. In some embodiments, the first identification module 531 may identify the location of the LED lights of the target sound. In some embodiments, the processing device (e.g., the processor 120) may extract features of the plurality of LED lights from the panoramic image, and the first identification module 531 may obtain a baseline formed by the connection of the plurality of features and determine the location of the LED lights in the panoramic image based on the baseline.

In some embodiments, the first identification module 531 may identify the second distance between the target sound and the photographer of the panoramic image by identifying the shape or position of the LED lights of the target sound in the panoramic image. The second distance is the relative distance between the photographer and the target sound equipment. In some embodiments, a processing device (e.g., processor 120) may determine a location of the photographer from the panoramic image and determine a baseline formed by the location being connected with the location of the LED lights. In some embodiments, the first identification module 531 may determine the length of the second distance from the baseline in conjunction with the scale of the panoramic image. By way of example only, the ratio of panoramic images is 1:20, the length of the base line is 5cm. Thus, the second distance is 100cm in length.

In some embodiments, the first identification module 531 may determine the location of the target sound based on the second distance. For example only, assume that the photographer's position coordinates are the origin of coordinates and the second distance is 100cm. In this way, the first identifying module 531 may calculate the coordinates of the target sound according to the relative distance, which indicates that the relative distance between the target sound and the position of the photographer is 100cm, and may further calculate the position of the target sound.

Because the shape and the size of the LED lamp are simpler than those of the target sound, and the outline of the LED lamp in the panoramic image in the lighting state can be clear and the display resolution is higher according to the above, the position of the target sound can be identified more quickly and accurately by identifying the LED lamp of the target sound, so that the efficiency and the accuracy of the subsequent target sound parameter determination can be improved.

Step 332, based on the listening position and the position of the target sound, identifying a first distance and a first angle between the listening position and the target sound. In some embodiments, step 332 may be performed by the second identification module 532.

In some embodiments, the second recognition module 532 may determine a baseline for the connection of the listening position and the target sound in the panoramic image based on the position of the listening position and determine the first distance based on the length of the baseline in combination with the scale of the panoramic image. When there are a plurality of target sounds, the second identifying module 532 may determine a plurality of first distances between the listening position and the target sound according to a baseline that connects the listening position and the plurality of target sounds in the panoramic image.

For more details regarding the identification of the first distance, reference may be made to the identification of the second distance in step 331, which is not described in detail herein.

In some embodiments, the second identification module 532 may identify a first angle between the listening position and the target sound by an off-axis curve. The off-axis curve refers to the frequency response curve of the sound when off-axis. The axis is the connecting line between the sound and listening positions at 0 deg. The off-axis curves may reflect the quantized representation of the sound. In some embodiments, the off-axis curve may be preset. Specifically, the data can be obtained by measuring the target sound in advance, and the off-axis curve is drawn based on the obtained data. For example, an off-axis curve is drawn for sound output conditions within 20-22kHz with the output sound pressure level and frequency as axes.

It will be appreciated that the second identifying module 532 may identify the sound pressure level of the target sound output from the listening position at a specific frequency (e.g., 20-22 kHz), and then compare the output sound pressure level according to a preset off-axis curve, so as to identify the first angle between the listening position and the target sound.

When the target sound is at an angle of 0 ° to the listening position (referred to as on-axis) due to the directivity of the high-frequency signal, the high-frequency signal is heard more clearly and more accurately by the user than by other angles (off-axis). That is, the larger the off-axis angle, the less the sense of the amount of the treble part emitted from the sound. Thus, the equalizer for off-axis, i.e., off-axis EQ, can be preset based on the above attributes.

In some embodiments, a processing device (e.g., processor 120) may determine the gain of the target sound by off-axis EQ. Specifically, the off-axis EQ can adjust the treble emitted by the target sound under different off-axis angles to ensure that the sound quality of the off-axis target sound is as close to the on-axis state as possible.

