Audio production method, medium, apparatus, and computing device

Abstract

Embodiments of the present disclosure provide an audio production method, medium, device and computing device, relating to the technical field of digital signal processing. The method comprises: obtaining a target chord related to a sweep chord generated based on a composition template; mapping the target chord on a single note MIDI key position to obtain a target single note MIDI track; determining a target sample file corresponding to the target single note MIDI track based on a mapping relationship between sample files in a sample library of a soft sound source corresponding to a sweep chord track and the single note MIDI track; and applying the target single note MIDI track to the target sample file based on an engine of the soft sound source to render the target sample file and obtain audio corresponding to the target chord. The present disclosure can improve the authenticity of the performance effect when performing a sweep chord based on a composition template. In addition, the embodiments of the present disclosure provide a medium, an audio production device and a computing device.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of digital signal processing technology, and more specifically, to audio production methods, media, apparatus, and computing devices. Background Technology

[0002] This section is intended to provide background or context for embodiments of this disclosure. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] Artificial intelligence (AI) music composition refers to the process of using artificial intelligence technology to automatically generate or assist in the creation of music. With the advancement of machine learning and deep learning technologies, AI music composition has made significant progress.

[0004] Currently, by incorporating a Musical Instrument Digital Interface (MIDI) and software sound sources within an AI music composition module that includes tracks for different instruments, users can perform MIDI music on various instruments. However, the realism of the performance is poor when strumming through this AI music composition module. Summary of the Invention

[0005] This disclosure provides an audio production method, medium, apparatus, and computing device to solve the problem of poor performance realism when performing strumming through existing AI music composition modules.

[0006] In a first aspect of this disclosure, an audio production method is provided, comprising:

[0007] Obtain the target chord, which is a strumming-related chord generated based on the arrangement template;

[0008] Map the target chord onto the Musical Instrument Digital Interface (MIDI) keys to obtain the target single-note MIDI track;

[0009] Based on the mapping relationship between the sample files in the sample library corresponding to the soft sound source of the strumming track and the single note MIDI track, the target sample file corresponding to the target single note MIDI track is determined. The sample files in this sample library correspond one-to-one with the chords contained in the arrangement template.

[0010] Based on a soft-source engine, the target sample file is rendered using a target single-note MIDI track to obtain the audio corresponding to the target chord.

[0011] In one possible implementation, a single-note MIDI track is obtained as follows:

[0012] Obtain the first chord list; for each predefined chord in the first chord list, determine the chord type corresponding to the other notes in the predefined chord except the root note; combine the chord types with different predefined root notes to obtain the chords contained in the arrangement template; for each chord contained in the arrangement template, map the chord to a MIDI key to obtain a single-note MIDI track.

[0013] In one possible implementation, the soft audio source is tested and passed in the following way:

[0014] Obtain the multinote MIDI track corresponding to the strumming track; obtain the second chord list corresponding to the multinote MIDI track based on the multinote MIDI track; obtain the single-note MIDI track corresponding to the multinote MIDI track based on the second chord list; determine the sample file corresponding to the single-note MIDI track based on the mapping relationship between the sample files in the sample library of the soft source corresponding to the strumming track and the single-note MIDI track; render the sample file using the single-note MIDI track based on the soft source engine.

[0015] In one possible implementation, obtaining a second chord list corresponding to a multinote MIDI track based on the multinote MIDI track includes: parsing the multinote MIDI track and extracting at least one note interval from the parsed multinote MIDI track, where each note interval represents a chord; for each note interval, determining the chord name corresponding to the note interval based on a chord recognition algorithm; and determining the set of chord names as the second chord list.

[0016] In one possible implementation, the chord name corresponding to the note interval is determined based on a chord recognition algorithm, including: determining the root note from the notes included in the note interval; arranging all notes above the root note in octave increments according to pitch from low to high to obtain the chord property corresponding to the note interval; and determining the chord name corresponding to the note interval based on the chord property.

[0017] In one possible implementation, the audio production method further includes: generating a target multinote MIDI track corresponding to the target single-note MIDI track; and outputting the target multinote MIDI track.

[0018] In one possible implementation, generating a target multinote MIDI track corresponding to a target single-note MIDI track includes: determining the chord name corresponding to the target single-note MIDI track based on the target sample file; determining all notes of the chord corresponding to the chord name based on a chord recognition algorithm; and generating the target multinote MIDI track based on all notes.

[0019] In one possible implementation, the soft source further includes a soft source type. Based on the soft source engine, the target sample file is rendered using a target single-note MIDI track to obtain audio corresponding to the target chord. This includes: determining the soft source type corresponding to the target sample file, where the soft source type includes a first source type and a second source type; if the soft source type is the first source type, a first MIDI control signal is sent to the soft source engine, the first MIDI control signal carrying the target single-note MIDI track and the target sample file, and the engine is used to render the target sample file using the target single-note MIDI track to obtain audio corresponding to the target chord; if the soft source type is the second source type, a second MIDI control signal is sent to the soft source engine, the second MIDI control signal carrying the target single-note MIDI track and the target sample file, and the engine is used to render the target sample file using the target single-note MIDI track to obtain audio corresponding to the target chord.

[0020] In a second aspect of this disclosure, an audio production apparatus is provided, comprising:

[0021] The acquisition module is used to acquire the target chord, which is a strumming-related chord generated based on the arrangement template;

[0022] The mapping module is used to map the target chord onto single-note MIDI keys to obtain the target single-note MIDI track.

[0023] The determination module is used to determine the target sample file corresponding to the target single note MIDI track based on the mapping relationship between the sample files in the sample library of the soft sound source corresponding to the strumming track and the single note MIDI track. The sample files in this sample library correspond one-to-one with the chords contained in the arrangement template.

[0024] The rendering module is used by the software-based engine to render the target sample file using the target single-note MIDI track, thereby obtaining the audio corresponding to the target chord.

[0025] In one possible implementation, a single-note MIDI track is obtained as follows:

[0026] Obtain the first chord list; for each predefined chord in the first chord list, determine the chord type corresponding to the other notes in the predefined chord except the root note; combine the chord types with different predefined root notes to obtain the chords contained in the arrangement template; for each chord contained in the arrangement template, map the chord to a MIDI key to obtain a single-note MIDI track.

[0027] In one possible implementation, the soft audio source is tested and passed in the following way:

[0028] Obtain the multinote MIDI track corresponding to the strumming track; obtain the second chord list corresponding to the multinote MIDI track based on the multinote MIDI track; obtain the single-note MIDI track corresponding to the multinote MIDI track based on the second chord list; determine the sample file corresponding to the single-note MIDI track based on the mapping relationship between the sample files in the sample library of the soft source corresponding to the strumming track and the single-note MIDI track; render the sample file using the single-note MIDI track based on the soft source engine.

