Accompaniment generating method, device and storage medium

By generating virtual audio signals from a dry audio signal set and integrating them with audio effect synthesis, the method addresses the lack of three-dimensionality in virtual 3D audio, enhancing user experience through immersive audio surround effects.

JP2024544712AActive Publication Date: 2024-12-03TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2024535382
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-14
Filing Date
2022-10-11
Publication Date
2024-12-03
Estimated Expiration
2042-10-11

AI Technical Summary

Technical Problem

Existing methods for applying virtual 3D audio technology in multi-person chorus scenes fail to enhance sound effects and auditory sensation, leading to a lack of three-dimensionality and degraded user experience.

Method used

A method and apparatus for generating accompaniment that involves obtaining a dry audio signal set, creating virtual audio signals based on different spatial sound image positions, integrating these signals, and performing audio effect synthesis to produce an immersive three-dimensional audio experience.

Benefits of technology

The method enriches audio processing effects and enhances user experience by simulating omnidirectional audio stereo surround and improving the sense of presence in virtual 3D audio environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024544712000001_ABST
    Figure 2024544712000001_ABST
Patent Text Reader

Abstract

In the embodiment of the present application, an accompaniment generating method, device and storage medium are provided. The accompaniment generating method includes the following contents: Obtain a dry audio signal set. The dry audio signal set includes x dry audio signals corresponding to a target song. Generate a virtual audio signal based on the dry audio signal corresponding to each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions. The x dry audio signals correspond to N virtual three-dimensional space sound image positions, and the N virtual three-dimensional space sound image positions are different, and each virtual three-dimensional space sound image position is allowed to correspond to one or more dry audio signals among the x dry audio signals. Integrate each virtual audio signal in the virtual audio signal set to obtain a chorus dry audio. According to the audio effect optimization rule, perform audio effect synthesis processing on the chorus dry audio and the background music of the target song to obtain the accompaniment of the target song. The present application can realize the effect of stereo surround of the accompaniment.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present application relates to the technical field of computer applications, and in particular to an accompaniment generation method, device, and storage medium. [Background technology]

[0002] With the development of virtual reality technology, virtual three-dimensional (3D) audio technology is also gradually being optimized. Virtual 3D audio technology can create a three-dimensional dynamic effect, and when applied to singing software, it can give users a sense of immersion. Currently, when applying virtual 3D audio technology to a multi-person chorus scene, the existing technical solution is to directly weight and overlap multiple voices, but this processing method lacks audio effects and audible three-dimensionality, which reduces the user experience. Summary of the Invention

[0003] The embodiments of the present application provide an accompaniment generating method, device, and storage medium that can achieve an omnidirectional stereo surround effect for audio and improve user experience.

[0004] In one aspect, an embodiment of the present application provides a method for generating accompaniment, the method comprising: Obtaining a dry audio signal set, where the dry audio signal set includes x dry audio signals corresponding to a target song, where x is an integer greater than 1; generating virtual audio signals based on dry audio signals corresponding to each virtual three-dimensional spatial sound image location among the N virtual three-dimensional spatial sound image locations, where x dry audio signals correspond to the N virtual three-dimensional spatial sound image locations, N being an integer greater than 1, and the N virtual three-dimensional spatial sound image locations are distinct, and each virtual three-dimensional spatial sound image location is permitted to correspond to one or more dry audio signals among the x dry audio signals; Integrating each virtual audio signal in a virtual audio signal set to obtain a chorus dry audio, the virtual audio signal set including a virtual audio signal at each virtual three-dimensional spatial sound image position among the N virtual three-dimensional spatial sound image positions; and performing a voice effect synthesis process on the chorus dry voice and the background music of the target song according to a voice effect optimization rule to obtain an accompaniment for the target song.

[0005] In one aspect, an embodiment of the present application provides a method for processing an accompaniment playback, the method comprising: displaying a user interface for receiving a selection indication for a target song; When the selection indication received at the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode, obtaining an accompaniment corresponding to the target song; and playing an accompaniment corresponding to the target song; The accompaniment is generated based on a chorus dry audio and background music, the chorus dry audio is generated based on a plurality of dry audio signals in a dry audio signal set, the plurality of dry audio signals in the dry audio signal set correspond to a plurality of different virtual three-dimensional spatial sound image positions, and the dry audio signal set is obtained based on dry audio signals recorded by a plurality of users for the target song.

[0006] In another aspect, an embodiment of the present application provides an accompaniment generating apparatus, comprising an obtaining unit and a processing unit.

[0007] The acquisition unit is used to acquire a dry audio signal set, where the dry audio signal set includes x dry audio signals corresponding to a target song, where x is an integer greater than 1. The acquisition unit is used to generate a virtual audio signal based on the dry audio signal corresponding to each virtual three-dimensional spatial sound image position among the N virtual three-dimensional spatial sound image positions, where the x dry audio signals correspond to the N virtual three-dimensional spatial sound image positions, where N is an integer greater than 1, the N virtual three-dimensional spatial sound image positions are different, and each virtual three-dimensional spatial sound image position is allowed to correspond to one or more dry audio signals among the x dry audio signals.

[0008] The processing unit is used to integrate each virtual audio signal in the virtual audio signal set to obtain a chorus dry audio, and the virtual audio signal set includes a virtual audio signal at each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions. The processing unit is used to perform audio effect synthesis processing on the chorus dry audio and the background music of the target song according to the audio effect optimization rule to obtain an accompaniment of the target song.

[0009] In another aspect, an embodiment of the present application provides an apparatus for processing an accompaniment playback, comprising an acquisition unit and a processing unit.

[0010] The obtaining unit is used for displaying a user interface for receiving a selection indication for the target song, and the obtaining unit is used for obtaining an accompaniment corresponding to the target song when the selection indication received on the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode.

[0011] The processing unit is used for playing an accompaniment corresponding to the target song, the accompaniment being generated based on a chorus dry voice and background music, the chorus dry voice being generated based on a plurality of dry voice signals in a dry voice signal set, the plurality of dry voice signals in the dry voice signal set corresponding to a plurality of different virtual three-dimensional space sound image positions, and the dry voice signal set being obtained based on dry voice signals recorded by a plurality of users for the target song.

[0012] Accordingly, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a network interface, the processor being connected to the memory and the network interface, the network interface being used to provide a network communication function, the memory being used to store a program code, and the processor being used to call the program code to perform the method in the embodiment of the present application.

[0013] Accordingly, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method of the embodiment of the present application.

[0014] Accordingly, an embodiment of the present application provides a computer program product or a computer program, which includes computer instructions, the computer instructions being stored in a computer-readable storage medium, and a processor of a computing device reads and executes the computer instructions from the computer-readable storage medium to cause the computing device to perform a method in an embodiment of the present application.

[0015] By implementing the embodiment of the present application, on the one hand, a virtual audio signal at a different virtual three-dimensional space sound image position of each dry audio signal corresponding to a target song in a dry audio signal set can be obtained, and then the virtual audio signal corresponding to each dry audio signal can be integrated to obtain a chorus dry audio, and finally, according to the audio effect optimization rule, an audio effect synthesis process can be performed on the chorus dry audio and the background music of the target song to obtain the accompaniment of the target song. On the other hand, a selection indication of the target song by a user can be received, and if the received selection indication indicates that the accompaniment mode of the target song is a chorus accompaniment mode, an accompaniment corresponding to the target song can be obtained and played. In this way, the sound image position in the virtual three-dimensional space of the dry audio signal can be simulated in all directions to realize the effect of stereo surround of audio, so that the user can realize a realistic and immersive experience when obtaining the corresponding accompaniment. [Brief description of the drawings]

[0016] In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the drawings used in the description of the embodiments or the prior art are briefly introduced below. Obviously, the drawings used in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative efforts. [Figure 1] FIG. 2 is a schematic diagram of an application scenario of the accompaniment generation method according to an embodiment of the present application; [Diagram 2] 2 is a flowchart of an accompaniment generating method according to an embodiment of the present application. [Figure 3a] 3A to 3C are schematic diagrams of a horizontal plane, an upper plane, and a lower plane in an accompaniment generating method according to an embodiment of the present application; [Figure 3b] 3 is a schematic diagram of a virtual three-dimensional space sound image position in the accompaniment generating method according to the embodiment of the present application. FIG. [Figure 3c] 10 is a schematic diagram showing how each plane is divided at intervals of a preset angle in the accompaniment generating method according to the embodiment of the present application. FIG. [Figure 4] 4 is a flowchart of another accompaniment generating method according to an embodiment of the present application. [Diagram 5] 4 is a flowchart of acquiring a binaural signal corresponding to a dry audio signal in a dry audio signal set in an accompaniment generating method according to an embodiment of the present application. [Figure 6] 4 is a flowchart of an accompaniment playback processing method according to an embodiment of the present application. [Figure 7a] 4 is a flowchart for acquiring an accompaniment corresponding to a target piece of music in the accompaniment reproduction processing method according to the embodiment of the present application. [Figure 7b] FIG. 2 is a schematic diagram showing a first sentence interface in the accompaniment playback processing method according to an embodiment of the present application; [Figure 7c] FIG. 11 is a schematic diagram showing a second sentence interface in the accompaniment playback processing method according to an embodiment of the present application; [Figure 8a] 1 is a schematic structural diagram of an accompaniment generating device according to an embodiment of the present application; [Figure 8b] 1 is a schematic structural diagram of an accompaniment playback processing device according to an embodiment of the present application; [Figure 9] 1 is a schematic diagram of an electronic device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, the technical solutions of the embodiments of the present application will be described clearly and completely with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments that a person skilled in the art can obtain without creative efforts belong to the protection scope of the present application.