Step 333, identifying the position of the placed object in the target space, the size of the target space, and the wall surface material of the target space. In some embodiments, step 333 may be performed by third identification module 533.

In some embodiments, third identification module 533 may identify the location of the placeholder based on features of the placeholder extracted by the processing device (e.g., processor 120). For more details on identifying the location of the placements, see fig. 2 and its associated description, which are not repeated here.

In some embodiments, the third identifying module 533 may also identify the material, shape, and size of the placements through preset parameters of the placements. The preset parameters of the placements may include material parameters, shape parameters, and size parameters of the placements. In some embodiments, the processing device (e.g., the processor 120) may extract a feature of the placeholder from the panoramic image, and the third identification module 533 may compare the feature with a preset parameter and determine a material, shape, and size of the placeholder according to the comparison. For example only, the third identifying module 533 may compare the characteristic of the placed object with the material parameter of the placed object, and if the characteristic is wood, it indicates that the material of the placed object is wood.

In some embodiments, the third identification module 533 may identify the size of the target space. The size of the target space may be the volume of the target space or the surface area of all walls, floors in the target space. Specifically, the third identifying module 533 may identify a plurality of baselines of the panoramic image, calculate the actual length of each of the baselines according to the proportion of the panoramic image, and calculate the size of the target space according to the actual length of each of the baselines. For more details on the baseline, see the relevant description below regarding baseline and target spatial dimensions, which are not repeated here.

In some embodiments, the third identification module 533 may identify wall coverings of the target space. Taking the target space as a single room as an example, the wall surface material of the target space may be surface materials of six wall surfaces in the target space, for example, paint, coating, and the like. Specifically, the third identifying module 533 may compare the elements corresponding to the wall material in the panoramic image with the features of the panoramic image, and identify the wall material in the target space according to the obtained comparison result. The panoramic image features may be features of wall coverings pre-extracted from the panoramic image, such as pixels of different wall coverings, feature vectors, etc.

It should be noted that, both the size of the target space and the wall material of the target space may affect the reverberation of the target space, and further details regarding the reverberation of the target space may be found in the following embodiments and the related descriptions thereof, which are not repeated herein.

Through the position, the material, the shape and the size of the object to be placed, the size of the target space and the wall surface material of the target space are identified, and a plurality of influence factors of the information on the target acoustic parameters can be analyzed by combining the information, so that the comprehensiveness and the accuracy of acoustic parameter determination can be improved.

In some embodiments, analyzing the panoramic image may further include: at least one of a size of the target space, a standing wave of the target space, reverberation of the target space, sensitivity of the target sound, and a gain formula of the target sound is identified. In some embodiments, the identification operations of the size of the target space, the standing wave of the target space, the reverberation of the target space, the sensitivity of the target sound, the gain formula of the target sound, and the like may be performed by the third identification module 533. For example, a placement of sound absorbing material can absorb sound waves of the target sound, and thus reduce sound parameters such as sound quality and volume of the target sound. For another example, irregularly shaped or large sized placements may obstruct the sound wave transmission of the target sound, thereby weakening sound parameters such as surround sound and stereo sound of the target sound.

In some embodiments, the third identification module 533 may identify the size of the target space. In some embodiments, a processing device (e.g., processor 120) may extract keypoints of a plurality of target spaces from a panoramic image of the target space. The key point may be a connection point of a boundary line between a wall surface of the target space and the ground. In some embodiments, the third identifying module 533 may identify a baseline formed by connecting a plurality of keypoints according to the plurality of keypoints, and calculate the size of the target space according to the size of the baseline and the ratio of the panoramic image. By way of example only, assuming that one of the plurality of baselines is 20cm in length, the ratio of panoramic images is 1:5, the size of the target space corresponding to the base line is 100cm.