[0029] In one possible implementation, the audio production apparatus further includes a processing module for: parsing a multinote MIDI track and extracting at least one note interval from the parsed multinote MIDI track, wherein one note interval represents a chord; for each note interval, determining the chord name corresponding to the note interval based on a chord recognition algorithm; and determining the set of chord names as a second chord list.

[0030] In one possible implementation, the processing module is further configured to: determine the root note from the notes included in the note interval; arrange all notes above the root note in octaves in order of pitch from low to high to obtain the chord properties corresponding to the note interval; and determine the chord name corresponding to the note interval based on the chord properties.

[0031] In one possible implementation, the audio production apparatus further includes a generation module for: generating a target multinote MIDI track corresponding to the target single-note MIDI track; and outputting the target multinote MIDI track.

[0032] In one possible implementation, the generation module is further configured to: determine the chord name corresponding to the target single-note MIDI track based on the target sample file; determine all notes of the chord corresponding to the chord name based on a chord recognition algorithm; and generate the target multi-note MIDI track based on all notes.

[0033] In one possible implementation, the soft source further includes a soft source type. The rendering module is specifically used to: determine the soft source type corresponding to the target sample file, whereby the soft source type includes a first source type and a second source type; if the soft source type is the first source type, then send a first MIDI control signal to the soft source engine, the first MIDI control signal carrying the target single-note MIDI track and the target sample file, the engine being used to render the target sample file using the target single-note MIDI track to obtain audio corresponding to the target chord; if the soft source type is the second source type, then send a second MIDI control signal to the soft source engine, the second MIDI control signal carrying the target single-note MIDI track and the target sample file, the engine being used to render the target sample file using the target single-note MIDI track to obtain audio corresponding to the target chord.

[0034] In a third aspect of the present disclosure, a computing device is provided, including: a processor and a memory communicatively connected to the processor;

[0035] The memory stores instructions that the computer executes;

[0036] The processor executes computer execution instructions stored in memory to implement the audio production method provided in the first aspect of this disclosure.

[0037] In a fourth aspect of the present disclosure, a storage medium is provided that stores computer program instructions, which, when executed, implement the audio production method provided in the first aspect of the present disclosure.

[0038] In a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed, implements the audio production method provided in the first aspect of the present disclosure.

[0039] The audio production method, medium, apparatus, and computing device disclosed herein improve the realism of the performance when strumming based on an arrangement template. This is achieved by acquiring a target chord related to strumming generated from an arrangement template, mapping the target chord onto single-note MIDI keys to obtain a target single-note MIDI track, determining the target sample file corresponding to the single-note MIDI track based on the mapping relationship between sample files in the sample library of the soft source corresponding to the strumming track, and rendering the target sample file using the target single-note MIDI track based on the soft source engine. Furthermore, by designing the soft source corresponding to the strumming track and the mapping relationship between sample files in the soft source sample library and single-note MIDI tracks, and by rendering the target sample file corresponding to the target single-note MIDI track using the soft source engine, this disclosure enhances the user experience. Attached Figure Description

[0040] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0041] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0042] Figure 2 A flowchart illustrating an audio production method provided in an embodiment of this disclosure;

[0043] Figure 3 A flowchart illustrating the method for obtaining a single-note MIDI track according to embodiments of this disclosure;

[0044] Figure 4 A flowchart illustrating the testing and pass procedures for a software audio source provided in this embodiment of the disclosure;

[0045] Figure 5 A logical diagram illustrating chord property determination provided in an embodiment of this disclosure;

[0046] Figure 6 A schematic diagram illustrating the mapping of a multinote MIDI track to a single-note MIDI track, provided for embodiments of this disclosure;

[0047] Figure 7 A schematic diagram of a storage medium provided in an embodiment of this disclosure;

[0048] Figure 8 This is a schematic diagram of the structure of an audio production apparatus provided in an embodiment of the present disclosure;

[0049] Figure 9 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present disclosure.

[0050] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0051] The principles and spirit of this disclosure will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0052] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0053] According to embodiments of this disclosure, an audio production method, medium, apparatus, and computing device are proposed.

[0054] In this article, it is important to understand that the terms used have the following meanings:

[0055] Terminology 1: Composition and Arrangement: Composition is the process by which musicians create entirely new musical works based on their inspiration and understanding, through the creative arrangement of melody, harmony, and rhythm. Arrangement, on the other hand, is a musical creation activity based on existing musical materials. Arrangement involves rearranging and designing various musical elements to generate new musical works and giving them a specific musical style and form.

[0056] Term 2, MIDI: MIDI is a digital protocol used to transmit music information between electronic music devices. MIDI signals contain data on musical parameters such as notes, pitch, volume, and timbre, as well as control instructions and time encoding information. A "MIDI file" is a specific format of computer file that contains musical information such as notes, volume, and timbre recorded as MIDI signals. Due to their small file size and high editability, MIDI files are widely used in electronic music production and communication. In this disclosure, MIDI files are used as a medium for storing information about the works of composers.

[0057] Term 3, Software Audio Provider: Also known as a virtual instrument, it refers to a software entity that generates instrument sounds through MIDI signals. It is often sold as a plugin for digital music production. Software audio providers are divided into two types:

[0058] ① The sampler sound source consists of a sampling library / audio processing algorithm and can simulate real musical instruments;

[0059] ② Synthesizer sound source, composed of wavetable synthesis algorithm / audio processing algorithm, can generate synthesized timbres.

[0060] Term 4, Sampler Source: This comprises three parts: a sample library / tone library, an engine, and presets. Only after all three parts are determined can the rendering effect of the software source be uniquely determined. Among them:

[0061] ① Sample library / tone library: usually contains samples of different pitches, different key pressures, and different techniques;

[0062] ② Engine: Implements all control logic for MIDI and the sampling library, as well as sampling rendering logic;

[0063] ③ Preset: Defines the configuration, informing the engine how to control and render the MIDI and sampling libraries.

[0064] Term 5, Software Arrangement: refers to the process in a Digital Audio Workstation (DAW) where the arranger inputs MIDI signals via a MIDI keyboard to drive software hardware plugins to play / render sounds, thereby producing the instrumental parts of a musical work.

