CN107622775B - Method for splicing noise-containing songs and related products - Google Patents

Abstract

The embodiment of the present invention discloses a method for splicing noise-containing songs and related products. The method includes: acquiring N song audio files; judging whether the N song audio files contain noise audio files; if the N song audio files contain noise audio files; The file contains noise audio files, and noise reduction processing is performed on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold; M segments are extracted from the noise-reduced song audio file and the noise-reduced audio file, where M is an integer greater than 1; the M segments are spliced in a preset order to obtain the spliced song audio file. The embodiment of the present invention also discloses a device for splicing songs containing noise. By adopting the invention, the noise-containing audio files can be cut and spliced, and noise reduction processing can be performed on the spliced audio files, so as to improve the sound quality of the spliced audio files.

Description

Method for splicing noise-containing songs and related products

technical field

Embodiments of the present invention relate to the technical field of audio processing, and in particular, to a method for splicing noise-containing songs and related products.

Background technique

With the rapid development of mobile Internet technology, devices (such as mobile phones, tablet computers, touch) and dedicated players are increasingly pursuing music. At present, the functional playback of music in the prior art is limited to improving its own sound quality processing, for example, by appropriately processing low-quality audio files through the processing software built into the device or dedicated player to improve playback quality; The quality requirements of the audio files themselves are relatively high, and often genuine audio files can be broadcast with better effects, while the local processing of audio files, such as cutting technology and extraction technology, is less researched.

In the prior art, the cutting of songs mainly relies on network software, and these softwares often require manual operation and cannot precisely locate the exact position of each lyric.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a method and related products for splicing songs containing noise, which can cut and splicing audio files of songs containing noise.

A first aspect of the embodiments of the present invention provides a method for splicing noise-containing songs, including:

Obtain N song audio files, where N is an integer greater than 1;

Judging whether the N song audio files contain a noise audio file, the noise audio file is a noise audio file whose noise is greater than a noise threshold;

If the N song audio files contain noise audio files, perform noise reduction processing on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold;

Extract M segments from the N song audio files that have not been subjected to the noise reduction process and the noise reduction audio files, where M is an integer greater than 1;

The M segments are spliced in a preset order to obtain an audio file of the spliced song.

A second aspect of the embodiments of the present invention provides a device for splicing songs containing noise, including:

an acquisition unit for acquiring N song audio files, where N is an integer greater than 1;

a first judging unit, configured to judge whether the N song audio files acquired by the acquiring unit contain a noise audio file, and the noise audio file is a noise audio file whose noise is greater than a noise threshold;

a first processing unit, configured to perform noise reduction processing on the noise audio files in the N song audio files when the first judgment unit judges that the N song audio files contain noise audio files, to obtain a noise-reduced audio file with noise less than the threshold;

a first extraction unit, configured to extract M segments from the N song audio files without the noise reduction processing and the noise reduction audio files, where M is an integer greater than 1;

A splicing unit, configured to splicing the M segments extracted by the first extracting unit according to a preset order to obtain a spliced song audio file.

Implementing the embodiment of the present invention has the following beneficial effects:

In this embodiment of the present invention, N song audio files are acquired, where N is an integer greater than 1; it is determined whether the N song audio files contain noise audio files, and the noise audio files are noise audio files with noise greater than a noise threshold file; if the N song audio files contain noise audio files, perform noise reduction processing on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold; from the Extract M segments from the N song audio files that have not been subjected to the noise reduction process and the noise reduction audio files, where M is an integer greater than 1; perform the M segments in a preset order. Splicing to get spliced song audio files. By adopting the invention, the noise-containing audio files can be cut and spliced, and noise reduction processing can be performed on the spliced audio files, so as to improve the sound quality of the spliced audio files.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the drawings that are used in the embodiments and descriptions. Obviously, the drawings in the following descriptions are only some of the embodiments of the present invention. In the embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

1 is a schematic flowchart of a first embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention;

2 is a schematic flowchart of a second embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention;

3 is a schematic flowchart of a third embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention;

4 is a schematic flowchart of a fourth embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention;

5 is a schematic flowchart of a fifth embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention;

6 is a schematic structural diagram of a first embodiment of a device for splicing songs containing noise according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a second embodiment of an apparatus for splicing songs containing noise according to an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. . Based on the embodiments in the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work fall within the protection scope of the embodiments of the present invention.