[0018] Before describing the embodiments of the present application in more detail, the nouns and terms mentioned in the embodiments of the present application will be explained. The following explanation applies to the nouns and terms mentioned in the embodiments of the present application.

[0019] 1) Dry audio signal: In the embodiments of the present application, the dry audio signal refers to a pure human voice signal without accompanying music, and the dry audio signal is a single-channel audio signal, i.e., it does not contain directional information.

[0020] 2) Binaural signal: Binaural means that there are two audio channels. The principle is that when a person hears an audio signal, the specific location of the sound source can be determined based on the phase difference between the audio heard by the left and right ears. The binaural signal in the embodiment of the present application refers to the left channel audio signal and the right channel audio signal.

[0021] 3) Head Related Transfer Functions (HRTF): HRTF, also known as binaural transfer function, represents the process by which sound waves are transmitted from a sound source to both ears. HRTF is a set of filters that employs the principle that time domain convolution is equivalent to frequency domain convolution to calculate a virtual sound signal transmitted to both ears based on the HRTF data corresponding to the position information of the sound source.

[0022] The embodiment of the present application provides an accompaniment generating method, device, and storage medium. By implementing the embodiment of the present application, a dry audio signal set consisting of a plurality of dry audio signals corresponding to the same target song is obtained, and virtual audio signals corresponding to different virtual three-dimensional space sound image positions of each dry audio signal included in the dry audio signal set are obtained, and then the virtual audio signals corresponding to each dry audio signal are integrated to obtain a chorus dry audio, and finally, according to the audio effect optimization rule, an audio effect synthesis process is performed on the chorus dry audio and the background music of the target song to obtain the accompaniment of the target song. In this way, on the one hand, the sound image positions in the virtual three-dimensional space of each dry audio signal included in the dry audio signal set are simulated in all directions, and thus the chorus dry audio after integrating the virtual audio signals corresponding to the different virtual three-dimensional space sound image positions of each dry audio signal is obtained, thereby realizing the effect of stereo surround of audio. On the other hand, according to the audio effect optimization rule, an audio effect synthesis process is performed on the chorus dry audio and the background music to obtain the accompaniment, thereby enhancing the immersive feeling of the audio effect. In summary, compared with the processing method of directly overlapping each dry audio signal, the present invention can obtain richer audio processing effects and improve the user experience.

[0023] Referring to Fig. 1, Fig. 1 is a schematic diagram of an application scenario of an accompaniment generating method according to an embodiment of the present application. As shown in Fig. 1, the application scenario may include a smart device 100. The smart device communicates with a server 110 through a wired or wireless manner. The server 110 is connected to a database 120.

[0024] The accompaniment generating method according to the embodiment of the present application can be realized by an electronic device such as a smart device 100. For example, when the smart device 100 receives a selection indication indicating that the accompaniment mode of the target song is a chorus accompaniment mode, the smart device 100 obtains a dry sound signal set corresponding to the target song, and generates a virtual sound signal based on the dry sound signal corresponding to each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions, for example, the virtual sound signal may be a binaural signal. Then, the virtual sound signal corresponding to each dry sound signal is integrated to obtain a chorus dry sound, and the accompaniment can be obtained by performing a sound effect synthesis process on the chorus dry sound and the background music of the target song according to the sound effect optimization rule. As an example, the smart device 100 in FIG. 1 shows an option of "chorus accompaniment", and the user can generate a selection indication of the chorus accompaniment mode through voice control, or can generate a selection indication of the chorus accompaniment mode by triggering a selection control displayed on a user interface. The dry audio signal set may be pre-stored locally by the smart device 100 or may be retrieved by the smart device 100 from the server 110 or the database 120.

[0025] The accompaniment generating method according to the embodiment of the present application can also be realized by an electronic device such as the server 110. For example, when the server 110 receives a selection indication indicating that the accompaniment mode of the target song is a chorus accompaniment mode, the server 110 obtains a dry sound signal set corresponding to the target song, and generates a virtual sound signal based on the dry sound signal corresponding to each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions, for example, the virtual sound signal may be a binaural signal. Then, the virtual sound signals corresponding to each dry sound signal are integrated to obtain a chorus dry sound, and the accompaniment can be obtained by performing a sound effect synthesis process on the chorus dry sound and the background music of the target song according to the sound effect optimization rule. The dry sound signal set may be stored locally in advance by the server 110, or may be obtained from the database 120 by the server 110. The finally obtained accompaniment may be stored locally or in the database 120, and may be called up when necessary. Of course, the server 110 can start generating the accompaniment without waiting for the reception of a selection indication indicating that the accompaniment mode of the target song is the chorus accompaniment mode. The server 110 can start performing the relevant steps of the accompaniment generation method of the present application to generate the accompaniment at an appropriate time, for example, when the server 110 is low-loaded, or when the server 110 receives a new dry audio signal of the target song, or when the server 110 receives a management operation related to accompaniment generation. Preferably, the chorus version of the accompaniment can be generated in advance and stored in the server. After many song accompaniments are generated, the user can send a selection indication for the target song through the smart device 100, such as by selecting "chorus accompaniment" in the user interface. In this way, the server 110 can find the chorus accompaniment of the target song from many generated accompaniments, and send the chorus accompaniment to the smart device 100 in response to the selection indication.

[0026] The accompaniment generating method according to the embodiment of the present application can also be realized by an electronic device such as the smart device 100 and an electronic device such as the server 110 in cooperation with each other. For example, the server 110 generates a virtual audio signal based on a dry audio signal corresponding to each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions, and the virtual audio signal may be a binaural signal, for example. Then, the virtual audio signal corresponding to each dry audio signal is integrated to obtain a chorus dry audio, and according to the audio effect optimization rule, a sound effect synthesis process is performed on the chorus dry audio and the background music of the target song to obtain an accompaniment, and the accompaniment can be transmitted to the smart device 100.

[0027] The accompaniment generating method according to the embodiment of the present application may be realized by executing a computer program by an electronic device such as the smart device 100 and an electronic device such as the server 110. For example, the computer program may be a native program or software module of an operating system, a local application (APP), or a mini-program. In summary, the computer program may be any type of application, module, or plug-in, and the embodiment of the present application is not particularly limited thereto.

[0028] The smart device according to the embodiment of the present application may be, but is not limited to, a personal computer, a laptop computer, a smartphone, a tablet computer, a smart watch, a smart voice dialogue device, a smart home appliance, an in-vehicle terminal, a smart wearable device, etc. The server may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services based on cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The smart device and the server may be directly or indirectly connected by wired or wireless communication methods, and are not particularly limited in the embodiment of the present application.

[0029] As can be appreciated, the number of dry audio signals and virtual three-dimensional space sound image positions shown in FIG. 1 are merely exemplary, and any number of dry audio signals may be included in the dry audio signal set, and any number of virtual three-dimensional space sound image positions may be included in the virtual three-dimensional space, depending on implementation needs.

[0030] Further, referring to FIG. 2, FIG. 2 is a flow chart of an accompaniment generating method according to an embodiment of the present application. The method of the embodiment of the present application can be applied to an electronic device. For example, the electronic device may be a smart device such as a smart phone, a tablet computer, a smart wearable device, a personal computer, or a server, etc. The method includes, but is not limited to, steps S201 to S204.

[0031] S201: Obtain a dry audio signal set.

[0032] In an embodiment of the present application, the electronic device may obtain a dry audio signal set including several dry audio signals corresponding to a target song.

[0033] In one embodiment, the set of dry audio signals can be obtained from an audio database, the audio database including initial dry audio signals recorded by multiple users singing the same song, the initial dry audio signals in the audio database being recorded with the approval of the users, and the electronic device can select dry audio signals that meet a condition based on audio parameters of the initial dry audio signals to form the set of dry audio signals.

[0034] In one embodiment, the electronic device can select a dry audio signal that satisfies a condition from the initial set of dry audio signals based on an intonation characteristic parameter and a tone quality characteristic parameter. The intonation characteristic parameter may include any one or more of a pitch parameter, a rhythm parameter, and a prosody parameter. The dry audio signal that satisfies the condition selected based on the intonation characteristic parameter has a high matching with the pitch and rhythm of the song and the melody of the accompaniment. The tone quality characteristic parameter may include any one or more of a noise parameter, an energy parameter, and a speed parameter. The dry audio signal that satisfies the condition selected based on the tone quality characteristic parameter has a clear audio, a suitable audio energy, a uniform audio speed, etc. The embodiment of the present application does not limit the selection order of the dry audio signals that satisfies the condition. For example, the electronic device can first select dry audio signals that satisfy the conditions based on the intonation characteristic parameters, and then select dry audio signals that satisfy the conditions of the preset sound quality characteristic parameters from the dry audio signals that satisfy the conditions of the preset intonation characteristic parameters, or can first select dry audio signals that satisfy the conditions based on the sound quality characteristic parameters, and then select dry audio signals that satisfy the conditions of the preset audio quality characteristic parameters from the dry audio signals that satisfy the conditions of the preset sound quality characteristic parameters. The dry audio signal set consisting of the dry audio signals selected in this way from the initial dry audio signal set has good intonation and sound quality.

[0035] S202: Generate a virtual sound signal based on a dry sound signal corresponding to each of the N virtual three-dimensional space sound image positions.