[0065] Term 6, Strumming: refers to a technique for playing chords on a guitar. Its unit is a loop of a certain chord and rhythm pattern played as a measure (strumming rhythm patterns can be further subdivided into techniques such as upsweep, downsweep, and muted sweep, but this disclosure does not consider such fine details); for common guitar sound sources, the arranger needs to select a certain rhythm pattern and then input the chord using a MIDI keyboard (pressing multiple notes at the same time) to trigger the strumming performance.

[0066] Terminology 7, Single-Note MIDI and Multi-Note MIDI: Single-note MIDI means that pressing one note on the MIDI input device triggers one sound, while multi-note MIDI means that pressing multiple notes on the MIDI input device triggers one sound. Multi-note MIDI is often used for advanced techniques such as guitar strumming.

[0067] Term 8, NetEase Tianyin: This is an AI music production website that includes an AI arrangement module. This module provides hundreds of arrangement style templates. In terms of technical backend: Each arrangement template consists of a set of MIDI and software sound sources (containing various instrument tracks). In styles like pop and rock, there will be some guitar strumming tracks to varying degrees.

[0068] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0069] Furthermore, the number of any elements in the accompanying drawings is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0070] The principles and spirit of this disclosure will be explained in detail below with reference to several representative embodiments. SUMMARY

[0072] The inventors have discovered that the chords played by strumming, such as those played on a guitar, are determined by the physical properties of the guitar, resulting in fewer notes compared to a piano, often with note omissions. Therefore, the MIDI track-to-chord recognition method differs from that of other instruments when playing guitar strumming. Furthermore, the software source design for guitar strumming differs from that of piano chords; it cannot simply be achieved by sampling and superimposing multiple single notes within a chord. Piano chords, in their sound production principle, are indeed formed by superimposing multiple single note samples.

[0073] Currently, there are several types of software sound sources for guitar strumming: First, one can simulate strumming by superimposing multiple single-note samples. However, this software source also adds many undisclosed audio processing technologies to make the guitar strumming sound closer to a realistic performance. These undisclosed audio processing technologies are unavailable, therefore, simply using multiple single-note samples to simulate strumming results in a less realistic performance. Second, each chord is analyzed into two parts: ① one basic strumming loop sample (composed of the root note and the fifth note) ② one single-note sample that determines the chord's properties. However, this type of software source is a commercial solution and cannot be directly obtained; furthermore, its development cost is high.

[0074] Because the soft sound sources set up inside the AI ​​arrangement module, which contains tracks for different instruments, are not suitable for guitar strumming, the performance of guitar strumming MIDI based on this AI arrangement module is not very realistic.

[0075] To address the aforementioned issues, this disclosure provides an audio production method, medium, apparatus, and computing device. By designing a soft sound source suitable for strumming, and a mapping relationship between sample files in the soft sound source's sample library and single-note MIDI tracks, and establishing an arrangement template, strumming-related chords generated based on the arrangement template, and mapping control logic between the soft sound source and single-note MIDI tracks, the method enables the rendering of strumming-related chords generated based on the arrangement template to obtain audio corresponding to the chords, thereby improving the realism of the performance effect during strumming.

[0076] After introducing the basic principles of this disclosure, various non-limiting embodiments of this disclosure will be described in detail below.

[0077] OVERVIEW OF APPLICATION SCENARIOS

[0078] First refer to Figure 1 Examples of application scenarios for the solutions provided in this disclosure are given.

[0079] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure, such as... Figure 1 As shown, this application scenario includes a client. The client can be a desktop computer, laptop, tablet, etc. For example, the user selects a strumming arrangement template in the AI ​​arrangement module of the client interface, generates strumming-related chords based on the template, maps these chords onto single-note MIDI keys via the client, obtaining a single-note MIDI track. Based on the mapping relationship between sample files in the sample library of the corresponding soft sound source and the single-note MIDI track, the user determines the sample file corresponding to the single-note MIDI track. Further, based on the soft sound source engine, the user renders the sample file using the single-note MIDI track to obtain the audio corresponding to the chord, and then exports this audio using the export control on the client interface.

[0080] In some alternative embodiments, the scenario may also include a server.

[0081] In this context, a server is a business unit that provides data processing, database, and other functions. A server can be a monolithic server or a distributed server spanning multiple computers or a computer data center. A server can include hardware, software, or embedded logical components or combinations of two or more such components to perform the appropriate functions supported or implemented by the server. Examples of servers include blade servers, cloud servers, or server clusters composed of multiple servers.

[0082] The client and server can communicate via a wired or wireless network. In this embodiment, the server can perform some of the client's functions.

[0083] For example, a user selects a strumming arrangement template in the AI ​​arrangement module of the client interface and generates strumming-related chords based on the template. The client sends the chords to the server, which, upon receiving the chords, maps them onto single-note MIDI keys to obtain a single-note MIDI track. Based on the mapping relationship between sample files in the sample library of the soft source corresponding to the strumming track and the single-note MIDI track, the server determines the sample file corresponding to the single-note MIDI track. Furthermore, based on the soft source engine, the server renders the sample file using the single-note MIDI track to obtain the audio corresponding to the chords and sends the audio to the client. The user then exports the audio using the export control on the client interface.

[0084] For example, the AI ​​music arrangement module in the client interface includes guitar strumming. Accordingly, the arrangement template can contain guitar strumming tracks.

[0085] It is understood that one specific application scenario of this disclosure embodiment can be audio production suitable for guitar strumming tracks.

[0086] As can be seen, the embodiments of this disclosure can be performed through a client or through the interaction between the client and the server.

[0087] It should be noted that, Figure 1 This is merely a schematic diagram illustrating one application scenario provided by an embodiment of this disclosure; this embodiment does not necessarily represent an application scenario. Figure 1 The included equipment is not limited, nor is it restricted. Figure 1 The positional relationships between the devices are defined.

[0088] Exemplary Method

[0089] The following is combined Figure 1 Application scenarios, refer to Figure 1 This document describes a method for audio production according to exemplary embodiments of the present disclosure. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in any way. Rather, the embodiments of the present disclosure can be applied to any applicable scenario.

[0090] The audio production method provided in this disclosure will be described in detail below with reference to specific embodiments.

[0091] Figure 2This is a flowchart illustrating an audio production method according to an embodiment of the present disclosure. The method of this embodiment can be applied to a computing device, such as a client. Figure 2 As shown, the specific implementation of this audio production method includes the following steps:

[0092] S201, Obtain the target chord, which is a strumming-related chord generated based on the arrangement template.

[0093] For example, the arrangement template can be an arrangement template that includes a strumming track in the AI ​​arrangement module. The instrument to which this arrangement template is applicable can be a guitar, that is, the strumming track can be a guitar strumming track.