The terms "first", "second", "third" and "fourth" in the description and claims of the present invention and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. . Furthermore, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally also includes For other steps or units inherent to these processes, methods, products or devices.

In implementation, in this embodiment of the present invention, the device may include, but is not limited to, a notebook computer, a mobile phone, a tablet computer, a smart wearable device, a player, MP3, MP4, a smart TV, a set-top box, a server, and the like. The system of the device refers to the operating system of the device, which may include, but is not limited to: Android system, Symbian system, Windows system, IOS (mobile operating system developed by Apple Inc.) system, and so on. It should be noted that the Android device refers to the device of the Android system, the Symbian device refers to the device of the Symbian system, and so on. The above-mentioned devices are only examples, not exhaustive, including but not limited to the above-mentioned devices.

In implementation, in this embodiment of the present invention, songs may include but are not limited to: Chinese songs, English songs, Russian songs, Spanish songs, classical songs, pop music songs, rock music songs, light music songs, rap songs, cappella songs, videos songs in , etc. The above songs are only examples, not exhaustive, including but not limited to the above songs.

In the implementation process, the format of the song may include, but is not limited to, MP3, MP4, WMV, WAV, FLV, and so on. The formats of the above songs are only examples, not exhaustive, including but not limited to the formats of the above songs.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of an embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention. The method for splicing noise-containing songs described in this embodiment includes the steps:

S101. Obtain N song audio files.

Specifically, N song audio files can be obtained from a device for splicing noisy songs, N song audio files can also be obtained from a mobile terminal, or N song audio files can be obtained from other methods, where N is an integer greater than 1 , the mobile terminal may be, for example, a mobile phone, a tablet computer, a notebook computer, a handheld computer, a mobile internet device (MID, mobile internet device), a wearable device (such as a smart watch (such as an iwatch, etc.), a smart bracelet, a pedometer, etc.) or Other terminal devices that can install and deploy instant messaging application clients, store the acquired N song audio files, and the location where the N song audio files are stored can be the local device where the noise-containing songs are spliced, or the cloud, or other storage.

S102. Determine whether the N song audio files contain a noise audio file, where the noise audio file is a noise audio file with a noise greater than a noise threshold.

Specifically, it is determined whether the N song audio files contain noise, where the noise may be a kind of interference signal, which will affect the sound quality of the audio files. Normally, noise is a random signal, and it can be determined whether the N song audio files contain noise by simply analyzing the audio files.

As a possible implementation manner, the size of the noise is determined by the degree of its interference to the audio file. Usually, the noise will cause interference in a certain playing time period of the audio file.

S103. Perform noise reduction processing on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold.

Specifically, if it is determined that the N song audio files contain noise audio files, noise reduction processing is performed on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold. , obtain N noise reduction audio files, and store the N noise reduction audio files. The location where the N noise reduction audio files are stored may be the local device where the noise-containing songs are spliced, or the cloud, or other storage space .

S104. Extract M segments from the N song audio files that have not been subjected to the noise reduction process and the noise reduction audio files.

Specifically, a total of M segments are extracted from the storage space i for storing the N song audio files and the storage space j for storing the noise reduction audio files, and the extracted M segments are stored in the storage of the segment to be spliced space, where M is an integer greater than 1.

S105, splicing the M segments according to a preset order to obtain an audio file of the spliced song.

Specifically, the M segments stored in the storage space of the segments to be spliced are spliced in a preset order to obtain the audio files of the spliced songs, wherein the preset order may be added to the storage space of the segments to be spliced The spatial time sequence may also be a random sequence preset by the device for splicing noise-containing songs, or other sequences.

In this embodiment of the present invention, N song audio files are acquired, where N is an integer greater than 1; it is determined whether the N song audio files contain noise audio files, and the noise audio files are noise audio files with noise greater than a noise threshold file; if the N song audio files contain noise audio files, perform noise reduction processing on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold; from the Extract M segments from the N song audio files that have not been subjected to the noise reduction process and the noise reduction audio files, where M is an integer greater than 1; perform the M segments in a preset order. Splicing to get spliced song audio files. By adopting the invention, the noise-containing audio files can be cut and spliced, and noise reduction processing can be performed on the spliced audio files, so as to improve the sound quality of the spliced audio files.

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of a second embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention, including steps:

S201. Analyze the N song audio files to obtain a frequency spectrum variation rule of the N song audio files.