[0036] In an embodiment of the present application, the electronic device can simulate a different sound image position in the virtual three-dimensional space for each dry audio signal in the set of dry audio signals, and then generate a virtual audio signal based on the dry audio signal corresponding to each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions. The virtual audio signal can be, for example, a binaural signal. The N virtual three-dimensional space sound image positions are different, and each virtual three-dimensional space sound image position can correspond to one or more dry audio signals.

[0037] In one embodiment, N virtual 3D space sound image positions can be obtained by simulating in the virtual 3D space in the following manner. As shown in FIG. 3a, the positive directions of the x-axis, y-axis, and z-axis in the virtual 3D space correspond to the direction directly in front of, to the left of, and above a person's head, respectively. The virtual 3D space is divided into three planes: a horizontal plane 301, an upper plane 302 whose angle with the horizontal plane is a first angle threshold, and a lower plane 303 whose angle with the horizontal plane is a second angle threshold. As shown in FIG. 3b, each virtual 3D space sound image position in the virtual 3D space has an azimuth angle and an elevation angle. If θ represents the azimuth angle of the virtual 3D space sound image position and φ represents the elevation angle of the virtual 3D space sound image position, each virtual 3D space sound image position can be expressed as (θ,φ). Accordingly, the horizontal plane 301 is a plane corresponding to an elevation angle of 0°. The upper plane is a plane corresponding to an elevation angle that is a first angle threshold, and the first angle threshold may be any angle value above the horizontal plane. The lower plane is a plane corresponding to an elevation angle that is a second angle threshold, and the second angle threshold may be any angle value below the horizontal plane. For example, the upper plane may be a plane corresponding to an elevation angle that is 40°, and the lower plane may be a plane corresponding to an elevation angle that is -40°. The azimuth angle θ may represent an angle of the virtual three-dimensional space sound image position to the target direction line along a clockwise direction on the plane. Furthermore, as shown in FIG. 3c, after dividing the planes corresponding to different elevation angles into intervals of preset angles corresponding to each of them, a plurality of virtual three-dimensional space sound image positions can be obtained. Specifically, after dividing the horizontal plane into intervals of the first preset angle, n1 virtual three-dimensional space sound image positions on the horizontal plane can be obtained. After dividing the upper plane into intervals of the second preset angle, n2 virtual three-dimensional space sound image positions on the upper plane can be obtained. After dividing the lower plane with a third preset angle as an interval, n3 virtual three-dimensional spatial sound image positions on the lower plane can be obtained.For example, if the first preset angle is 10°, and the second and third preset angles are all 15°, dividing the horizontal plane at intervals of 10° can obtain 36 virtual three-dimensional space sound image positions, dividing the upper plane at intervals of 15° can obtain 24 virtual three-dimensional space sound image positions, and dividing the lower plane at intervals of 15° can obtain 24 virtual three-dimensional space sound image positions as well, resulting in a total of 84 different virtual three-dimensional space sound image positions. Note that the first preset angle, the second preset angle, and the third preset angle in the embodiment of the present application may be any preset angle value. The specific values ​​of the above three preset angles are used for illustrative purposes only and do not limit the embodiment of the present application. As a result, multiple virtual three-dimensional space sound image positions can be virtualized at intervals of different azimuth angles on three different planes in the virtual three-dimensional space, and a simulation with an omnidirectional immersive feeling of the sound source can be realized.

[0038] In one embodiment, each virtual three-dimensional space sound image position may correspond to one dry audio signal or multiple dry audio signals. The electronic device can obtain virtual audio signals corresponding to one or multiple dry audio signals at each virtual three-dimensional space sound image position. Specifically, the electronic device can obtain virtual audio signals corresponding to each dry audio signal in the virtual three-dimensional space in the following manner. The azimuth and elevation angle of the virtual three-dimensional space sound image position corresponding to the dry audio signal is obtained, and a head-related transfer function HRTF corresponding to the virtual three-dimensional space sound image position is determined based on the azimuth and elevation angle of the virtual three-dimensional space sound image position, and a virtual audio signal corresponding to the dry audio signal at the virtual space sound image position can be calculated based on the azimuth and elevation angle of the virtual three-dimensional space sound image position and the corresponding HRTF data. For example, the azimuth and elevation angle of the virtual three-dimensional space sound image position corresponding to the dry audio signal X are (θ,φ), and the formula of the HRTF data corresponding to the virtual three-dimensional space sound image position is Equation 1.

number

[0039] In one embodiment, the electronic device can obtain some dry audio signals from the dry audio signal set, for example, dry audio signals with better intonation and sound quality can be obtained randomly or selected according to a new selection rule. A delay process is separately performed on the selected dry audio signals to obtain a delayed binaural signal corresponding to each dry audio signal among these dry audio signals. Specifically, when performing a delay process on one dry audio signal, eight sets of different time parameters can be selected. Note that the eight sets of time parameters represent eight time parameters for obtaining a delayed left channel signal and eight time parameters for obtaining a delayed right channel signal, and a total of 16 time parameters are selected. For example, based on the reverberation time of a general room impulse response being 80 ms, 16 unequal parameters in the range of 21 ms to 79 ms can be selected as time parameters. Or, 16 unequal parameters (or other values) can be selected as time parameters randomly in another reasonable range according to actual needs. In this way, the dry audio signal obtained at the left ear or right ear of a person's head can be simulated, and the audio effect can be made richer. In one embodiment, the selection method and the setting of the time parameter (delay time parameter) of the delay processing can be adjusted through one interface, facilitating the flexible configuration of the user to create chorus audio. Note that the above-mentioned step of obtaining a virtual voice signal and the step of obtaining a delayed left channel signal and a delayed right channel signal can be performed simultaneously or one after the other, and the present application is not limited thereto.

[0040] S203: Each virtual audio signal in the virtual audio signal set is integrated to obtain a chorus dry audio.

[0041] In an embodiment of the present application, the electronic device may combine each virtual sound signal in the set of virtual sound signals to obtain a chorus dry sound.

[0042] In one embodiment, the integration of the virtual audio signals corresponding to each dry audio signal can be realized through a normalization process to achieve the purpose of adjusting the volume of the integrated virtual audio signal to [-1 dB, 1 dB]. Each virtual audio signal handled during the integration process includes a virtual audio signal corresponding to a dry audio signal at each virtual three-dimensional space sound image position among the acquired N virtual three-dimensional space sound image positions, and a respective delayed binaural signal obtained by performing a delay process on some dry audio signals in the dry audio signal set.

[0043] S203: According to the sound effect optimization rule, perform sound effect synthesis processing on the chorus dry voice and the background music of the target song to obtain the accompaniment of the target song.

[0044] In the embodiment of the present application, the electronic device can perform a sound effect synthesis process on the chorus dry sound and the background music of the target song according to the sound effect optimization rule to obtain a final accompaniment. The sound effect optimization rule can be, for example, adjusting sound parameters of the background music of the target song and the virtual sound signals corresponding to the obtained multiple dry sound signals, and the sound parameters can be commonly adjustable parameters such as volume, timbre, etc.

[0045] In one embodiment, the electronic device can obtain background music of the target song after obtaining the chorus dry voice. If the energy relationship between the obtained chorus dry voice and the background music of the target song does not satisfy the energy ratio condition, the electronic device can adjust the energy relationship between the chorus dry voice and the background music of the target song. The energy ratio condition may be set so that the proportion between the energy value of the chorus dry voice and the energy value of the background music of the target song is smaller than a proportion threshold, and the volume of the chorus dry voice may be set so that it is 3 dB lower than the volume of the background music of the target song. This can prevent the energy of the chorus dry voice from being larger than the energy of the background music of the target song, and make the final accompaniment more harmonious.

[0046] By implementing the embodiment of the present application, a virtual audio signal corresponding to a different virtual three-dimensional space sound image position in the virtual three-dimensional space of each dry audio signal can be obtained, and then each virtual audio signal is integrated to obtain a chorus dry audio, and according to the audio effect optimization rule, an audio effect synthesis process is performed on the chorus dry audio and the background music of the target song to obtain the accompaniment of the target song, thereby realizing a stereoscopic surround effect in the auditory sense of the audio, enhancing the immersive feeling of the audio effect, and providing a good user experience.

[0047] Further, referring to FIG. 4, FIG. 4 is a flow chart of another accompaniment generating method according to an embodiment of the present application. The method of the embodiment of the present application can be applied to an electronic device. The electronic device is, for example, a smart phone, a tablet computer, a smart wearable device, a personal computer, a server, etc. The method includes, but is not limited to, steps S401 to S412.

[0048] S401: Obtain an initial set of dry audio signals from an audio database.

[0049] In an embodiment of the present application, the electronic device can obtain an initial set of dry audio signals from an audio database, where the initial set of dry audio signals was recorded with the approval of a user.

[0050] In one embodiment, the audio database may be an independently configured database, or may be integrated into the electronic device, i.e., the audio database may be considered to be stored inside the electronic device, where the initial dry audio signal set refers to a set of original dry audio signals recorded after approval when the user sings the same song in the audio database.

[0051] S402: Select dry audio signals from the initial dry audio signal set based on audio parameters of each initial dry audio signal, and the selected dry audio signals constitute the dry audio signal set.

[0052] In an embodiment of the present application, the electronic device can select dry audio signals from the initial dry audio signal set that meet a condition based on audio parameters of each initial dry audio signal, thereby narrowing down the initial dry audio signal set to form the dry audio signal set.