[0094] In one possible implementation, users can edit chords based on the arrangement templates contained in the AI ​​arrangement module of the client interface to obtain the target chords.

[0095] For example, the target chord can be a triad, a seventh chord, or something similar.

[0096] S202 maps the target chord to single-note MIDI keys to obtain the target single-note MIDI track.

[0097] For example, a single-note MIDI key means that pressing a MIDI key will trigger a chord sound.

[0098] One possible implementation is to establish a relationship between chords and single-note MIDI keys, and based on this mapping relationship, map the target chord onto the single-note MIDI keys to obtain the target single-note MIDI track.

[0099] S203, based on the mapping relationship between the sample files in the sample library of the soft sound source corresponding to the strumming track and the single note MIDI track, determines the target sample file corresponding to the target single note MIDI track. The sample files in this sample library correspond one-to-one with the chords contained in the arrangement template.

[0100] For example, in the audio production method provided in this disclosure embodiment, the soft sound source corresponding to the strumming track can be a sound source with a single note MIDI control of a single sample file format.

[0101] For example, a software audio source includes a sample library, an engine, and presets. The sample library can be a loop sample library for guitar strumming, and the number of presets can be one or more. This embodiment does not limit the number of presets in the software audio source; it can be determined based on actual application requirements.

[0102] For example, sample files in the guitar strumming loop sample library can be audio files that you have recorded yourself.

[0103] For example, the sampling file can be in one or more of the following formats: wav, flac, and ogg.

[0104] Understandably, each sample file in the sample library is used to represent a chord.

[0105] For example, the arrangement template contains a predefined chord list. The sample files in the sample library correspond one-to-one with the chords in the predefined chord list.

[0106] For example, in the audio production method provided in this disclosure embodiment, the soft source corresponding to the strumming track may also include the mapping relationship between the sample files in the sample library of the soft source and the single note MIDI track.

[0107] S204 is a software-based engine that uses a target single-note MIDI track to render the target sample file, resulting in audio corresponding to the target chord.

[0108] For example, the engine of a soft source is used to render a target sample file using a target single-note MIDI track to obtain audio corresponding to the target chord.

[0109] In this embodiment, a target chord is obtained and mapped onto single-note MIDI keys to create a target single-note MIDI track. Based on the mapping relationship between sample files in the sample library of the soft source corresponding to the strumming track and the single-note MIDI track, the target sample file corresponding to the target single-note MIDI track is determined. Using the soft source engine, the target sample file is rendered using the target single-note MIDI track to obtain the audio corresponding to the target chord. The target chord is a strumming-related chord generated based on an arrangement template. This embodiment improves the realism of the performance effect when strumming based on the arrangement module by designing the soft source corresponding to the strumming track, the mapping relationship between sample files in the soft source sample library and the single-note MIDI track, and rendering the target sample file corresponding to the target single-note MIDI track using the soft source engine. Simultaneously, because users using the arrangement module are completely unaware of any processing performed on the strumming track by the client, the user experience is enhanced.

[0110] Understandably, compared to related technologies, the use cases for arrangement templates are primarily for instrument users to perform MIDI music or for end-users to play instruments for entertainment. In the audio production method disclosed herein, the use case for arrangement templates can be to use strumming as one type of instrument sound source for the arrangement template, enabling users to create audio based on the arrangement template.

[0111] The following is combined Figure 3The method for obtaining single-note MIDI tracks provided in the embodiments of this disclosure will be described in detail.

[0112] Figure 3 A flowchart illustrating how a single-note MIDI track is obtained, as provided in an embodiment of this disclosure.

[0113] like Figure 3 As shown, obtaining this single-note MIDI track can include the following steps:

[0114] S301, Get the list of first chords.

[0115] For example, the first chord list is obtained from the AI ​​composing module.

[0116] Table 1 is a list of first chords provided in the embodiments of this disclosure.

[0117] As shown in Table 1, the chords in the first chord list can be chords with C as the root note, which are suitable for guitar strumming, such as triads and seventh chords.

[0118] As shown in Table 1, in triads / suspended chords, the chord with the name Cmaj consists of the root note C and notes 1, 3, and 5; the chord with the name Cmin consists of the root note C and notes 1, b3, and 5.

[0119] In Table 1, note 3 indicates a major third; note b3 indicates a minor third; note 2 indicates a major second without a third; note 4 indicates a perfect fourth without a third; note (5) indicates a perfect fifth without a fifth; note #5 indicates an augmented fifth; note b5 indicates a diminished fifth; note 7 indicates a major seventh with a seventh; note b7 indicates a minor seventh with a seventh; note 6 indicates a major sixth without a seventh; and note 9 or 2 indicates a major ninth with either a ninth or a second.

[0120] It should be noted that in Table 1, the numbers 1, 3 and 5 in note 1, note 3 and note 5 are used to indicate the interval between the note and the root note. Note (5) is used to indicate that the 5th note can be omitted on the guitar.

[0121] Table 1

[0122]

[0123] It should be noted that the chord list shown in Table 1 is a chord list defined by the business based on the arrangement habits, and provides users with any note as the root note of the inversion. However, the technical backend of the client does not consider the inversion chords. The "inverted chord" can be approximated to a certain "root position chord" in the chord list, such as Am / C being equivalent to C6 chord.

[0124] S302, for each predefined chord in the first chord list, determine the chord type corresponding to the other notes in the predefined chord except the root note; combine the chord types with different predefined root notes to obtain the chords contained in the arrangement template.

[0125] For example, taking the Cmaj chord shown in Table 1 above as a predefined chord, the root note of this chord is C, and the other notes besides the root note are the 1st note, the 3rd note, and the 5th note. The chord type corresponding to the other notes can be represented as maj.

[0126] For example, taking the predefined chord as the Cmaj chord shown in Table 1 above, the root note of this chord is C. The chord types maj corresponding to the other notes besides the root note are combined with the root notes A, B, D, E, F and G respectively to obtain the chords Amaj, Bmaj, Dmaj, Emaj, Fmaj and Gmaj.

[0127] In one possible implementation, for each predefined chord shown in Table 1 above, the chord type maj corresponding to the other notes in the chord (excluding the root note) is combined with the root note A, root note B, root note D, root note E, root note F, and root note G respectively to obtain different chords, and the set of all the obtained chords is used as the chords included in the arrangement template.

[0128] S303 maps each chord in the arrangement template to a MIDI key, resulting in a single-note MIDI track.

[0129] For example, a single-note MIDI track can also be described as a single-note MIDI file.