In some embodiments, the third identification module 533 may identify standing waves of the target space. In some embodiments, the third identification module 533 may identify the standing wave of the target space according to the size of the target space. In some embodiments, the calculation formula of the standing wave frequency can be expressed as:

wherein F is ₁ For the first-order standing wave frequency in the length direction of the target space, F ₂ For the first-order standing wave frequency in the width direction of the target space, F ₃ A first-order standing wave frequency L in the target space height direction ₁ For the length of the target space, L ₂ For the width of the target space, L ₃ V is the propagation speed of sound emitted by a sound source in the target space, i.e., the speed of sound, which is the height of the target space.

It should be noted that, since the corresponding standing wave frequency needs to be calculated by the sound velocity V in the formula (1). Thus, when a sound source is presentWhen the sound is completely shielded by the placed object, L in the formula (1) is needed ₁ Defined as the distance of the sound source from the object placed.

The reverberations of the target space may be represented by T60 reverberations. T60 reverberation refers to the time required for sound to decay by 60dB when it suddenly stops after reaching steady state. In some embodiments, the measurement formula for T60 reverberation of the target space can be expressed as:

where V denotes the size (volume) of the target space, m denotes the air attenuation coefficient, S denotes the surface area of the target space, and α denotes the average sound absorption coefficient.

In some embodiments, the third identification module 533 may identify reverberation of the target space. From equation (2), it can be known that the reverberation of the target space is related to the volume, surface area and texture of the target space. In some embodiments, the processing device (e.g., the processor 120) may obtain the size and texture of the target space according to the foregoing steps, and the third identifying module 533 may estimate the reverberation of the target space according to the foregoing information of the target space, so as to determine the gain of the target sound through the bass equalizer.

In some embodiments, the third identification module 533 may identify the sensitivity of the target sound. In some embodiments, the third identifying module 533 may identify the sensitivity of the target sound according to a preset sensitivity parameter. The preset sensitivity parameters may include a maximum voltage capacity and a voltage gain of the target sound. In some embodiments, the processing device (e.g., the processor 120) may extract a characteristic of the target sound, e.g., a model of the target sound, and the third identification module 533 may determine a preset sensitivity parameter for the target sound based on the characteristic. For example, a preset sensitivity parameter may be selected where the maximum voltage capacity is equal or closest. In some embodiments, the third identifying module 533 may obtain the sensitivity of the target sound according to a preset sensitivity parameter in combination with a sensitivity calculation formula. In some embodiments, the calculation formula for sensitivity can be expressed as:

where V' denotes the sensitivity of the target sound, V denotes the maximum voltage capacity of the target sound, and a denotes the voltage gain. Typically, the sensitivity of the target sound is between 0.775V and 1.5V.

The gain formula of the target sound equipment refers to a formula used in the process of determining the gain of the target sound equipment. In some embodiments, the gain of the target sound may be a maximum voltage capacity formula of the target sound. The target sound can be protected by determining the maximum voltage capacity of the target sound. The maximum voltage capacity of the target sound can be obtained according to the maximum power and the load impedance of the target sound, and the corresponding gain formula can be expressed as follows:

V＝W×Ω (4)

Where V denotes the maximum voltage capacity of the target sound, W denotes the maximum power of the target sound, and Ω denotes the load impedance of the target sound.

In some embodiments, the third identification module 533 may identify a gain formula of the target sound. In some embodiments, the third identification module 533 may obtain the gain formula of the target sound from the storage device 130 or from the server 110 via the network 150.

By identifying the plurality of information related to the target space and the target sound, a plurality of factors affecting the target sound parameters can be analyzed in combination with the information, so that the comprehensiveness and accuracy of sound parameter determination can be improved.

And step 340, determining the gain of the target sound based on the analysis result of the panoramic image. In some embodiments, step 340 may be performed by the first determination module 540.

In some embodiments, the parameters of the target sound may include, but are not limited to, the gain of the target sound, the output power of the target sound, the delay of the target sound, and the like.