[0053] In one embodiment, the voice parameters of the initial dry voice signal may include intonation characteristic parameters and tone quality characteristic parameters of the initial dry voice signal. The intonation characteristic parameters may include any one or more of pitch parameters, rhythm parameters, and prosody parameters, and the tone quality characteristic parameters may include any one or more of noise parameters, energy parameters, and speed parameters. In this way, it is possible to remove initial dry voice signals having poor audio effects such as noise, off-key, audio time too short, low audio energy, and pop sounds from the initial dry voice signal set, and obtain a dry voice signal set with excellent intonation and tone quality.

[0054] S403: A head-related transfer function corresponding to each of the N virtual three-dimensional space sound image positions is obtained.

[0055] In an embodiment of the present application, an electronic device can obtain N virtual three-dimensional spatial sound image positions in a virtual three-dimensional space, and then obtain head-related transfer functions corresponding to each virtual three-dimensional spatial sound image position based on the N virtual three-dimensional spatial sound image positions.

[0056] In one embodiment, the head-related transfer functions corresponding to each virtual 3D spatial sound image position in the virtual 3D space can be stored in advance in a head-related transfer function database, thereby allowing the electronic device to retrieve the corresponding head-related transfer function from the head-related transfer function database based on the virtual 3D spatial sound image position.

[0057] S404: Process the dry sound signal corresponding to the target virtual three-dimensional space sound image position through a head-related transfer function corresponding to the target virtual three-dimensional space sound image position to obtain a virtual sound signal at the target virtual three-dimensional space sound image position.

[0058] In an embodiment of the present application, the electronic device can process the target dry audio signal based on a head-related transfer function corresponding to the target virtual three-dimensional spatial sound image position to obtain a virtual audio signal corresponding to the target dry audio signal at the target virtual three-dimensional spatial sound image position. The target virtual three-dimensional spatial sound image position can be any one of the N virtual three-dimensional spatial sound image positions. The target dry audio signal can be any one of the dry audio signals in the dry audio signal set.

[0059] In one embodiment, the head-related transfer function corresponding to the target virtual 3D spatial sound image position is HRTF data corresponding to the virtual 3D spatial sound image position. According to the azimuth and elevation of the target virtual 3D spatial sound image position, the HRTF data corresponding to the target virtual 3D spatial sound image position can be determined from the known HRTF data, and then the electronic device can perform convolution on the target dry sound signal and the HRTF data corresponding to the target virtual 3D spatial position to obtain a virtual sound signal corresponding to the target dry sound signal at the target virtual 3D spatial sound image position.

[0060] S405: p dry audio signals are obtained from the x dry audio signals included in the dry audio signal set.

[0061] In an embodiment of the present application, the electronic device may randomly obtain p dry audio signals from x dry audio signals included in the dry audio signal set. Note that, S404 and S405 may be performed simultaneously or one after the other, which is not limited in the present application.

[0062] S406: Perform a delay process on each of the p dry audio signals to obtain a delayed left channel signal and a delayed right channel signal corresponding to each of the p dry audio signals.

[0063] In an embodiment of the present application, the electronic device performs delay processing of m1 time parameters on each dry audio signal of the p dry audio signals to obtain m1 delayed dry audio signals corresponding to each dry audio signal of the p dry audio signals, and overlaps the m1 delayed dry audio signals corresponding to each dry audio signal to obtain a delayed left channel signal corresponding to each dry audio signal of the p dry audio signals, where m1 is a positive integer. Also, the electronic device performs delay processing of m2 time parameters on each dry audio signal of the p dry audio signals to obtain m2 delayed dry audio signals corresponding to each dry audio signal of the p dry audio signals, and overlaps the m2 delayed dry audio signals corresponding to each dry audio signal to obtain a delayed right channel signal corresponding to each dry audio signal of the p dry audio signals, where m2 is a positive integer.

[0064] In one embodiment, the electronic device can process one dry audio signal through 16 delays with different time parameters to obtain 16 dry audio signals with different delays and attenuations, then equally divide the 16 dry audio signals with different delays and attenuations into two sets, separately superimpose the dry audio signals with different delays and attenuations of each set, and finally obtain a delayed left channel signal and a delayed right channel signal corresponding to the dry audio signal.

[0065] In one embodiment, before obtaining a delayed binaural signal corresponding to each of the p dry audio signals, a bass boost and reverberation simulation module is added to widen the sound field of the dry audio signal, thereby reducing the correlation between the delayed left channel signal and the delayed right channel signal among the binaural signals obtained through the delay process. Note that the steps S403 and S404 of obtaining a virtual audio signal and the steps S405 and S406 of obtaining a delayed left channel signal and a delayed right channel signal may be performed simultaneously or one after the other, and the present application is not limited thereto. S405 and S406 are two selectable steps.

[0066] S407: Each virtual audio signal in the virtual audio signal set is integrated to obtain a chorus dry audio.

[0067] In an embodiment of the present application, the electronic device can obtain a chorus dry sound by integrating each virtual sound signal in the virtual sound signal set, which includes virtual sound signals corresponding to each dry sound signal obtained by the electronic device simulating N virtual three-dimensional space positions, and delayed binaural signals obtained by the electronic device performing delay processing on p dry sound signals in the dry sound signal set.

[0068] In one embodiment, each virtual audio signal in the virtual audio signal set is a binaural signal, and the binaural signal includes a left channel signal and a right channel signal. When integrating each virtual audio signal, the left channel signal and the right channel signal can be processed separately. The left channel signal and the right channel signal are applied with the same processing rule. The integration process can be realized through a normalization process, so that the volume of the binaural signal after integration process is [-1 dB, 1 dB]. For example, assuming there are 1000 binaural signals including 1000 left channel signals and 1000 right channel signals, the sum of the 1000 normalized left channel signals can be divided by 1000 after each left channel signal is normalized separately to obtain an integrated left channel signal. Similarly, the sum of the 1000 normalized right channel signals can be divided by 1000 after each right channel signal is normalized separately to obtain an integrated right channel signal. In this way, a chorus dry voice can be obtained.

[0069] In one embodiment, the energy relationship between the obtained chorus dry voice and the background music of the target song may or may not satisfy the energy ratio condition. If the energy relationship between the obtained chorus dry voice and the background music satisfies the energy ratio condition, step S408 can be omitted. Accordingly, if the energy relationship between the obtained chorus dry voice and the background music does not satisfy the energy ratio condition, step S408 is executed.

[0070] S408: Obtain background music of the target song, and adjust the energy relationship between the chorus dry voice and the background music.

[0071] In an embodiment of the present application, the electronic device can obtain background music of a target song, and adjust the energy relationship between the chorus dry voice and the corresponding background music, and the energy relationship between the adjusted chorus dry voice and the adjusted background music satisfies an energy ratio condition.

[0072] In one embodiment, the energy of the chorus dry voice may be too high and exceed the energy of the background music. The chorus dry voice and the background music may be adjusted so that the energy relationship between the adjusted chorus dry voice and the adjusted background music satisfies an energy ratio condition, and in this manner, the situation where the energy of the chorus dry voice is too high may be addressed. The energy ratio condition may be set such that the proportion between the energy value of the chorus dry voice and the energy value of the background music is less than a proportion threshold, and the volume of the chorus dry voice may be set to be 3 dB lower than the volume of the background music.

[0073] In one embodiment, after obtaining the background music of the target song, according to the detailed description of generating a virtual audio signal based on a dry audio signal corresponding to each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions in the above step S202, the background music is similarly processed to obtain a chorus dry audio and background music with similar effects, so as to realize a more harmonious and integrated listening experience.

[0074] S409: Spectral equalization processing is performed on the chorus dry voice in a preset frequency band.

[0075] In an embodiment of the present application, the electronic device can perform a spectral equalization process on the chorus dry audio in a pre-defined frequency band.

[0076] In one embodiment, the electronic device can achieve the purpose of spectrum equalization by adding a spectrum notch processing in a preset frequency band. For example, the electronic device can add a spectrum notch processing of about 6 dB near 4 kHz, which can make the chorus dry voice sound more natural and prevent high-frequency current sound caused by spectrum disharmony.

[0077] S410: Get the background music volume.

[0078] In an embodiment of the present application, the electronic device can obtain the volume of the background music.

[0079] S411: If the volume is less than the volume threshold, increase the volume of the adjusted background music to the volume threshold.

[0080] In an embodiment of the present application, if the volume of the background music is lower than the volume threshold, the electronic device can increase the volume of the background music to the volume threshold. For example, the volume threshold can be set to -14 dB. If the volume of the background music is lower than -14 dB, the electronic device can increase the volume of the background music to -14 dB.

[0081] S412: Acquire accompaniment.

[0082] In an embodiment of the present application, the electronic device can superimpose the chorus dry voice and background music to obtain the final accompaniment. Note that the accompaniment may be obtained according to any one or a combination of steps S408-S411. In addition, in an embodiment, S408-S411 can be selectively performed according to actual needs. For example, it may not be necessary to adjust the energy relationship between the chorus dry voice and the background music, so in this case S408 is not performed. Similarly, it is also possible to select to perform a spectrum equalization process on the chorus dry voice in a preset frequency band. As another example, steps S410 and S411 may not be performed. FIG. 4 only shows a technical solution adopted to make the accompaniment more harmonious and natural and improve the sound quality. In addition, the order of performing the three aspects of the energy relationship adjustment in S408, the spectrum equalization adjustment in S409, and the volume adjustment in S410 and S411 is not limited in the present application.

[0083] In one embodiment, after obtaining the final accompaniment, the accompaniment can be stored in a database, so that when the electronic device receives a chorus request for the same song, it can directly obtain the corresponding accompaniment from the database.