[0130] In this step, by mapping a chord to a MIDI key, it is possible to trigger a chord note each time a MIDI key is pressed on a MIDI device.

[0131] It should be noted that the chords shown in Table 1 above include triads / suspended chords, as well as seventh chords and their derivatives. Triads / suspended chords are described as Type A chords, of which there are 6 types, while seventh chords and their derivatives are described as Type B chords, of which there are 8 types. Since there are 12 keys within an octave corresponding to 12 root note chords, we can calculate that there are 72 Type A chords and 96 Type B chords. However, a MIDI keyboard has a total of 108 notes, meaning it contains 108 MIDI keys. Therefore, a single MIDI keyboard cannot map 72+96 chords. Based on this, the audio production method provided in this disclosure assigns Type A chords and Type B chords to the 108 MIDI keys of two software presets, and uses MIDI control signals (Programs) to switch between these two presets.

[0132] In this embodiment of the disclosure, a first chord list is obtained, and for each predefined chord in the first chord list, the chord type corresponding to the other notes in the predefined chord (excluding the root note) is determined. The chord types are combined with different predefined root notes to obtain the chords contained in the arrangement template. Furthermore, for each chord contained in the arrangement template, the chord is mapped to a MIDI key to obtain a single-note MIDI track that can be used to render the sample file in the soft source corresponding to the strumming track.

[0133] Compared to related technologies, there is a lack of software sound sources suitable for strumming tracks, such as guitar strumming tracks. The audio production method provided in this disclosure includes a software sound source designed for strumming tracks. This software sound source is tested based on existing multinote MIDI tracks to obtain a rendering link suitable for strumming tracks, enabling the strumming tracks to be correctly rendered by the software sound source and improving the realism of the performance during strumming.

[0134] The following is combined Figure 4 The testing methods for the software audio source provided in the embodiments of this disclosure will be described in detail.

[0135] Figure 4 A flowchart illustrating the testing method for the software audio source provided in this embodiment of the disclosure. Figure 4 As shown, the testing process for this soft audio source may include the following steps:

[0136] S401 retrieves the multinote MIDI track corresponding to the strumming track.

[0137] For example, the strumming track can be a guitar strumming track.

[0138] One possible implementation involves exporting a multi-note MIDI track from the strumming track separately within the AI ​​composition module that includes guitar strumming.

[0139] For example, this multinote MIDI track can be created by a professional arranger.

[0140] S402: Based on the multinote MIDI track, obtain the list of second chords corresponding to the multinote MIDI track.

[0141] For example, the second chord list is similar to the chord list shown in Table 1 above, and will not be repeated here.

[0142] It is understood that the chords included in the second chord list can be one or more chords from the first chord list shown in Table 1 above.

[0143] Optionally, in one possible implementation, a multinote MIDI track is parsed, and at least one note interval included in the multinote MIDI track is extracted from the parsed multinote MIDI track, where a note interval is used to represent a chord; for each note interval, the chord name corresponding to the note interval is determined based on a chord recognition algorithm; and the set of chord names is determined as a second chord list.

[0144] For example, after parsing a multinote MIDI track, you can query the start time (note-on) and end time (note-off) of the notes from the parsed multinote MIDI track, and call the interval corresponding to each start time and end time a note interval.

[0145] One note interval is used to represent one chord, that is, one note interval can correspond to one chord name.

[0146] Based on chord recognition algorithms, the chord names corresponding to note intervals are determined. One possible implementation involves identifying the root note from the notes included in the note interval; arranging all notes above the root note in octave increments according to pitch from low to high to obtain the chord properties corresponding to the note interval; and then determining the chord names corresponding to the note interval based on the chord properties.

[0147] For example, determining the root note from the notes included in a note interval can be achieved by identifying the lowest note in the note interval as the root note, without considering transitions. The root note can be root note A, root note B, root note C, root note D, root note E, root note F, or root note G.

[0148] If we consider all notes above the root note as an octave, we can understand that when the note is 8, its pitch is equivalent to the pitch of the note 1; when the note is 9, its pitch is equivalent to the pitch of the note 2; when the note is 11, its pitch is equivalent to the pitch of the note 4; when the note is 13, its pitch is equivalent to the pitch of the note 6. That is, the 8th note becomes the 1st note, the 9th note becomes the 2nd note, the 11th note becomes the 4th note, the 13th note becomes the 6th note, and so on.

[0149] In one possible implementation, the chord properties corresponding to the note intervals are determined in the following way:

[0150] First, determine the position of the note 3 (the third note). There are four possibilities: ① There is a third note, which is a major third; ② There is a third note, which is a minor third; ③ There is no third note, which is only a major second; ④ There is no third note, which is only a perfect fourth. Next, determine the position of the note 5 (the fifth note). There are four possibilities: ① There is a fifth note, which is an augmented fifth; ② There is a fifth note, which is a perfect fifth; ③ There is a fifth note, which is a diminished fifth; ④ There is no fifth note. Next, determine the position of the note 7 (the seventh note). There are four possibilities: ① There is a seventh note, which is a major seventh; ② There is a seventh note, which is a minor seventh; ③ There is no seventh note, which is only a major sixth; ④ There is no seventh note. Next, determine the position of the note 9 (the ninth note, which is the second note). There are two possibilities: ① There is a ninth note or a second note, which is a major ninth; ② There is neither a ninth note nor a second note. Finally, determine the special chord intervals. There are two possibilities: ① There is a diminished fifth; ② There is an augmented fifth.

[0151] When determining the position of the third note, as shown in Table 1 above, note 3 indicates the presence of a third note, which is a major third; note b3 indicates the presence of a third note, which is a minor third; note 2 indicates the absence of a third note, which is only a major second; and note 4 indicates the absence of a third note, which is only a major fourth.

[0152] When determining the position of the 5th note, as shown in Table 1 above, the note 5 indicates the presence of the 5th note, which is a perfect fifth; the note #5 indicates the presence of the 5th note, which is an augmented fifth; the note b5 indicates the presence of the 3rd note, which is a diminished fifth; and the note (5) indicates the absence of the 5th note.

[0153] When determining the position of the 7th note, as shown in Table 1 above, the note 7 indicates that there is a 7th note, which is a major seventh; the note b7 indicates that there is a 7th note, which is a minor seventh; and the note 6 indicates that there is no 7th note, which is only a major sixth.

[0154] When determining the position of the 9th note, as shown in Table 1 above, the note 9 or 2 indicates that there is a 9th note or a 2nd note, which is a major ninth.