In some embodiments, the first determination module 540 may determine the parameters of the target sound through a machine learning model. In some embodiments, multiple images or panoramic images of the target space may be input to the machine learning model, outputting parameters that result in a better target sound. In some embodiments, a processing device (e.g., processor 120) may obtain the original parameters of the target sound stored in storage device 130 and evaluate the sound quality of the target sound at the original parameters by an auxiliary device or program (e.g., a sound quality evaluation application) to determine the optimized parameters of the target sound.

In some embodiments, the parameters of the target sound may also be determined by preset parameters of the target sound. For more details on determining the parameters of the target sound through the preset parameters of the target sound, refer to fig. 4 and the related description thereof, and are not repeated here.

In some embodiments, the first determination module 540 may determine the gain of the target sound through a machine learning model. In some embodiments, the machine learning model may be a trained acoustic parameter configuration model. In some embodiments, the acoustic parameter configuration model may include, but is not limited to, convolutional neural network (Convolutional Neural Networks, CNN), long Short-Term Memory (LSTM) model, and the like. In some embodiments, the input of the acoustic parameter configuration model may be one or more of a location of the target acoustic, a first distance between the listening position and the target acoustic, a first angle, a location of the placements, a type of the placements, a shape of the placements, a material of the placements, etc., and the output may be a parameter (e.g., gain) of the target acoustic. In some embodiments, the input to the acoustic parameter configuration model may also be an image containing the information described above. Wherein the above-mentioned target sound information can be obtained by a processing device (e.g., processor 120) in an image recognition method.

In some embodiments, the acoustic parameter configuration model may be trained based on a plurality of labeled training samples. Specifically, a training sample with a label is input into the acoustic parameter configuration model, and parameters of the acoustic parameter configuration model are updated through training.

In some embodiments, the training sample may include a location of the target sound, a first distance between the listening location and the target sound, a first angle, a location of the placeholder, a material of the placeholder, a shape of the placeholder, parameters of the target sound, or an image comprising the foregoing, or the like, or a combination thereof.

In some embodiments, the training samples may be obtained by an auxiliary device. In some embodiments, the auxiliary device may be an automated device. Such as robotic arms, carts, etc. In some embodiments, the auxiliary device may obtain training samples in a variety of ways. For example, the auxiliary device may change the position of the target sound, the first distance between the listening position and the target sound, the first angle, the position of the placement by moving the target sound, the listening device, or the placement. For another example, the auxiliary device may replace the type, shape and/or material of each of the placements. For another example, the auxiliary device may automatically set or adjust the parameters of the target sound according to the data, so as to obtain the parameters of the plurality of target sound. So that the auxiliary device can acquire a large number of training samples through the above-described operations.

In some embodiments, the tag may be the sound quality of the target sound or a parameter of the target sound. In some embodiments, the timbre of the target sound may be represented by a corresponding score. Wherein, the higher the score is, the better the tone quality of the corresponding target sound. In some embodiments, the parameter of the target sound may be a plurality of parameter values of the target sound that are automatically set. The parameter values may be automatically set according to the training samples.

In some embodiments, the tag may be obtained by a listening device (e.g., a simulated user system) having scoring functionality. In some embodiments, the listening device may automatically score the quality of the target sound by receiving the sound emitted by the target sound. In some embodiments, the listening device may screen the tag, and use the sound quality of the target sound or the parameter of the target sound that meets the preset condition as the tag of the corresponding training sample. In some embodiments, the preset condition may be the sound quality of the target sound, or the sound quality corresponding to the parameter of the target sound is greater than a preset threshold. In some embodiments, the listening device may acquire, as the tag, the sound quality of the target sound conforming to the preset condition. For example, the listening device obtains that the sound quality of the target sound in the current training sample is 95 minutes, and the preset threshold is 90 minutes, so that the sound quality of the target sound meets the preset condition, and the target sound quality can be used as a label of the corresponding training sample. In some embodiments, the listening device may acquire, as the tag, a parameter of the target sound that meets the preset condition. For example, the auxiliary device may acquire a plurality of sets of training samples, automatically set a plurality of different parameters of the target sound for each set of training samples, and the listening device acquires the sound quality score of the target sound corresponding to the plurality of different parameters, and uses the parameter of the target sound with the sound quality score exceeding the preset threshold as the label of the corresponding training sample.