[0084] By implementing the embodiment of the present application, N virtual three-dimensional space positions can be simulated to obtain virtual audio signals corresponding to each dry audio signal, and delay processing can be performed on each dry audio signal to obtain delayed binaural signals corresponding to each dry audio signal, thereby enriching the chorus dry audio signal. In addition, by adjusting the energy relationship between the chorus dry audio and the background music, the final accompaniment is more harmonious and natural, and the user can clearly feel the sense of space and immersion when playing the chorus.

[0085] Further, referring to Fig. 5, Fig. 5 is a flowchart of acquiring a virtual audio signal in an accompaniment generating method according to an embodiment of the present application. Acquiring a virtual audio signal includes acquiring a virtual audio signal corresponding to a dry audio signal at each of the N virtual three-dimensional space sound image positions, and performing a delay process on each of the p dry audio signals to acquire a delayed binaural signal corresponding to each of the p dry audio signals.

[0086] In an embodiment of the present application, after obtaining a dry audio signal set, a virtual audio signal corresponding to the dry audio signal at each of the N virtual three-dimensional spatial sound image positions can be obtained, and a delay process can be performed on each of the p dry audio signals in the dry audio signal set to obtain a delayed binaural signal corresponding to each of the p dry audio signals.

[0087] As an example, as shown in FIG. 5, for the dry audio signal X and the dry audio signal W included in the dry audio signal set, corresponding virtual audio signals are obtained by the above two methods separately. The dry audio signal X and the dry audio signal W may be any dry audio signal in the dry audio signal set. Specifically, after obtaining the dry audio signal X in the dry audio signal set, the electronic device can describe the position information of the virtual three-dimensional space sound image position based on the azimuth angle and the elevation angle of the virtual three-dimensional space sound image position, that is, it can be described as (θ,φ). Then, according to the position information (θ,φ) of the virtual three-dimensional space sound image position, the head related transfer function HRTF(θ,φ) corresponding to the virtual three-dimensional space sound image position can be determined. Next, a convolution operation is performed on the dry audio signal X and the head related transfer function HRTF(θ,φ) corresponding to the virtual three-dimensional space sound image position to obtain a virtual audio signal corresponding to the dry audio signal at the virtual three-dimensional space sound image position. The virtual audio signal is a left channel signal Y L and the right channel signal Y R The binaural signal thus obtained corresponds to the dry audio signal, and can enhance the user's sense of three-dimensional immersion.

[0088] In addition, after obtaining the dry audio signal W in the set of dry audio signals, the electronic device may perform a delay process on the dry audio signal W. For example, the electronic device may L (1),d L (2),…,d L (8) and d R (1),d R (2),…,d R (8) delays the dry audio signal W through a total of 16 delays with different time parameters. Then, L (1),d L (2),…,d L The eight dry audio signals obtained through the delay process of the eight delay units (8) are overlapped to produce a delayed left channel signal W corresponding to the dry audio signal W. L Get d R (1),d R (2),…,dR The eight dry audio signals obtained through the delay process of the eight delay units (8) are overlapped to produce a delayed right channel signal W corresponding to the dry audio signal W. R The delayed binaural signal thus obtained, which corresponds to the dry audio signal, can simulate the binaural signal at the left or right ear of the human head, and can enrich the user's listening experience.

[0089] In one embodiment, the final virtual audio signal set includes the above two situations. That is, the final virtual audio signal set includes Z={ZL, ZR}, ZL=Y L +W R , ZR=Y R +W R It should be noted that the above-mentioned steps of obtaining a virtual audio signal and obtaining a delayed left channel signal and a delayed right channel signal can be performed simultaneously or one after the other, and the present application is not limited thereto. By using the above-mentioned two different methods to obtain a virtual audio signal corresponding to a dry audio signal in a dry audio signal set, the scene experience during the chorus can be presented in an all-round manner, and the audio effect can be made richer.

[0090] Further, referring to FIG. 6, FIG. 6 is a flow chart of an accompaniment playback processing method according to an embodiment of the present application. The method of the embodiment of the present application can be applied to an electronic device. The electronic device can be, for example, a smart device such as a smart phone, a tablet computer, a smart wearable device, a personal computer, or a server. The method includes, but is not limited to, steps S601-S603.

[0091] S601: The user interface is displayed.

[0092] In an embodiment of the present application, the electronic device may display a user interface that is adapted to receive a user's indication of a selection of a target song.

[0093] In one embodiment, the selection indication may include a selection indication for an accompaniment mode of the target song, which may be, but is not limited to, a chorus accompaniment mode, an original accompaniment mode, or an artificial intelligence (AI) accompaniment mode.

[0094] In one embodiment, the selection indication may be an indication generated by a user triggering a selection control displayed on a user interface. The selection indication may also be an indication generated by a user controlling the electronic device with voice, for example, the user's voice control on the electronic device may be "play in choral accompaniment mode", which allows the electronic device to generate a selection indication indicating that the accompaniment mode of the target song is the choral accompaniment mode.

[0095] S602: If the selection indication received at the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode, obtain an accompaniment corresponding to the target song.

[0096] In an embodiment of the present application, when a selection indication received on the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode, the electronic device can obtain accompaniment corresponding to the chorus accompaniment mode of the target song.

[0097] In one embodiment, a selection control for an accompaniment mode of the target song is displayed on the user interface. The selection control may include a choral accompaniment mode selection control and an original accompaniment mode selection control. Before acquiring the accompaniment corresponding to the target song, the electronic device may detect whether a selection operation for the choral accompaniment mode selection control is acquired. If the electronic device detects that a selection operation for the choral accompaniment mode selection control is acquired, it confirms that the selection indication received on the user interface indicates that the accompaniment mode of the target song is the choral accompaniment mode.

[0098] In one embodiment, the accompaniment corresponding to the chorus accompaniment mode is generated based on the chorus dry sound and background music. The chorus dry sound can be generated based on a virtual sound signal set, and the virtual sound signal set includes a virtual sound signal at each of the N virtual three-dimensional space sound image positions generated based on the obtained dry sound signal set. The dry sound signals in the dry sound signal set can correspond to a plurality of different virtual three-dimensional space sound image positions, and each virtual three-dimensional space sound image position can correspond to one or more dry sound signals. The dry sound signal set is obtained based on dry sound signals recorded by a plurality of users for a target song. Note that the user's dry sound signals for the target song are recorded with the user's approval. Specifically, the accompaniment generation method corresponding to the chorus accompaniment mode can be referred to the embodiments shown in the above figures 2 to 5, and will not be described again here.

[0099] S603: Play back the accompaniment corresponding to the target song.

[0100] In an embodiment of the present application, after the electronic device obtains the corresponding accompaniment in the chorus accompaniment mode of the target song, the electronic device can play the accompaniment to the user.

[0101] In one embodiment, the accompaniment corresponding to the target song can be used in a karaoke scene. The user can sing along while the accompaniment is being played. If approved by the user, the electronic device can collect the user's singing voice and blend it with the accompaniment corresponding to the target song before playing it back, providing the user with a unique experience of being at a concert.

[0102] In one embodiment, as shown in FIG. 7a, the electronic device obtaining the accompaniment corresponding to the target song may include, but is not limited to, steps S701-S704.

[0103] S701: An accompaniment request is transmitted to the server.

[0104] In an embodiment of the present application, the electronic device may send an accompaniment request to the server, where the accompaniment request may include an identification of the target song.

[0105] In one embodiment, the identification information of the target song is the only information used to identify the target song, for example, the identification information of the target song may be the song title of the target song.

[0106] S702: Receive the chorus dry voice and background music returned by the server in response to the accompaniment request.

[0107] In an embodiment of the present application, the electronic device may receive chorus dry voice and background music returned by the server in response to a request for accompaniment of a target song.

[0108] In one embodiment, the server can return the chorus dry voice and the background music separately, or can return the chorus dry voice and the background music after integrating them. The specific return method can be selected according to the user's settings.

[0109] S703: A target chorus dry voice segment is determined from the chorus dry voice.

[0110] In an embodiment of the present application, the electronic device can determine a target chorus dry audio segment based on the returned chorus dry audio.

[0111] In one embodiment, as shown in Fig. 7b, the electronic device can display a first sentence interface, in which each sentence in the text data corresponding to the chorus dry voice is displayed according to a sequence of time play nodes of the chorus dry voice. A user can select a target chorus dry voice segment based on each sentence displayed in the first sentence interface.

[0112] In one embodiment, the target chorus dry voice segment may consist of a portion of a sentence in the chorus dry voice, or may consist of an entire sentence in the chorus dry voice, and can be determined by a user selection operation.

[0113] S704: Obtain an accompaniment corresponding to the target song based on the chorus dry voice corresponding to the target chorus dry voice segment and background music.

[0114] In an embodiment of the present application, the electronic device can obtain an accompaniment corresponding to a target song based on the chorus dry voice corresponding to the target chorus dry voice segment selected by a user and background music.

[0115] In one embodiment, as shown in Fig. 7c, the electronic device can display a second sentence interface. The second sentence interface can be displayed during the playback of the accompaniment corresponding to the target song. In addition, in the second sentence interface, each sentence in the text data corresponding to the accompaniment can be displayed according to the sequence of the time playback nodes of the accompaniment.

[0116] In one embodiment, the electronic device can also detect whether a silent selection operation for the chorus dry voice in the accompaniment is obtained during playback. If a silent selection operation for the chorus dry voice in the accompaniment is obtained, the electronic device can cancel the playback of the chorus dry voice in the accompaniment at the current time playback node and only maintain the playback of the background music in the accompaniment.