[0155] Figure 5 This is a logical diagram illustrating the chord property determination provided in an embodiment of this disclosure. Figure 5As shown, for a note range, all notes above the root note are arranged in octaves, and notes 3, 5, 7 and 9 are judged in order from top to bottom. The chord properties are judged according to this judgment logic to obtain the chord name corresponding to the chord property.

[0156] like Figure 5 As shown, when judging the note 3 (the third note), if the third note corresponds to a major second, and the root note is C, the chord name corresponding to this chord property can be determined as Csus2; if the third note corresponds to a major third, further judging the note 5 (the fifth note), and if the fifth note corresponds to an augmented fifth, and the root note is C, the chord name corresponding to this chord property can be determined as Caug, etc., according to... Figure 5 The logic for determining chord properties shown can sequentially determine the chord names corresponding to the chord properties.

[0157] S403, based on the second chord list, obtain the single-note MIDI track corresponding to the multi-note MIDI track.

[0158] In one possible implementation, for each chord in the second chord list, based on the chord name of the chord, the chord types corresponding to the other notes in the chord (excluding the root note) are combined with different predefined root notes to obtain different chords. Each chord is then mapped to a MIDI key, and the MIDI key mapped with the chords is stored as a single-note MIDI track.

[0159] Figure 6 This is a schematic diagram illustrating the mapping of a multinote MIDI track to a single-note MIDI track, provided as an embodiment of this disclosure.

[0160] like Figure 6 As shown, the chord types corresponding to notes other than the root note can be one or more of the following: maj, min, sus2, sus4, aug, dim, maj7, 7, min7, m7b5, add9, madd9, 6, and 7sus4. Chord types maj, min, sus2, sus4, aug, and dim can be defined as Type A chords, and chord types maj7, 7, min7, m7b5, add9, madd9, 6, and 7sus4 can be defined as Type B chords. Type A and Type B chords can then be assigned to two different soft sound source presets of 108 MIDI keys.

[0161] like Figure 6As shown, when the chord type is maj, the chord type is combined with different predefined root notes, and each combined chord name is mapped to a MIDI key corresponding to a Class A chord, resulting in a single-note MIDI track corresponding to the combined chord name; when the chord type is maj7, the chord type is combined with different predefined root notes, and each combined chord name is mapped to a MIDI key corresponding to a Class B chord, resulting in a single-note MIDI track corresponding to the combined chord name.

[0162] S404 determines the sample file corresponding to the single-note MIDI track based on the mapping relationship between the sample files in the sample library of the soft source corresponding to the strumming track and the single-note MIDI track.

[0163] The specific implementation method is similar to that described above, and will not be repeated here.

[0164] The S405 is a software-based engine that uses single-note MIDI tracks to render sample files.

[0165] For example, a soft source engine is used to render sample files using single-note MIDI tracks.

[0166] In this step, if the sample file is rendered using a single-note MIDI track based on the soft sound source engine, and the rendering is successful, then the soft sound source test is passed; if the rendering fails, then the soft sound source test is failed, and the soft sound source needs to be tested again based on the above test method.

[0167] In this embodiment, the multinote MIDI track corresponding to the strumming track is obtained, a second chord list corresponding to the multinote MIDI track is obtained based on the multinote MIDI track, a single-note MIDI track corresponding to the multinote MIDI track is obtained based on the second chord list, the sampling file corresponding to the single-note MIDI track is determined based on the mapping relationship between the sampling file in the sampling library of the soft source corresponding to the strumming track and the single-note MIDI track, and the sampling file is rendered using the single-note MIDI track based on the soft source engine. In this embodiment, on the one hand, based on the multi-note MIDI track corresponding to the strumming track in the arrangement template, the multi-note MIDI track is first mapped to a chord, and then the chord is mapped to a single-note MIDI track, thereby realizing the identification of chords from the strumming multi-note MIDI track. The computational load of the identification process is relatively small, and the mapping from multi-note MIDI track to single-note MIDI track is also realized. On the other hand, the soft sound source provided in this embodiment is a sound source that controls a single sample file with a single-note MIDI track. By mapping the multi-note MIDI track to a single-note MIDI track and controlling the sample file in the soft sound source based on the single-note MIDI track, the rendering logic of the soft sound source is realized, thereby obtaining the rendering link corresponding to the strumming track in the arrangement template. The audio corresponding to the strumming-related chords rendered based on the rendering link can improve the realism of the strumming performance effect.

[0168] Understandably, compared to related technologies that identify chords from multinote MIDI tracks, the latter are more complex because multinote MIDI tracks are not specifically designed for soft sound sources suitable for guitar strumming and do not take into account the characteristics of guitar chords. The multinote MIDI track chord identification technology provided in this disclosure is simpler and more reliable.

[0169] Optionally, in the audio production method provided in this embodiment, when the audio corresponding to the target chord can be obtained based on the arrangement template, the target multinote MIDI track corresponding to the single-note MIDI track of the target chord can also be obtained. In one possible implementation, the audio production method further includes generating the target multinote MIDI track corresponding to the target single-note MIDI track and outputting the target multinote MIDI track.

[0170] For example, based on the client interface, the target multinote MIDI track is output to the user.

[0171] For example, the target multinote MIDI track conforms to the MIDI track corresponding to the business-defined chord table.

[0172] For example, the target multinote MIDI track can be a multinote MIDI track for a guitar strumming track.

[0173] For example, a chord table that conforms to the business definition can be the chord list shown in Table 1 above.

[0174] Understandably, when the target multinote MIDI track is a guitar strumming track, it has high versatility and can be used by users for secondary creation.

[0175] Optionally, one possible implementation for generating a target multinote MIDI track corresponding to a target single-note MIDI track is as follows: determine the chord name corresponding to the target single-note MIDI track based on the target sample file; determine all the notes of the chord corresponding to the chord name based on a chord recognition algorithm; and generate the target multinote MIDI track based on all the notes.

[0176] For example, the chord name corresponding to the target sample file is the same as the chord name corresponding to the target single-note MIDI track.

[0177] Based on the chord recognition algorithm, all the notes of the chord corresponding to the chord name are determined. The specific implementation method is similar to that described above, and will not be repeated here.