Specifically, the N song audio files may be analyzed by an audio file spectrum processing apparatus to obtain the frequency spectrum variation rule of the N song audio files.

S202. Determine whether the N song audio files contain noise audio files according to the frequency spectrum change rule of the N song audio files.

Specifically, it is determined whether the N song audio files contain noise audio files according to the frequency spectrum change rule of the N song audio files. Analyze and compare the spectrum of each song audio file under normal conditions and the spectrum under noise conditions. If the spectrum with obvious fluctuations in the song audio file is the noise spectrum, the song audio file containing the noise spectrum is a noisy song. audio file.

In the embodiment of the present invention, the N song audio files are analyzed to obtain the frequency spectrum change rule of the N song audio files; according to the frequency spectrum change rule of the N song audio files, it is determined whether the N song audio files contain Noise audio files, so that it can be determined whether the N song audio files contain noise audio files.

Please refer to FIG. 3. FIG. 3 is a schematic flowchart of a third embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention, including steps:

S301. Extract the song audio files that are not subjected to the noise reduction processing and the original singing part of the noise reduction audio files from the N song audio files.

Specifically, the song audio files without noise reduction processing and the original singing part of the noise reduction audio files are extracted from the N song audio files. Usually, the song audio file may include the original singing part and the accompaniment part, and the song audio file may be separated to extract the original singing part of the song audio file.

S302. Determine the start time and end time of each voice segment in the N song audio files that have not been subjected to the noise reduction process and the original singing part of the noise reduction audio file.

Specifically, the start time and the end time of each voice segment in the song audio file without noise reduction processing and in the original singing part of the noise reduction audio file among the N song audio files are determined. The voice of the original singing part can be separated into sentence fragments one by one, and each sentence fragment has a corresponding start time and end time.

S303, cut according to the start time and end time of each voice segment in the original singing part of the N song audio files without the noise reduction process and the noise reduction audio file, to extract the M fragments.

Specifically, cutting is performed according to the start time and end time of each voice segment in the original singing part of the N song audio files without noise reduction processing and the noise reduction audio file, so as to extract the M fragment. The sentence fragments separated from the voice of the original singing part can be cut one by one according to the corresponding start time and end time of each sentence fragment, so as to extract M fragments.

The embodiment of the present invention extracts the song audio files that are not subjected to the noise reduction processing and the original singing part of the noise reduction audio files in the N song audio files; it is determined that the N song audio files are not subjected to the noise reduction process. The start time and end time of each voice segment in the noise-reduced song audio file and the original singing part of the noise-reduced audio file; according to the song audio without the noise-reduction process in the N song audio files The file and the start time and end time of each speech segment in the original singing part of the noise reduction audio file are cut to extract the M segments. By adopting the embodiment of the present invention, the audio file of the song can be cut to obtain the segments contained in the audio file of the song.

Please refer to FIG. 4. FIG. 4 is a schematic flowchart of a fourth embodiment of a method for splicing songs containing noise provided by an embodiment of the present invention, including steps:

S401. Extract the song audio files that are not subjected to the noise reduction processing and the accompaniment part of the noise reduction audio files from the N song audio files.

Specifically, the song audio files and the accompaniment parts of the noise reduction audio files that are not subjected to noise reduction processing among the N song audio files are extracted. Usually, the song audio file may include the original singing part and the accompaniment part, and the song audio file may be separated to extract the accompaniment part of the song audio file.

S402. Determine the start time and end time of each melody segment in the N song audio files for which the noise reduction processing has not been performed and the accompaniment part of the noise reduction audio file.

Specifically, the start time and the end time of each melody segment in the accompaniment singing part of the song audio files that are not subjected to noise reduction processing among the N song audio files are determined. The voice of the accompaniment part can be separated into sentence fragments one by one, and each sentence fragment has a corresponding start time and end time.

S403. Cut according to the start time and end time of each tune segment in the accompaniment part of the N song audio files without the noise reduction processing and the noise reduction audio files, to The M fragments are extracted.

Specifically, cutting is performed according to the start time and end time of each voice segment in the accompaniment part of the song audio files without noise reduction processing and the noise reduction audio files in the N song audio files, so as to extract the M Fragment. The sentence fragments separated from the voice of the accompaniment part can be cut one by one according to the corresponding start time and end time of each sentence fragment, so as to extract M fragments.