[0117] By implementing the embodiment of the present application, on the one hand, a user's selection indication for a target song can be received. If the user's selection indication indicates that the accompaniment mode of the target song is a chorus accompaniment mode, an accompaniment corresponding to the target song can be obtained and played. On the other hand, the accompaniment of the target song in the chorus accompaniment mode is generated based on a chorus dry voice and background music. A target chorus dry voice segment is determined from the chorus dry voice, and an accompaniment corresponding to the target song is generated based on the chorus dry voice corresponding to the target chorus dry voice segment and the background music. In this way, when the accompaniment corresponding to the target song is played, the user can experience it as if he or she is at a concert, and feel a sense of realism through listening, and the user can also flexibly select the chorus dry voice in the accompaniment, which enhances the enjoyment of the accompaniment and improves the user experience.

[0118] Further, referring to Fig. 8a, Fig. 8a is a schematic structural diagram of an accompaniment generating device according to an embodiment of the present application. The accompaniment generating device according to an embodiment of the present application can be applied to an electronic device. The electronic device can be, for example, a smartphone, a tablet computer, a smart wearable device, a personal computer, a server, etc. In one embodiment, as shown in Fig. 8a, the accompaniment generating device 80 can include an acquisition unit 801 and a processing unit 802.

[0119] The acquisition unit 801 is used to acquire a dry audio signal set, where the dry audio signal set includes x dry audio signals corresponding to a target song, where x is an integer greater than 1. The acquisition unit 801 is used to generate a virtual audio signal based on the dry audio signal corresponding to each virtual three-dimensional spatial sound image position among the N virtual three-dimensional spatial sound image positions, where the x dry audio signals correspond to the N virtual three-dimensional spatial sound image positions, where N is an integer greater than 1, the N virtual three-dimensional spatial sound image positions are different, and each virtual three-dimensional spatial sound image position is allowed to correspond to one or more dry audio signals among the x dry audio signals.

[0120] The processing unit 802 is used to integrate each virtual audio signal in the virtual audio signal set to obtain a chorus dry audio, where the virtual audio signal set includes a virtual audio signal at each virtual three-dimensional space sound image position among the N virtual three-dimensional space sound image positions. The processing unit 802 is used to perform audio effect synthesis processing on the chorus dry audio and the background music of the target song according to the audio effect optimization rule to obtain an accompaniment of the target song.

[0121] In one embodiment, the acquiring unit 801 may also be used to acquire an initial dry audio signal set from an audio database, which includes initial dry audio signals recorded by multiple users when singing the same song. The processing unit 802 may also be used to select dry audio signals from the initial dry audio signal set based on audio parameters of each initial dry audio signal, and the selected dry audio signals constitute the dry audio signal set.

[0122] In one embodiment, the set of dry speech signals includes dry speech signals selected from the set of initial dry speech signals based on intonation characteristic parameters and timbre characteristic parameters, the intonation characteristic parameters including any one or more of a pitch parameter, a rhythm parameter, and a prosody parameter, and the timbre characteristic parameters including any one or more of a noise parameter, an energy parameter, and a rate parameter.

[0123] In one embodiment, the N virtual three-dimensional space sound image positions include n1 virtual three-dimensional space sound image positions in a horizontal plane obtained after dividing a horizontal plane at a first preset angle interval on the horizontal plane, n2 virtual three-dimensional space sound image positions in an upper plane obtained after dividing an upper plane at a second preset angle interval on the upper plane, and n3 virtual three-dimensional space sound image positions in a lower plane obtained after dividing a lower plane at a third preset angle interval on the lower plane. The angle between the upper plane and the horizontal plane is a first angle threshold, the angle between the lower plane and the horizontal plane is a second angle threshold, n1, n2, and n3 are positive integers, and the sum of n1, n2, and n3 is equal to N.

[0124] In one embodiment, the acquisition unit 801 can also be used to acquire a head-related transfer function corresponding to each virtual three-dimensional spatial sound image position among the N virtual three-dimensional spatial sound image positions. The processing unit 802 can also be used to process a dry audio signal corresponding to a target virtual three-dimensional spatial sound image position through the head-related transfer function corresponding to the target virtual three-dimensional spatial sound image position to acquire a virtual audio signal at the target virtual three-dimensional spatial sound image position, where the virtual audio signal at the target virtual three-dimensional spatial sound image position is a binaural signal, and the target virtual three-dimensional spatial sound image position is any one of the N virtual three-dimensional spatial sound image positions.

[0125] In one embodiment, the virtual audio signal set further includes a delayed left channel signal and a delayed right channel signal corresponding to each of the p dry audio signals. The acquisition unit 801 may also be used to acquire p dry audio signals from the x dry audio signals included in the dry audio signal set, where p is a positive integer and is less than or equal to x. The processing unit 802 may also be used to perform delay processing of m1 time parameters on each of the p dry audio signals to acquire m1 delayed dry audio signals corresponding to each of the p dry audio signals, and overlap the m1 delayed dry audio signals corresponding to each of the dry audio signals to acquire a delayed left channel signal corresponding to each of the p dry audio signals, where m1 is a positive integer. The processing unit 802 may also be used to perform delay processing of m2 time parameters on each dry audio signal among the p dry audio signals to obtain m2 delayed dry audio signals corresponding to each dry audio signal among the p dry audio signals, and to obtain a delayed right channel signal corresponding to each dry audio signal among the p dry audio signals by superimposing the m2 delayed dry audio signals corresponding to each dry audio signal, where m2 is a positive integer.

[0126] In one embodiment, the acquisition unit 801 can also be used to acquire background music of the target song, and the processing unit 802 can also be used to adjust the energy relationship between the chorus dry voice and the background music. The energy relationship between the adjusted chorus dry voice and the adjusted background music satisfies an energy ratio condition. The accompaniment is obtained based on the adjusted chorus dry voice and the background music.

[0127] In one embodiment, the processing unit 802 can also be used to perform a spectral equalization process on the chorus dry voice in a preset frequency band. The acquisition unit 801 can also be used to acquire the volume of the background music. If the volume of the background music is lower than the volume threshold, the processing unit 802 can also be used to increase the volume of the background music to the volume threshold. The accompaniment is obtained based on the chorus dry voice after the spectral equalization process and the background music after the volume process.

[0128] In addition, for contents not mentioned in the embodiment corresponding to FIG. 8a and specific implementation methods of each step, you may refer to the embodiments shown in FIGS. 2 to 5 and the above-mentioned contents, and will not be described again here.

[0129] Further, referring to Fig. 8b, Fig. 8b is a schematic structural diagram of an accompaniment playback processing device according to an embodiment of the present application. The accompaniment playback processing device according to an embodiment of the present application can be applied to an electronic device. The electronic device can be, for example, a smart phone, a tablet computer, a smart wearable device, a personal computer, a server, etc. In one embodiment, as shown in Fig. 8b, the accompaniment playback processing device 81 can include an acquisition unit 811 and a processing unit 812.

[0130] The obtaining unit 811 is used for displaying a user interface for receiving a selection indication for the target song, and for obtaining an accompaniment corresponding to the target song when the selection indication received in the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode.

[0131] The processing unit 812 is used for playing an accompaniment corresponding to the target song, where the accompaniment is generated based on a chorus dry voice and background music, the chorus dry voice is generated based on a plurality of dry voice signals in a dry voice signal set, the plurality of dry voice signals in the dry voice signal set correspond to a plurality of different virtual three-dimensional space sound image positions, and the dry voice signal set is obtained based on dry voice signals recorded by a plurality of users for the target song.

[0132] In one embodiment, the chorus dry sound is generated based on a virtual sound signal set, the virtual sound signal set including a virtual sound signal at each of the N virtual three-dimensional spatial sound image locations generated based on the derived dry sound signal set, the dry sound signals in the dry sound signal set corresponding to the N virtual three-dimensional spatial sound image locations, N being an integer greater than 1, the N virtual three-dimensional spatial sound image locations being different, and each virtual three-dimensional spatial sound image location being permitted to correspond to one or more dry sound signals.

[0133] In one embodiment, an accompaniment mode selection control for a target song is displayed on the user interface. The accompaniment mode selection control includes a chorus accompaniment mode selection control and an original accompaniment mode selection control. The processing unit 812 may be used to detect whether a selection operation on the chorus accompaniment mode selection control is acquired before acquiring an accompaniment corresponding to the target song. If the processing unit 812 detects that a selection operation on the chorus accompaniment mode selection control is acquired, the processing unit 812 may be used to confirm that the selection indication received on the user interface indicates that the accompaniment mode of the target song is the chorus accompaniment mode.

[0134] In one embodiment, the processing unit 812 can also be used to send an accompaniment request including the identification information of the target song to the server. The obtaining unit 811 can also be used to receive the chorus dry voice and background music returned by the server in response to the accompaniment request. The processing unit 812 can also be used to determine a target chorus dry voice segment from the chorus dry voice, and obtain an accompaniment corresponding to the target song based on the chorus dry voice corresponding to the target chorus dry voice segment and the background music.

[0135] In one embodiment, the processing unit 812 can also be used to display a first sentence interface, and display each sentence in the text data corresponding to the chorus dry voice according to a sequence of time play nodes of the chorus dry voice. The target chorus dry voice segment is determined based on a sentence selection operation on the first sentence interface.