[0178] Optionally, the soft sound source related to strumming provided in this embodiment of the present disclosure further includes a sound source type. When the soft sound source includes a sound source type, a possible implementation of step S204, based on the soft sound source engine, applying a target single-note MIDI track to render the target sample file to obtain audio corresponding to the target chord, can be as follows: determine the soft sound source type corresponding to the target sample file, the soft sound source type includes a first sound source type and a second sound source type; if the soft sound source type is the first sound source type, then send a first MIDI control signal to the soft sound source engine, the first MIDI control signal carrying the target single-note MIDI track and the target sample file, the engine is used to apply the target single-note MIDI track to render the target sample file to obtain audio corresponding to the target chord; if the soft sound source type is the second sound source type, then send a second MIDI control signal to the soft sound source engine, the second MIDI control signal carrying the target single-note MIDI track and the target sample file, the engine is used to apply the target single-note MIDI track to render the target sample file to obtain audio corresponding to the target chord.

[0179] For example, when the soft source type is the first source type, the target chord is determined to be a Class A chord, the first MIDI control signal is set to 0, and the first MIDI control signal is sent to the soft source engine, so that the engine applies the target single note MIDI track to render the target sample file and obtain the audio corresponding to the target chord.

[0180] For example, when the soft source type is the second source type, the target chord is determined to be a B-type chord, the second MIDI control signal is set to 1, and the second MIDI control signal is sent to the soft source engine, so that the engine applies the target single note MIDI track to render the target sample file and obtain the audio corresponding to the target chord.

[0181] Based on the above embodiments, it can be understood that the audio production method provided in this disclosure, on the one hand, fully utilizes the business-defined chord list to map multi-note MIDI tracks to chords, and then maps the chords to single-note MIDI tracks, thus realizing a multi-note MIDI chord recognition method with low computational load; on the other hand, by designing a soft source for single-note MIDI control of individual sample files suitable for strumming tracks, and the mapping relationship between sample files in the soft source's sample library and single-note MIDI tracks, and testing the designed soft source based on the single-note MIDI tracks obtained by mapping multi-note MIDI tracks, a set of soft source design and rendering logic is defined based on low-cost mapping rules; furthermore, applying the above-defined soft source design and rendering logic to the arrangement template of the AI ​​arrangement module can improve the realism of the performance effect when strumming. At the same time, since guitar strumming has no difference in user operation from other instruments, users are completely unaware of any processing done to the strumming track by the technical backend when using AI arrangement, which can improve the user experience.

[0182] Exemplary Medium

[0183] After introducing the methods of exemplary embodiments of this disclosure, the following references are made. Figure 7 The storage medium of the exemplary embodiments of this disclosure will be described.

[0184] Figure 7 This is a schematic diagram of a storage medium provided according to an embodiment of the present disclosure. (See reference...) Figure 7 As shown, the storage medium 70 stores a program product for implementing the above-described method according to embodiments of the present disclosure. This program product may be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto.

[0185] The program product may employ any combination of one or more readable media. A readable media may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0186] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium.

[0187] Program code for performing the operations disclosed herein can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0188] Exemplary Apparatus

[0189] Having introduced the medium of exemplary embodiments of this disclosure, the following references are made to... Figure 8 The audio production apparatus of the exemplary embodiments of this disclosure will be described to implement the methods in any of the above method embodiments. The implementation principle and technical effect are similar, and will not be repeated here.

[0190] Figure 8 This is a schematic diagram of the structure of an audio production apparatus provided in one embodiment of the present disclosure. Figure 8 As shown, the audio production apparatus 80 of this embodiment includes: an acquisition module 810, a mapping module 820, a determination module 830, and a rendering module 840. Wherein:

[0191] The acquisition module 810 is used to acquire a target chord, which is a strumming-related chord generated based on the arrangement template;

[0192] The mapping module 820 is used to map the target chord onto the single-note MIDI key to obtain the target single-note MIDI track.

[0193] The determination module 830 is used to determine the target sample file corresponding to the target single note MIDI track based on the mapping relationship between the sample files in the sample library of the soft sound source corresponding to the strumming track and the single note MIDI track. The sample files in the sample library correspond one-to-one with the chords contained in the arrangement template.

[0194] The rendering module 840 is used by the software-based engine to render the target sample file using the target single-note MIDI track, thereby obtaining the audio corresponding to the target chord.

[0195] In one possible implementation, a single-note MIDI track is obtained as follows:

[0196] Obtain the first chord list; for each predefined chord in the first chord list, determine the chord type corresponding to the other notes in the predefined chord except the root note; combine the chord types with different predefined root notes to obtain the chords contained in the arrangement template; for each chord contained in the arrangement template, map the chord to a MIDI key to obtain a single-note MIDI track.

[0197] In one possible implementation, the soft audio source is tested and passed in the following way:

[0198] Obtain the multinote MIDI track corresponding to the strumming track; obtain the second chord list corresponding to the multinote MIDI track based on the multinote MIDI track; obtain the single-note MIDI track corresponding to the multinote MIDI track based on the second chord list; determine the sample file corresponding to the single-note MIDI track based on the mapping relationship between the sample files in the sample library of the soft source corresponding to the strumming track and the single-note MIDI track; render the sample file using the single-note MIDI track based on the soft source engine.

[0199] In one possible implementation, the audio production apparatus 80 further includes a processing module 850, which is configured to: parse a multinote MIDI track and extract at least one note interval from the parsed multinote MIDI track, wherein one note interval represents a chord; for each note interval, determine the chord name corresponding to the note interval based on a chord recognition algorithm; and determine the set of chord names as a second chord list.

[0200] In one possible implementation, the processing module 850 is further configured to: determine the root note from the notes included in the note interval; arrange all notes above the root note in octaves in order of pitch from low to high to obtain the chord properties corresponding to the note interval; and determine the chord name corresponding to the note interval based on the chord properties.

[0201] In one possible implementation, the audio production apparatus 80 further includes a generation module 860, which is used to: generate a target multinote MIDI track corresponding to the target single-note MIDI track; and output the target multinote MIDI track.

[0202] In one possible implementation, the generation module 860 is further configured to: determine the chord name corresponding to the target single-note MIDI track based on the target sample file; determine all notes of the chord corresponding to the chord name based on a chord recognition algorithm; and generate the target multi-note MIDI track based on all notes.

[0203] In one possible implementation, the soft source further includes a soft source type. The rendering module 840 is specifically used to: determine the soft source type corresponding to the target sample file, wherein the soft source type includes a first source type and a second source type; if the soft source type is the first source type, then send a first MIDI control signal to the soft source engine, wherein the first MIDI control signal carries the target single-note MIDI track and the target sample file, and the engine is used to render the target sample file using the target single-note MIDI track to obtain the audio corresponding to the target chord; if the soft source type is the second source type, then send a second MIDI control signal to the soft source engine, wherein the second MIDI control signal carries the target single-note MIDI track and the target sample file, and the engine is used to render the target sample file using the target single-note MIDI track to obtain the audio corresponding to the target chord.