The embodiment of the present invention extracts the song audio files that are not subjected to the noise reduction processing and the accompaniment part of the noise reduction audio files in the N song audio files; it is determined that the noise reduction is not performed in the N song audio files The start time and end time of each tune segment in the processed song audio file and the accompaniment part of the noise reduction audio file; according to the song audio files and The start time and end time of each melody segment in the accompaniment part of the noise reduction audio file are cut to extract the M segments. By adopting the embodiment of the present invention, the audio file of the song can be cut to obtain the segments contained in the audio file of the song.

Please refer to FIG. 5. FIG. 5 is a schematic flowchart of a fifth embodiment of a method for splicing noise-containing songs according to an embodiment of the present invention, including steps:

S501. Obtain N song audio files.

Specifically, N song audio files can be obtained from a device for splicing noisy songs, N song audio files can also be obtained from a mobile terminal, or N song audio files can be obtained from other methods, where N is an integer greater than 1 , the mobile terminal may be, for example, a mobile phone, a tablet computer, a notebook computer, a handheld computer, a mobile internet device (MID, mobile internet device), a wearable device (such as a smart watch (such as an iwatch, etc.), a smart bracelet, a pedometer, etc.) or Other terminal devices that can install and deploy instant messaging application clients, store the acquired N song audio files, and the location where the N song audio files are stored can be the local device where the noise-containing songs are spliced, or the cloud, or other storage.

S502. Determine whether the N song audio files contain a noise audio file, where the noise audio file is a noise audio file with a noise greater than a noise threshold.

Specifically, it is determined whether the N song audio files contain noise, where the noise may be a kind of interference signal, which will affect the sound quality of the audio files. Normally, noise is a random signal, and it can be determined whether the N song audio files contain noise by simply analyzing the audio files.

As a possible implementation manner, the size of the noise is determined by the degree of its interference to the audio file. Usually, the noise will cause interference in a certain playing time period of the audio file.

S503. Perform noise reduction processing on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold.

Specifically, if it is determined that the N song audio files contain noise audio files, noise reduction processing is performed on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold. , obtain N noise reduction audio files, and store the N noise reduction audio files. The location where the N noise reduction audio files are stored may be the local device where the noise-containing songs are spliced, or the cloud, or other storage space .

S504. Extract M segments from the N song audio files that have not been subjected to the noise reduction processing and the noise reduction audio files.

Specifically, a total of M segments are extracted from the storage space i for storing the N song audio files and the storage space j for storing the noise reduction audio files, and the extracted M segments are stored in the storage of the segment to be spliced space, where M is an integer greater than 1.

S505, splicing the M segments according to a preset order to obtain an audio file of the spliced song.

Specifically, the M segments stored in the storage space of the segments to be spliced are spliced in a preset order to obtain the audio files of the spliced songs, wherein the preset order may be added to the storage space of the segments to be spliced The spatial time sequence may also be a random sequence preset by the device for splicing noise-containing songs, or other sequences.

S506. Lock the splicing position of the spliced song audio file.

Specifically, lock the splicing place of the high-quality splicing songs. In order to achieve seamless splicing, therefore, traces of splicing cannot be displayed, and the splicing place needs to be locked and preprocessed.

S507, processing the splicing position of the splicing song audio file to obtain the seamless splicing song audio file.

Specifically, the splicing position of the spliced song audio file is processed to obtain the seamless spliced song audio file. Wherein, the preprocessing may include, but is not limited to: adjusting the tune at the splicing places of the spliced songs, inserting tunes with similar degrees of change, and smoothing the splicing places with larger changes.

The embodiment of the present invention acquires N song audio files, where N is an integer greater than 1; judges whether the N song audio files contain noise audio files, and the noise audio files are noise audio files with noise greater than a noise threshold; If the N song audio files contain noise audio files, perform noise reduction processing on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold; Extracting M fragments from the song audio file without the noise reduction processing in the song audio file and the noise reduction audio file, where M is an integer greater than 1; splicing the M fragments according to a preset order, To obtain the audio file of the spliced song, lock the splicing place of the high-quality splicing song; perform preset processing on the splicing place of the splicing song to obtain the seamless splicing song. By adopting the embodiment of the present invention, preset processing can be performed on the audio files of the spliced songs, so as to obtain songs with seamless and better sound quality.

Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of a first embodiment of a device for splicing songs containing noise provided by an embodiment of the present invention. The device for splicing songs containing noise shown in FIG. 6 may include an acquisition unit 601, a first A judgment unit 602, a first processing unit 603, a first extraction unit 604, and a splicing unit 605 are as follows:

The obtaining unit 601 is configured to obtain N song audio files, where N is an integer greater than 1.

The first determining unit 602 is configured to determine whether the N song audio files acquired by the acquiring unit contain noise audio files, where the noise audio files are noise audio files with noise greater than a noise threshold.

Specifically, the first judgment unit 602 includes: an analysis unit (not shown) for analyzing the N song audio files to obtain the frequency spectrum change rule of the N song audio files; a second judgment unit (not shown) Figure), for judging whether the N song audio files contain noise audio files according to the frequency spectrum variation rule of the N song audio files analyzed by the analysis unit.

A first processing unit 603, configured to perform noise reduction processing on the noise audio files in the N song audio files when the first judgment unit determines that the N song audio files contain noise audio files , to get denoised audio files with noise less than a threshold.

The first extraction unit 604 is configured to extract M segments from the N song audio files without the noise reduction processing and the noise reduction audio files, where M is an integer greater than 1.

Specifically, the first extraction unit 604 includes: a second extraction unit (not shown), configured to extract the song audio files and the noise reduction audio files that have not been subjected to the noise reduction process in the N song audio files The original singing part of the file; the first determination unit (not shown) is used to determine the song audio files that are not subjected to the noise reduction processing and the said N song audio files extracted by the second extraction unit. The start time and end time of each voice segment in the original singing part of the noise reduction audio file; the first cutting unit (not shown) is used to determine the N songs obtained according to the first determining unit The start time and end time of each voice segment in the audio file of the song without the noise reduction processing and the original singing part of the noise reduction audio file are cut to extract the M segments.

Specifically, the first extraction unit 604 includes: a third extraction unit (not shown), configured to extract the song audio files and the noise reduction audio files that have not been subjected to the noise reduction process in the N song audio files The accompaniment part of the file; the second determination unit (not shown) is used to determine the song audio files and the noise reduction audio files that are not subjected to the noise reduction process in the N song audio files of the third extraction unit The start time and end time of each tune segment in the accompaniment part of the The start time and end time of each tune segment in the noise reduction-processed song audio file and the accompaniment part of the noise reduction audio file are cut to extract the M segments.

The splicing unit 605 is configured to splicing the M segments extracted by the first extracting unit according to a preset order to obtain a spliced song audio file.

Optionally, after the splicing unit 605 splices the M segments in a preset order, the device further includes: locking the splicing position of the spliced song audio file; splicing the splicing position of the spliced song audio file; Process to get a seamless stitched song audio file.

It can be understood that the functions of each functional module of the apparatus for splicing songs containing noise in this embodiment can be specifically implemented according to the method in the method embodiment, and the specific implementation process can refer to the relevant description of the method embodiment. It is not repeated here.

In this embodiment of the present invention, the acquisition unit 601 acquires N song audio files, where N is an integer greater than 1; the first judgment unit 602 determines whether the N song audio files acquired by the acquisition unit contain noise audio file, the noise audio file is a noise audio file whose noise is greater than the noise threshold; the first processing unit 603, when the first judgment unit judges that the N song audio files contain noise audio files, The noise audio files in the song audio files are subjected to noise reduction processing to obtain noise reduction audio files with noise less than a threshold; the first extracting unit 604 selects the song audio files that are not subjected to the noise reduction processing from the N song audio files. M segments are extracted from the file and the noise reduction audio file, where M is an integer greater than 1; the splicing unit 605 splices the M segments extracted by the first extraction unit in a preset order to obtain A splicing song audio file; a locking unit for locking the splicing position of the splicing song audio file; a second processing unit for processing the splicing position of the splicing song audio file locked by the locking unit to obtain no stitch the song audio files. By adopting the invention, the noise-containing audio files can be cut and spliced, and noise reduction processing can be performed on the spliced audio files, so as to improve the sound quality of the spliced audio files.

Referring to FIG. 7 , FIG. 7 is a schematic structural diagram of a second embodiment of an apparatus for splicing songs containing noise according to an embodiment of the present invention. The apparatus for splicing noise-containing songs described in this embodiment includes: at least one input device 1000; at least one output device 2000; at least one processor 3000, such as a CPU; The device 3000 and the memory 4000 are connected through the bus 5000 .