[0136] In one embodiment, the processing unit 812 can also be used to display a second sentence interface and display each sentence in the text data corresponding to the accompaniment according to a sequence of the time reproduction nodes of the accompaniment. The processing unit 812 can also be used to detect whether a silent selection operation for the chorus dry voice in the accompaniment is obtained during the reproduction. If the processing unit 812 detects that a silent selection operation for the chorus dry voice in the accompaniment is obtained during the reproduction, it cancels the reproduction of the chorus dry voice at the current time reproduction node.

[0137] In addition, the contents not mentioned in the embodiment corresponding to Figure 8b and the specific implementation methods of each step can be referred to the embodiments shown in Figures 2 to 7c and the above-mentioned contents, so they will not be described again here.

[0138] Further referring to FIG. 9, FIG. 9 is a schematic block diagram of an electronic device according to an embodiment of the present application. The electronic device may include a network interface 901, a memory 902, and a processor 903. The network interface 901, the memory 902, and the processor 903 are connected by one or more communication buses. The communication buses are used to realize the connection and communication between these components. The network interface 901 may include a standard wired interface or a wireless interface (e.g., a WIFI interface). The memory 902 may include a volatile memory such as a random-access memory (RAM). The memory 902 may include a non-volatile memory such as a flash memory, a solid-state drive (SSD), and the like. The memory 902 may include a combination of the above types of memory. The processor 903 may be a central processing unit (CPU). The processor 903 may further include a hardware chip. The above hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), etc. The above PLD may be a field-programmable gate array (FPGA), a generic array logic (GAL), etc.

[0139] Optionally, the memory 902 can also be used to store program instructions that the processor 903 can invoke to achieve the following: Obtain a dry audio signal set, where the dry audio signal set includes x dry audio signals corresponding to the target song, where x is an integer greater than 1. A virtual audio signal is generated based on a dry audio signal corresponding to each virtual three-dimensional spatial sound image position of the N virtual three-dimensional spatial sound image positions, where x dry audio signals correspond to the N virtual three-dimensional spatial sound image positions, N being an integer greater than 1, and the N virtual three-dimensional spatial sound image positions are different, and each virtual three-dimensional spatial sound image position is permitted to correspond to one or more dry audio signals of the x dry audio signals. Each virtual audio signal in the virtual audio signal set is integrated to obtain a chorus dry audio. The virtual audio signal set includes a virtual audio signal at each virtual three-dimensional spatial sound image position among the N virtual three-dimensional spatial sound image positions. According to the sound effect optimization rules, sound effect synthesis processing is performed on the chorus dry sound and the background music of the target song to obtain the accompaniment of the target song.

[0140] In one embodiment, the processor 903 may also invoke program instructions to: obtain an initial dry audio signal set from an audio database, the audio database including initial dry audio signals recorded by multiple users singing the same song, select dry audio signals from the initial dry audio signal set based on audio parameters of each initial dry audio signal, and the selected dry audio signals constitute the dry audio signal set.

[0141] In one embodiment, the set of dry speech signals includes dry speech signals selected from the set of initial dry speech signals based on intonation characteristic parameters and timbre characteristic parameters, the intonation characteristic parameters including any one or more of a pitch parameter, a rhythm parameter, and a prosody parameter, and the timbre characteristic parameters including any one or more of a noise parameter, an energy parameter, and a rate parameter.

[0142] In one embodiment, the N virtual three-dimensional space sound image positions include n1 virtual three-dimensional space sound image positions in a horizontal plane obtained after dividing a horizontal plane at a first preset angle interval on the horizontal plane, n2 virtual three-dimensional space sound image positions in an upper plane obtained after dividing an upper plane at a second preset angle interval on the upper plane, and n3 virtual three-dimensional space sound image positions in a lower plane obtained after dividing a lower plane at a third preset angle interval on the lower plane. The angle between the upper plane and the horizontal plane is a first angle threshold, the angle between the lower plane and the horizontal plane is a second angle threshold, n1, n2, and n3 are positive integers, and the sum of n1, n2, and n3 is equal to N.

[0143] In one embodiment, the processor 903 may also invoke program instructions to achieve the following: Obtain a head-related transfer function corresponding to each virtual three-dimensional spatial sound image position among the N virtual three-dimensional spatial sound image positions; Process a dry audio signal corresponding to the target virtual three-dimensional spatial sound image position through the head-related transfer function corresponding to the target virtual three-dimensional spatial sound image position to obtain a virtual audio signal at the target virtual three-dimensional spatial sound image position; The virtual audio signal at the target virtual three-dimensional spatial sound image position is a binaural signal, and the target virtual three-dimensional spatial sound image position is any one of the N virtual three-dimensional spatial sound image positions.

[0144] In one embodiment, the virtual audio signal set further includes a delayed left channel signal and a delayed right channel signal corresponding to each of the p dry audio signals. The processor 903 may also call program instructions to achieve the following: Obtain p dry audio signals from the x dry audio signals included in the dry audio signal set, where p is a positive integer and is less than or equal to x. Perform delay processing of m1 time parameters on each of the p dry audio signals to obtain m1 delayed dry audio signals corresponding to each of the p dry audio signals, and superimpose the m1 delayed dry audio signals corresponding to each dry audio signal to obtain a delayed left channel signal corresponding to each of the p dry audio signals, where m1 is a positive integer. A delay process of m2 time parameters is performed on each of the p dry audio signals to obtain m2 delayed dry audio signals corresponding to each of the p dry audio signals, and the m2 delayed dry audio signals corresponding to each of the p dry audio signals are superimposed to obtain a delayed right channel signal corresponding to each of the p dry audio signals, where m2 is a positive integer.

[0145] In one embodiment, the processor 903 may also call program instructions to achieve the following: obtain background music of the target song; and adjust the energy relationship between the chorus dry voice and the background music; the energy relationship between the adjusted chorus dry voice and the adjusted background music satisfies an energy ratio condition; and an accompaniment is obtained based on the adjusted chorus dry voice and the background music.

[0146] In one embodiment, the processor 903 may also invoke program instructions to achieve the following: perform a spectral equalization process on the chorus dry voice in a preset frequency band; obtain the volume of the background music; and if the volume of the background music is lower than the volume threshold, increase the volume of the background music to the volume threshold. The accompaniment is obtained based on the chorus dry voice after the spectral equalization process and the background music after the volume process.

[0147] Optionally, the memory 902 can also be used to store program instructions that the processor 903 can invoke to achieve the following: A user interface is displayed for receiving a selection indication for the target song. If the selection indication received at the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode, an accompaniment corresponding to the target song is obtained. An accompaniment corresponding to a target song is played, the accompaniment being generated based on a chorus dry sound and background music, the chorus dry sound being generated based on a plurality of dry sound signals in a dry sound signal set, the plurality of dry sound signals in the dry sound signal set corresponding to a plurality of different virtual three-dimensional space sound image positions, and the dry sound signal set being obtained based on dry sound signals recorded by a plurality of users for the target song.

[0148] In one embodiment, the chorus dry sound is generated based on a virtual sound signal set, the virtual sound signal set including a virtual sound signal at each of the N virtual three-dimensional spatial sound image locations generated based on the derived dry sound signal set, the dry sound signals in the dry sound signal set corresponding to the N virtual three-dimensional spatial sound image locations, N being an integer greater than 1, the N virtual three-dimensional spatial sound image locations being different, and each virtual three-dimensional spatial sound image location being permitted to correspond to one or more dry sound signals.

[0149] In one embodiment, an accompaniment mode selection control for the target song is displayed on the user interface. The accompaniment mode selection control includes a chorus accompaniment mode selection control and an original accompaniment mode selection control. Before acquiring the accompaniment corresponding to the target song, the processor 903 may also call program instructions to achieve the following: Detect whether a selection operation on the chorus accompaniment mode selection control is acquired. If the processor 903 detects that a selection operation on the chorus accompaniment mode selection control is acquired, confirm that the selection indication received on the user interface indicates that the accompaniment mode of the target song is the chorus accompaniment mode.

[0150] In one embodiment, the processor 903 may also invoke program instructions to: send an accompaniment request including identification information of a target song to a server; receive a chorus dry voice and background music returned by the server in response to the accompaniment request; determine a target chorus dry voice segment from the chorus dry voice, and obtain an accompaniment corresponding to the target song based on the chorus dry voice corresponding to the target chorus dry voice segment and the background music.

[0151] In one embodiment, the processor 903 may also invoke program instructions to achieve the following: display a first sentence interface, and display each sentence in the text data corresponding to the chorus dry voice according to a sequence of time play nodes of the chorus dry voice; and determine a target chorus dry voice segment based on a sentence selection operation on the first sentence interface.

[0152] In one embodiment, the processor 903 may also invoke program instructions to achieve the following: Display a second sentence interface, and display each sentence in the text data corresponding to the accompaniment according to a sequence of the time reproduction nodes of the accompaniment. Detect whether a silent selection operation for the chorus dry voice in the accompaniment is obtained during the reproduction. If it is detected that a silent selection operation for the chorus dry voice in the accompaniment is obtained during the reproduction, cancel the reproduction of the chorus dry voice at the current time reproduction node.

[0153] As can be appreciated, the principles and beneficial effects of solving the problem by the electronic device 90 described in the embodiments of the present application are similar to the principles and beneficial effects of solving the problem in the embodiments shown in Figures 2 to 7c of the present application and the content described above, and therefore will not be repeated here for the sake of brevity.

[0154] In addition, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method according to the above-mentioned embodiment.

[0155] An embodiment of the present application further provides a computer program product or a computer program, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium, a processor of a computer device reading and executing the computer instructions from the computer-readable storage medium to cause the computer device to perform the method in the aforementioned embodiment.