In some embodiments, the acoustic parameter configuration model may be trained to update model parameters by various methods based on the samples described above. For example, training may be based on a gradient descent method.

In some embodiments, training is ended when the trained acoustic parameter configuration model satisfies a preset condition. The preset condition may be that the loss function result converges or is smaller than a preset threshold value, etc.

According to the description, the position of the target sound, the first distance between the listening position and the target sound, the first angle, the position of the placed object, the size of the target space, the wall surface materials of the target space and the like are considered when the parameters of the target sound are determined, so that the accuracy and the comprehensiveness of the determination of the parameters of the target sound are improved, and the listening experience of a user is improved.

In some embodiments, the first determination module 540 may determine the output power of the target sound and/or the delay of the target sound based on the analysis result of the panoramic image.

The output power of the target sound equipment refers to the rated power of the target sound equipment when in use. The output power of the target sound can determine the maximum sound intensity of the target sound. In some embodiments, the first determining module 540 may determine the output power of the target sound based on the analysis result of the panoramic image. In some embodiments, the analysis results of the panoramic image may include a target The size of the space. The first determining module 540 may determine the optimal output power of the target sound according to the size of the target space in combination with the gain formula of the target sound. In some embodiments, the gain formula of the target sound may be an optimal correspondence between the volume of the target space and the output power of the target sound. For example, when the volume of the target space is 20m ³ In this case, the first determining module 540 may determine the output power of the optimal target sound to be 60W according to the optimal correspondence.

The delay of the target sound is the delay of the user receiving the sound emitted by each sound. The stereo quality of the target sound can be improved by proper time delay. For example, when the delay amount of two sound sources is 5ms to 35ms, the human ear can only feel the existence of one sound source ahead; when the delay amount of the sound sources is 30ms to 50ms, the human ear can roughly distinguish the existence of the two sound sources; when the delay amount of the sound source is more than 50ms, the human ear can feel that two sound sources exist simultaneously. The smaller the delay of the target sound, the softer the tone quality of the target sound; the larger the delay of the target sound, the stronger the tone quality stereo surround of the target sound. In some embodiments, the first determination module 540 may determine the delay of the target sound based on the listening effect requested by the user. For example, when the user requires a sound quality with a strong stereoscopic effect, the first determining module 540 may determine a delay of a larger target sound within a reasonable range.

The parameters of the target sound can be reasonably adjusted by determining the output power of the target sound and the delay of the target sound, so that the comprehensiveness of sound parameter determination is improved, and the listening experience of a user is improved.

In some embodiments, the first determination module 540 may determine the gain of the target sound based on the first distance or the second distance. Taking the first distance between the listening position and the 5.1 sound as an example, the first distances between the listening position and the five sound boxes of the 5.1 sound are respectively a ₁ 、a ₂ 、a ₃ 、a ₄ 、a ₅ . In some embodiments, the average value of the first distance may be expressed as:

in some embodiments, the gains of the five speakers may be expressed as:

wherein a may be a ₁ To a ₅ Any one of them.

In some embodiments, the gain may be adjusted by an equalizer or dynamic equalizer of the target sound to determine parameters of the target sound.

Step 350, obtaining preset parameters of at least one sound in the target sound. In some embodiments, step 350 may be performed by the third acquisition module 550.

The preset parameters are parameters of preset target sound equipment. In some embodiments, the preset parameters may be preferred acoustic parameters. For example, the delay of the target sound may be between 5ms and 50ms, and if the sound quality stereo surround of the target sound is strong, the delay of the target sound may be between 30ms and 50ms. In some embodiments, the preset parameter may be an end point value of a parameter adjustable range of the target sound. For example, when the delay of the target sound is adjustable in size between 30ms and 50ms, the preset parameter may be that the delay of the target sound may be 30ms or 50ms.