The above-mentioned input device 1000 may be a touch panel, an ordinary PC, a liquid crystal screen, a touch screen, or the like.

The above-mentioned memory 4000 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as a disk memory. The above-mentioned memory 4000 is used to store a set of program codes, and the above-mentioned input device 1000, output device 2000 and processor 3000 are used to call the program codes stored in the memory 4000, and perform the following operations:

The above-mentioned processor 3000 is used to obtain N song audio files, wherein N is an integer greater than 1;

The above-mentioned processor 3000 is further configured to judge whether the N song audio files contain a noise audio file, and the noise audio file is a noise audio file whose noise is greater than a noise threshold;

The above-mentioned processor 3000 is further configured to perform noise reduction processing on the noise audio files in the N song audio files when it is determined that the N song audio files contain noise audio files, so as to obtain that the noise is less than a threshold value. The noise-reduced audio file;

The above-mentioned processor 3000 is further configured to extract M segments from the N song audio files without the noise reduction processing and the noise reduction audio files, where M is an integer greater than 1;

The above-mentioned processor 3000 is further configured to splicing the M segments according to a preset order to obtain an audio file of the spliced song.

In some feasible embodiments, the above-mentioned processor 3000 is also specifically used for:

Analyzing the N song audio files to obtain the frequency spectrum variation rule of the N song audio files;

It is determined whether the N song audio files contain noise audio files according to the frequency spectrum change rule of the N song audio files.

In some feasible embodiments, the above-mentioned processor 3000 is also specifically used for:

Extracting the song audio files that are not subjected to the noise reduction process and the original singing part of the noise reduction audio files in the N song audio files;

Determine the start time and end time of each voice segment in the original singing part of the N song audio files that are not subjected to the noise reduction process and the noise reduction audio file;

Cut according to the start time and end time of each voice segment in the original singing part of the N song audio files that have not been subjected to the noise reduction processing, to extract the M fragments.

In some feasible embodiments, the above-mentioned processor 3000 is also specifically used for:

Extracting the accompaniment part of the song audio file and the noise reduction audio file that have not been subjected to the noise reduction process in the N song audio files;

Determine the start time and end time of each tune segment in the accompaniment part of the N song audio files that are not subjected to the noise reduction process and the noise reduction audio file;

Cut according to the start time and end time of each tune segment in the accompaniment part of the N song audio files without the noise reduction processing and the noise reduction audio files, so as to extract the The M segments are described.

In some feasible embodiments, after the processor 3000 splices the M segments in a preset order to obtain the audio file of the spliced song, the processor 3000 is further specifically used for:

locking the splicing position of the spliced song audio file;

The splicing position of the spliced song audio file is processed to obtain the seamless spliced song audio file.

In specific implementation, the input device 1000 , the output device 2000 , and the processor 3000 described in the embodiments of the present invention can execute the various embodiments of the methods for splicing noise-containing songs described in FIGS. 1 to 5 provided in the embodiments of the present invention The implementation manner described in the embodiment of the present invention can also be implemented as the implementation manner of the apparatus for splicing noise-containing songs described in the first embodiment of the apparatus for providing the apparatus for splicing songs with noise, which will not be repeated here.

The modules or submodules in all the embodiments of the embodiments of the present invention may be implemented by a general-purpose integrated circuit, such as a CPU (Central Processing Unit, central processing unit), or an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit).

The steps in the method of the embodiment of the present invention may be adjusted, combined and deleted in sequence according to actual needs.

Units in the apparatus of the embodiment of the present invention may be combined, divided, and deleted according to actual needs.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. During execution, the processes of the embodiments of the above-mentioned methods may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM for short).

The above disclosures are only preferred embodiments of the embodiments of the present invention, and of course, the scope of the rights of the embodiments of the present invention cannot be limited by this. Therefore, equivalent changes made according to the claims of the embodiments of the present invention are still within the scope of the embodiments of the present invention. scope covered.