[0156] The steps in the methods of the embodiments of the present application may be adjusted, combined or deleted according to actual needs.

[0157] The units in the device of the embodiment of the present application can be combined, divided or deleted according to actual needs.

[0158] As can be understood by those skilled in the art, all or part of the processes in the methods of the above embodiments can be realized by a computer program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, the processes of the above method embodiments can be included. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.

[0159] The above contents are only some of the embodiments of the present application and are not used to limit the scope of the claims of the present application. Those skilled in the art can understand and realize the whole or part of the operation of the above embodiments, and the equivalent changes made by those skilled in the art based on the claims of the present application still belong to the scope of coverage of the present application.

Claims

1. 1. An accompaniment generation method, comprising: Obtaining a dry audio signal set, the dry audio signal set including x dry audio signals corresponding to a target song, where x is an integer greater than 1; generating virtual audio signals based on dry audio signals corresponding to each virtual three-dimensional spatial sound image location among N virtual three-dimensional spatial sound image locations, the x dry audio signals corresponding to the N virtual three-dimensional spatial sound image locations, N being an integer greater than 1, the N virtual three-dimensional spatial sound image locations being different, and each virtual three-dimensional spatial sound image location being permitted to correspond to one or more dry audio signals among the x dry audio signals; Integrating each virtual audio signal in a virtual audio signal set to obtain a chorus dry audio, the virtual audio signal set including a virtual audio signal at each virtual three-dimensional spatial sound image position among N virtual three-dimensional spatial sound image positions; and performing a sound effect synthesis process on the chorus dry voice and the background music of the target song according to a sound effect optimization rule to obtain an accompaniment of the target song. The accompaniment generating method according to the present invention is characterized in that

2. The obtaining of the dry audio signal set includes: Obtaining a set of initial dry voice signals from an audio database, the audio database including initial dry voice signals recorded by a plurality of users while singing a target song; and selecting x number of dry audio signals from the initial set of dry audio signals based on audio parameters of each initial dry audio signal to form the dry audio signal set.

2. The method of claim 1 .

3. The voice parameters include an intonation characteristic parameter and a tone quality characteristic parameter, The intonation characteristic parameters include any one or more of a pitch parameter, a rhythm parameter, and a prosodic parameter, and the sound quality characteristic parameters include any one or more of a noise parameter, an energy parameter, and a speed parameter.

3. The method of claim 2 .

4. The N virtual three-dimensional space sound image positions are a first preset angle is set on the horizontal plane, and then n1 virtual three-dimensional space sound image positions on the horizontal plane are obtained after dividing the horizontal plane at intervals of the first preset angle; n2 virtual three-dimensional space sound image positions on the upper plane obtained by dividing the upper plane at intervals of a second preset angle; and n3 virtual three-dimensional space sound image positions on the lower plane obtained by dividing the lower plane at intervals of a third preset angle on the lower plane; an angle between the upper plane and the horizontal plane is a first angle threshold, an angle between the lower plane and the horizontal plane is a second angle threshold, n1, n2, and n3 are positive integers, and the sum of n1, n2, and n3 is equal to N; 2. The method of claim 1 .

5. The generating of the virtual sound signal based on the dry sound signal corresponding to each of the N virtual three-dimensional space sound image positions includes: Obtaining a head-related transfer function (HRTF) corresponding to each of the N virtual three-dimensional space sound image positions; and processing the dry sound signal corresponding to the target virtual three-dimensional space sound image position through a head-related transfer function corresponding to the target virtual three-dimensional space sound image position to obtain a virtual sound signal at the target virtual three-dimensional space sound image position; the virtual sound signal at the target virtual three-dimensional space sound image position is a binaural signal; The target virtual three-dimensional space sound image position is any one of the N virtual three-dimensional space sound image positions.

5. The method according to claim 1, wherein the first and second electrodes are arranged in a first direction.

6. the set of virtual audio signals further includes a delayed left channel signal and a delayed right channel signal corresponding to each dry audio signal of the p dry audio signals; Before the step of aggregating each virtual sound signal in the set of virtual sound signals to obtain a chorus dry sound, the method further comprises: obtaining p dry audio signals from the x dry audio signals included in the set of dry audio signals, where p is a positive integer less than or equal to x; performing delay processing of m1 time parameters on each of the p dry audio signals to obtain m1 delayed dry audio signals corresponding to each of the p dry audio signals, and superimposing the m1 delayed dry audio signals corresponding to each of the p dry audio signals to obtain a delayed left channel signal corresponding to each of the p dry audio signals, where m1 is a positive integer; performing a delay process of m2 time parameters on each of the p dry audio signals to obtain m2 delayed dry audio signals corresponding to each of the p dry audio signals, and superimposing the m2 delayed dry audio signals corresponding to each of the p dry audio signals to obtain a delayed right channel signal corresponding to each of the p dry audio signals, where m2 is a positive integer.

5. The method according to claim 1, wherein the first and second electrodes are arranged in a first direction.

7. According to the sound effect optimization rule, a sound effect synthesis process is performed on the chorus dry sound and the background music of the target song to obtain an accompaniment of the target song. Obtaining background music of the target song, and adjusting the energy relationship between the chorus dry voice and the background music, so that the energy relationship between the adjusted chorus dry voice and the adjusted background music satisfies an energy ratio condition; and obtaining the accompaniment based on the adjusted chorus dry voice and background music.

5. The method according to claim 1, wherein the first and second electrodes are arranged in a first direction.

8. According to the sound effect optimization rule, a sound effect synthesis process is performed on the chorus dry sound and the background music of the target song to obtain an accompaniment of the target song. performing a spectral equalization process on the chorus dry voice in a preset frequency band; obtaining a volume of the background music; if the volume of the background music is less than a volume threshold, increasing the volume of the background music to a volume threshold; and obtaining the accompaniment based on the chorus dry voice after a spectral equalization process and the background music after a volume process.

5. The method according to claim 1, wherein the first and second electrodes are arranged in a first direction.

9. A method for playing back accompaniment, comprising the steps of: displaying a user interface for receiving a selection indication for a target song; obtaining an accompaniment corresponding to the target song when the selection indication received at the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode; and playing an accompaniment corresponding to the target piece of music; The accompaniment is generated based on a chorus dry sound and background music, the chorus dry sound is generated based on a plurality of dry sound signals in a dry sound signal set, the plurality of dry sound signals in the dry sound signal set correspond to a plurality of different virtual three-dimensional space sound image positions, and the dry sound signal set is obtained based on dry sound signals recorded by a plurality of users for the target song.

13. A method for reproducing and processing accompaniment comprising the steps of:

10. The chorus dry sound is generated based on a virtual sound signal set, the virtual sound signal set including a virtual sound signal at each of N virtual three-dimensional space sound image positions generated based on the obtained dry sound signal set, the dry audio signals in the dry audio signal set correspond to N virtual three-dimensional spatial sound image positions, N being an integer greater than 1, the N virtual three-dimensional spatial sound image positions being distinct, and each virtual three-dimensional spatial sound image position being permitted to correspond to one or more dry audio signals; 10. The method of claim 9.

11. The user interface displays an accompaniment mode selection control for a target song, the accompaniment mode selection control including a chorus accompaniment mode selection control and an original accompaniment mode selection control; and before obtaining the accompaniment corresponding to the target song, the method further comprises: detecting whether or not a selection operation on the chorus accompaniment mode selection control has been acquired; When detecting that a selection operation on the chorus accompaniment mode selection control is acquired, confirming that a selection indication received on the user interface indicates that the accompaniment mode of the target song is a chorus accompaniment mode.

11. The method according to claim 9 or 10.

12. The step of acquiring an accompaniment corresponding to the target piece of music includes: sending a request for accompaniment to a server, the request including an identification of the target piece of music; receiving the chorus dry voice and the background music returned by the server in response to the accompaniment request; determining a target chorus dry voice segment from the chorus dry voice; and obtaining an accompaniment corresponding to the target song based on a chorus dry voice corresponding to the target chorus dry voice segment and the background music.

10. The method of claim 9.

13. Before determining the target chorus dry voice segment from the chorus dry voice, the method further comprises: displaying a first sentence interface, and displaying each sentence in the text data corresponding to the chorus dry voice according to a sequence of time playback nodes of the chorus dry voice; The target chorus dry voice segment is determined based on a sentence selection operation on the first sentence interface.

13. The method of claim 12.

14. After said playing back the accompaniment corresponding to the target song, the method further comprises: Displaying a second sentence interface, displaying each sentence in the text data corresponding to the accompaniment according to a sequence of time play nodes of the accompaniment; Detecting whether a silent selection operation for the chorus dry voice in the accompaniment is acquired during playback; canceling the playback of the chorus dry voice at a current time playback node when detecting that a silent selection operation for the chorus dry voice in the accompaniment is acquired during playback; 13. The method according to claim 9 or 12.

15. An electronic device comprising a memory, a processor, and a network interface, the processor is connected to the memory and the network interface, the network interface being used to provide a network communication function, the memory being used to store a program code, and the processor being used to call the program code to execute the method according to any one of claims 1 to 14.

1. An electronic device comprising:

16. A computer-readable storage medium having a computer program stored thereon, When the computer program is executed by a processor, the method according to any one of claims 1 to 14 is realized. A computer-readable storage medium comprising:

Citation Information

Patent Citations

  • Karaoke device

    JP1996292774A

  • Voice mixing down apparatus and voice mixing down program

    JP2008051896A

  • Signal processing device, method, and program

    WO2021065496A1