In some embodiments, the third obtaining module 550 may obtain the preset parameters of the target space from the storage device 130, or from the cloud storage space through the network 150. In some embodiments, the third obtaining module 550 may obtain preset parameters of the target sound manually input by the user from the user terminal 140.

In some embodiments, the preset parameters may include a preset gain of the at least one sound. For example, a sensitivity gain of the target sound, an output power gain of the target sound, and the like.

Step 360, determining a target position of the at least one sound equipment based on the listening position and the preset parameters. In some embodiments, step 360 may be performed by the second determination module 560.

In some embodiments, the preset parameter may be a delay of the target sound. In some embodiments, the processing device (e.g., processor 120) may obtain a delay of the target sound at a listening position, and the second determination module 560 may determine the target position or an optional range of target positions for at least one sound based on the delay of the target sound. For example, when the delay of the target sound is greater than 50ms, the delay of the target sound is excessively large, which may generate an echo effect affecting the sound quality of the target sound, and the second determining module 560 may reduce the distance between at least one sound and the other sound, so as to reduce the overall delay of the target sound.

In some embodiments, the preset parameter may be a gain of the target sound. In some embodiments, the processing device (e.g., processor 120) may obtain the gain of the target sound at a listening position, and the second determination module 560 may determine the target position or an optional range of target positions for at least one sound based on the gain of the target sound. For example, when the gain of the target sound is a thousand-fold amplification gain of the output voltage of the target sound through 3 20db amplifiers, the user may evaluate the sound quality of the target sound through an auxiliary device or system (e.g., a sound quality evaluation application), and the second determination module 560 may increase the distance of at least one sound from other sounds to further increase the surround sound quality of the target sound.

According to the above description, when the parameter of the target sound reaches the optimal value, the optimal value or the end value of the adjustable range, the listening experience of the user can be further improved by changing the position of the target sound, so that the accuracy and the diversity of sound parameter determination are improved.

Fig. 4 is an exemplary flow chart for determining the gain of a target sound according to some embodiments of the present description. The process 400 may be performed by the processor 120.

Step 410, obtaining initial parameters of the target sound equipment.

The initial parameters may be default parameters of the target sound. In some embodiments, the initial parameters may be empirically set. In some embodiments, the initial parameters may include initial parameters of the target sound. For example, an initial gain of the target sound, an initial output power of the target sound, an initial delay of the target sound, and the like.

In some embodiments, the processor 120 may retrieve the initial parameters from the storage device 130 or the user terminal 140.

Step 420, determining at least one optimal listening position from the plurality of listening positions based on the analysis result of the panoramic image and the initial parameters.

In some embodiments, the analysis results of the panoramic image may include the location of the target sound and the listening location. In some embodiments, a processing device (e.g., processor 120) may obtain parameters of a plurality of target sounds corresponding to a plurality of listening positions, and determine at least one optimal listening position according to a comparison of the parameters of the plurality of target sounds with the initial parameters. For example only, assuming that the initial parameter is a delay of the target sound, the delay of the target sound corresponding to the first listening position is 40ms, and the delay of the target sound corresponding to the second listening position is 60ms, the comparison result is that the first listening position is better than the second listening position. Repeating the steps until at least one optimal listening position is determined.

Step 430, adjusting the gain of the target sound based on the optimal listening position.

In some embodiments, the processing device (e.g., processor 120) may adjust the gain of the target sound based on the optimal listening position. For example only, the processor 120 may decrease the gain of the target sound provided that the listening effect requested by the user is soft sound quality. For example by reducing the amplification of the target sound.

According to the description, the optimal parameters of the sound can be further determined at the optimal listening position, so that the comprehensiveness and accuracy of the determination of the sound parameters are improved, and the listening experience of a user is further improved.