Claims (6)

1. a method for splicing noise-containing songs, is characterized in that, comprising: Obtain N song audio files from the cloud, where N is an integer greater than 1; Judging whether the N song audio files contain a noise audio file, the noise audio file is a noise audio file whose noise is greater than a noise threshold; If the N song audio files contain noise audio files, noise reduction processing is performed on the noise audio files in the N song audio files to obtain noise reduction audio files with noise less than a threshold; Extract M segments from the N song audio files that have not been subjected to the noise reduction process and the noise reduction audio files, where M is an integer greater than 1; The M pieces are spliced in a preset order to obtain a spliced song audio file, the M pieces are stored in the storage space for storing the pieces to be spliced, and the preset order is that the M pieces are added to all the pieces. Describe the time sequence of the storage space of the pieces to be spliced; lock the splicing position of the splicing song audio file, and process the splicing position of the splicing song audio file to obtain the seamless splicing song audio file, wherein the processing includes : adjust the tune or insert a tune with a similar degree of change to the splicing place of the audio file of the spliced song; Wherein, extracting M segments from the N song audio files without the noise reduction processing and the noise reduction audio files, where M is an integer greater than 1, including: Extracting the song audio files that are not subjected to the noise reduction process and the original singing part of the noise reduction audio files in the N song audio files; Determining the start time and end time of each voice segment in the original singing part of the N song audio files without the noise reduction processing and the noise reduction audio files, and determining the The start time and end time of each voice segment in the original singing part of the N song audio files without the noise reduction processing and the original singing part of the noise reduction audio file include: The speech is separated into sentence fragments one by one, and each sentence fragment has a corresponding start time and end time; Cut according to the start time and end time of each voice segment in the original singing part of the N song audio files that have not been subjected to the noise reduction processing, to extract the M fragments. 2. method as claimed in claim 1, is characterized in that, described judging whether contains noise audio file in N song audio files, comprises: Analyzing the N song audio files to obtain the frequency spectrum variation rule of the N song audio files; It is determined whether the N song audio files contain noise audio files according to the frequency spectrum change rule of the N song audio files. 3. A device for splicing noise-containing songs, comprising: an acquisition unit, used to acquire N song audio files from the cloud, where N is an integer greater than 1; a first judging unit, configured to judge whether the N song audio files acquired by the acquiring unit contain a noise audio file, and the noise audio file is a noise audio file whose noise is greater than a noise threshold; a first processing unit, configured to perform noise reduction processing on the noise audio files in the N song audio files when the first judgment unit judges that the N song audio files contain noise audio files, to obtain a noise-reduced audio file with noise less than the threshold; A first extraction unit, configured to extract M segments from the N song audio files without the noise reduction processing and the noise reduction audio files, where M is an integer greater than 1; A splicing unit, used for splicing the M segments extracted by the first extraction unit according to a preset order to obtain a spliced song audio file, and the M segments are stored in a storage space for storing segments to be spliced , the preset sequence is the time sequence in which the M segments are added to the storage space of the segment to be spliced; The device is also specifically used to: lock the splicing position of the spliced song audio file; process the splicing position of the spliced song audio file to obtain the seamless spliced song audio file, wherein the processing includes: Adjust the tune or insert a tune with a similar degree of change in the splicing place of the audio file of the spliced song; Wherein, the first extraction unit includes: The second extraction unit is used to extract the original singing part of the song audio file and the noise reduction audio file that have not been subjected to the noise reduction process in the N song audio files; The first determining unit is configured to determine each of the song audio files that have not been subjected to the noise reduction processing and the original singing part of the noise reduction audio files in the N song audio files extracted by the second extraction unit. The start time and the end time of the voice segments , the determining of the N song audio files without the noise reduction processing and each voice segment in the original singing part of the noise reduction audio file The start time and the end time of the sing include: the voice of the original singing part is separated into sentence fragments one by one, and each sentence fragment has a corresponding start time and end time; The first cutting unit is used for determining according to the first determining unit the song audio files that have not been subjected to the noise reduction processing and the original singing part of the noise reduction audio files among the N song audio files determined by the first determining unit. The start time and end time of each speech segment are cut to extract the M segments. 4. The apparatus of claim 3, wherein the first judgment unit comprises: An analysis unit for analyzing the N song audio files to obtain the frequency spectrum variation rule of the N song audio files; A second judging unit, configured to judge whether the N song audio files contain noise audio files according to the frequency spectrum change rule of the N song audio files analyzed by the analyzing unit. 5. A device for splicing noise-containing songs, comprising: A processor and a memory; wherein the processor executes the method of any one of claims 1 to 2 by invoking codes or instructions in the memory. 6. A computer storage medium, characterized in that it is used for storing a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 2.

Images