[0204] The apparatus of this disclosure can be used to execute the audio production method in any of the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0205] Exemplary Computing Device

[0206] Having described the methods, media, and apparatus of exemplary embodiments of this disclosure, the following references... Figure 9 A computing device according to an exemplary embodiment of the present disclosure will be described.

[0207] Figure 9 The computing device 90 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0208] Figure 9This is a schematic diagram of the structure of a computing device provided in an embodiment of this disclosure. Figure 9 As shown, the computing device 90 is presented in the form of a general-purpose computing device. The components of the computing device 90 may include, but are not limited to: at least one processing unit 901, at least one storage unit 902, and a bus 903 connecting different system components (including the processing unit 901 and the storage unit 902). Exemplarily, the processing unit 901 may specifically be a processor, and the storage unit 902 stores computer execution instructions. The processing unit 901 executes the computer execution instructions stored in the storage unit 902 to implement the aforementioned audio production method.

[0209] The 903 bus includes a data bus, a control bus, and an address bus.

[0210] Storage unit 902 may include readable media in the form of volatile memory, such as random access memory (RAM) 9021 and / or cache memory 9022, and may further include readable media in the form of non-volatile memory, such as read-only memory (ROM) 9023.

[0211] Storage unit 902 may also include a program / utility 9025 having a set (at least one) of program modules 9024, such program modules 9024 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0212] The computing device 90 can also communicate with one or more external devices 904 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 905. Furthermore, the computing device 90 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 906. Figure 9 As shown, network adapter 906 communicates with other modules of computing device 90 via bus 903. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with computing device 90, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0213] It should be noted that although several units / modules or sub-units / modules of the audio production apparatus have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0214] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0215] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. An audio production method, characterized in that, include: Obtain the target chord, which is a strumming-related chord generated based on the arrangement template; The target chord is mapped onto the MIDI (Musical Instrument Digital Interface) keys of a single-note musical instrument to obtain the target single-note MIDI track. Based on the mapping relationship between the sample files in the sample library corresponding to the soft sound source of the strumming track and the single note MIDI track, the target sample file corresponding to the target single note MIDI track is determined, and the sample files in the sample library correspond one-to-one with the chords contained in the arrangement template; Based on the engine of the soft sound source, the target sample file is rendered using the target single-note MIDI track to obtain the audio corresponding to the target chord.

2. The manufacturing method according to claim 1, characterized in that, The single-note MIDI track was obtained in the following way: Get the list of first chords; For each predefined chord in the first chord list, determine the chord type corresponding to the other notes in the predefined chord except the root note; combine the chord types with different predefined root notes to obtain the chords contained in the arrangement template; For each chord contained in the arrangement template, the chord is mapped to a MIDI key to obtain the single-note MIDI track.

3. The manufacturing method according to claim 1, characterized in that, The software audio source passed the test in the following way: Obtain the multinote MIDI track corresponding to the strumming track; Based on the multinote MIDI track, obtain the second chord list corresponding to the multinote MIDI track; Based on the second chord list, the single-note MIDI track corresponding to the multi-note MIDI track is obtained; Based on the mapping relationship between the sample files in the sample library of the soft sound source corresponding to the strumming track and the single note MIDI track, the sample file corresponding to the single note MIDI track is determined; Based on the engine of the soft sound source, the sample file is rendered using the single-note MIDI track.

4. The manufacturing method according to claim 3, characterized in that, The step of obtaining the second chord list corresponding to the multi-note MIDI track based on the multi-note MIDI track includes: The multinote MIDI track is parsed, and at least one note interval included in the multinote MIDI track is extracted from the parsed multinote MIDI track, wherein the note interval is used to represent a chord; For each note interval, the chord name corresponding to the note interval is determined based on the chord recognition algorithm; The set of chord names is determined as the second chord list.

5. The manufacturing method according to claim 4, characterized in that, The method for determining the chord name corresponding to the note interval based on the chord recognition algorithm includes: The root note is determined from the notes included in the note interval; All notes above the root note are arranged in octaves, following the order of pitch from low to high, to obtain the chord properties corresponding to the note interval. Based on the chord properties, determine the chord name corresponding to the note interval.

6. The manufacturing method according to any one of claims 1 to 5, characterized in that, Also includes: Generate the target multinote MIDI track corresponding to the target single-note MIDI track; Output the target multinote MIDI track.

7. The manufacturing method according to claim 6, characterized in that, The process of generating the target multi-note MIDI track corresponding to the target single-note MIDI track includes: Based on the target sample file, determine the chord name corresponding to the target single-note MIDI track; Based on the chord recognition algorithm, all the notes of the chord corresponding to the chord name are determined; Generate the target multinote MIDI track based on all the notes.

8. The manufacturing method according to any one of claims 1 to 5, characterized in that, The soft sound source also includes a soft sound source type. The engine based on the soft sound source applies the target single-note MIDI track to render the target sample file to obtain audio corresponding to the target chord, including: Determine the soft audio source type corresponding to the target sampling file, wherein the soft audio source type includes a first audio source type and a second audio source type; If the soft audio source type is the first audio source type, then a first MIDI control signal is sent to the engine of the soft audio source. The first MIDI control signal carries the target single-note MIDI track and the target sample file. The engine is used to apply the target single-note MIDI track to render the target sample file to obtain the audio corresponding to the target chord. If the soft audio source type is the second audio source type, a second MIDI control signal is sent to the engine of the soft audio source. The second MIDI control signal carries the target single-note MIDI track and the target sample file. The engine is used to apply the target single-note MIDI track to render the target sample file to obtain the audio corresponding to the target chord.

9. An audio production apparatus, characterized in that, include: The acquisition module is used to acquire target chords, which are strumming-related chords generated based on an arrangement template; The mapping module is used to map the target chord onto the MIDI key of a single-note musical instrument to obtain the target single-note MIDI track; The determination module is used to determine the target sample file corresponding to the target single-note MIDI track based on the mapping relationship between the sample files in the sample library of the soft sound source corresponding to the strumming track and the single-note MIDI track. The sample files in the sample library correspond one-to-one with the chords contained in the arrangement template. The rendering module is used to render the target sample file using the target single-note MIDI track based on the engine of the soft sound source, so as to obtain the audio corresponding to the target chord.

10. A computing device, comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the audio production method as described in any one of claims 1 to 8.

11. A storage medium storing computer program instructions, which, when executed, implement the audio production method as described in any one of claims 1 to 8.

12. A computer program product comprising a computer program that, when executed, implements the audio production method as described in any one of claims 1 to 8.

Images