In some embodiments, the system 500 may include a first acquisition module 510, a second acquisition module 520, an analysis module 530, a first determination module 540, a third acquisition module 550, and a second determination module 560.

The first acquisition module 510 may be used to acquire panoramic images. In some embodiments, the first obtaining module 510 may be configured to obtain a panoramic image of a target space in which a target sound is placed, where the target sound has an LED lamp, and the panoramic image is captured when the LED lamp is turned on. In some embodiments, the first obtaining module 510 may be further configured to obtain a plurality of images of the target space from a mobile terminal; based on the plurality of images, the panoramic image is obtained.

The second acquisition module 520 may be used to acquire listening positions. In some embodiments, the second acquisition module 520 may be configured to acquire a listening position of the target space. In some embodiments, the second acquisition module 520 may also be used to acquire the listening position entered by the user from the mobile terminal.

The analysis module 530 may be used to analyze the panoramic image. In some embodiments, analysis module 530 may be used to identify the material, shape, and size of the placements in the target space.

In some embodiments, the analysis module 530 may further include a first identification module 531, a second identification module 532, and a third identification module 533.

The first recognition module 531 may be used to recognize the location of the target sound. In some embodiments, the first identifying module 531 may be configured to identify the location of the target sound by identifying the shape or location of the LED lights of the target sound in the panoramic image. In some embodiments, the first identifying module 531 may also be configured to identify a second distance between the target sound and a photographer of the panoramic image by identifying a shape or position of an LED lamp of the target sound in the panoramic image; and determining a position of the target sound based on the second distance.

The second recognition module 532 may be used to recognize the relative distance of the listening position from the target sound. In some embodiments, the second identification module 532 may be configured to identify a first distance and a first angle between the listening position and the target sound based on the listening position and the position of the target sound.

The third identification module 533 may be used to identify information of the placements and the target space. In some embodiments, a third identification module 533 may be used to identify the location of a placeholder in the target space. In some embodiments, the third identification module 533 may also be used to identify the material, shape, and size of the placements in the target space. In some embodiments, the third identifying module 533 may also be configured to identify at least one of a size of the target space, a standing wave of the target space, reverberation of the target space, sensitivity of the target sound, and a gain formula of the target sound.

The first determining module 540 may be configured to determine a gain of the target sound based on an analysis result of the panoramic image. In some embodiments, the first determining module 540 may be further configured to input the position of the target sound, the first distance and the first angle between the listening position and the target sound, the position of the placement object, the size of the target space, and the wall surface material of the target space to the trained sound parameter configuration model, and output the gain of the target sound. In some embodiments, the first determining module 540 may also be configured to obtain initial parameters of the target sound, where the initial parameters include an initial gain of the target sound; determining at least one optimal listening position from the plurality of listening positions based on an analysis result of the panoramic image and the initial parameter; and adjusting the gain of the target sound based on the optimal listening position.

The third obtaining module 550 may be configured to obtain preset parameters of the target sound. In some embodiments, the third obtaining module 550 may be configured to obtain a preset parameter of at least one sound of the target sound, where the preset parameter includes a preset gain of the at least one sound.

The second determination module 560 may be used to determine the location of the target sound. In some embodiments, the second determining module 560 may be configured to determine the target location of the at least one sound device based on the listening position and the preset parameter.

It should be understood that the system shown in fig. 5 and its modules may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system of the present specification and its modules may be implemented not only with hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software executed by various types of processors, for example, and with a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description of the acoustic parameter determining system 500 and its modules is for convenience only and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. For example, in some embodiments, the first acquisition module 510, the second acquisition module 520, the analysis module 530, the first determination module 540, the third acquisition module 550, and the second determination module 560 disclosed in fig. 5 may be different modules in one system, or may be one module to implement the functions of two or more modules. For another example, the first acquisition module 510 and the second acquisition module 520 may be two modules, or may be one module having both acquisition and data processing functions. For another example, the first recognition module 531 and the second recognition module 532 may be two modules, and when the listening position coincides with the position where the panoramic image is acquired, the first recognition module 531 and the second recognition module 532 may be one module while having a function of recognizing the distance between the listening position and the target sound. Such variations are within the scope of the present description.

Possible benefits of embodiments of the present description include, but are not limited to: (1) The panoramic image of the target space where the sound is located is identified, and a plurality of factors influencing the sound parameters are obtained, so that the parameters of the sound can be more conveniently, rapidly, comprehensively and accurately determined according to the influence factors; (2) By changing the position of the sound equipment, the gain of the sound equipment can be further determined under the optimal parameters or the optimal listening position of the sound equipment, so that the listening experience of a user can be improved.

It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A method of training an acoustic parameter configuration model, comprising:

Obtaining a training sample, wherein the training sample at least comprises: the training sample is obtained through auxiliary equipment, wherein the training sample comprises one or more of a position of a target sound, a first distance and a first angle between a listening position and the target sound, a position of a placed object in a target space, a material of the placed object, a shape of the placed object, parameters of the target sound or an image containing the information;

obtaining a label corresponding to the training sample, wherein the label at least comprises one or more of the tone quality of the target sound or the parameters of the target sound; and

training the acoustic parameter configuration model based on the training sample and the label corresponding to the training sample, and ending the training when the trained acoustic parameter configuration model meets the preset condition;

the obtaining the training sample by the auxiliary equipment comprises the following steps:

moving the target sound equipment, the hearing equipment or the placement object through the auxiliary equipment, and changing the position of the target sound equipment, a first distance and a first angle between the hearing position and the target sound equipment and the position of the placement object; or replacing the type, shape and/or material of the placed object by the auxiliary equipment; and

And automatically setting or adjusting the parameters of the target sound according to the data to acquire a plurality of parameters of the target sound, thereby acquiring the training sample.

2. The acoustic parameter configuration model training method of claim 1, the auxiliary device being an automated device comprising at least one or more of a robotic arm or an automated cart.

3. The acoustic parameter configuration model training method according to claim 1, wherein the parameters of the target acoustic include a plurality of parameter values of the target acoustic that are automatically set, the plurality of parameter values being set according to the training sample.

4. The method for training the acoustic parameter configuration model according to claim 1, wherein the obtaining the label corresponding to the training sample includes:

and screening the labels, and taking the tone quality of the target sound and/or the parameters of the target sound which meet preset screening conditions as the labels corresponding to the training samples.

5. The method for training the acoustic parameter configuration model according to claim 4, wherein the filtering the label, taking the sound quality of the target acoustic and/or the parameter of the target acoustic meeting the preset filtering condition as the label corresponding to the training sample comprises:

Automatically scoring the tone quality of the target sound corresponding to the sound emitted by the target sound; and

and when the score of the tone quality of the target sound or the score of the tone quality corresponding to the parameter of the target sound is larger than a preset score threshold, taking the tone quality of the target sound or the parameter of the target sound as a label corresponding to the training sample.

6. The acoustic parameter configuration model training method according to claim 5, wherein the automatically scoring the sound quality of the target sound corresponding to the sound emitted by the target sound comprises: and receiving the sound emitted by the target sound through the listening device with the scoring function, and automatically scoring the tone quality of the target sound corresponding to the sound emitted by the target sound.

7. The acoustic parameter configuration model training method of claim 6, the listening device comprising a simulated user system.

8. The method for training the acoustic parameter configuration model according to claim 1, wherein the training the acoustic parameter configuration model based on the training samples and the labels corresponding to the training samples, and when the trained acoustic parameter configuration model meets a preset condition, the training ending includes:

Training the acoustic parameter configuration model based on a gradient descent method.

9. The acoustic parameter configuration model training method of claim 1, the preset condition comprising a loss function result converging or being less than a preset threshold.