TW201828285A - Audio recognition method and system improving the feature point matching success rate in the audio recognition - Google Patents

Abstract

The embodiment of the present application discloses an audio recognition method, including: performing a diffusion process on first feature points in a spectrogram of an audio file to be recognized to obtain a feature point map, the number of the first feature points being multiple; searching, in the spectrogram of the target audio file, whether there is a second feature point corresponding to each of the first feature points after the diffusion processing in the feature point map; if positive, determining that the to-be-recognized audio file is part of the target audio file. The present application also discloses an embodiment of an audio recognition system. With this embodiment, the feature point matching success rate can be improved in the audio recognition.

Description

 Audio recognition method and system  

The present application relates to the field of Internet technologies, and in particular, to an audio recognition method and system.

With the continuous development of Internet technology, the Internet has become an indispensable tool in people's lives. The use of Internet devices to achieve the recognition of unknown audio, and based on the interaction of audio recognition, has become a new application trend.

There are many applications for interaction based on audio recognition. One application is, for example, a user who hears a song that does not know the name of the song, can record a piece of audio of the song, and then uses audio recognition technology to recognize the song title, singer, etc. of the song. News.

In the prior art, the feature points of the to-be-identified audio are generally extracted, and the feature point pairs are identified. As shown in Fig. 1, the horizontal axis represents time and the vertical axis represents frequency. The extracted feature points are “X” in the figure; two feature points form a feature point pair, and there are 8 feature point pairs in the target area; the feature point pairs are used to identify in the database, and the database memory The feature points and song information of the song are stored, such as song title, singer, etc.; if the same feature point pair can be matched in the same target area in the database, the matching is successful; and the corresponding song information can be obtained. However, since the extracted feature points are not necessarily in the normal position due to the inevitable noise interference when recording the audio, the probability of the feature point pair matching being successful is low.

In summary, in the prior art, there is a problem that the feature point matching success rate in audio recognition is low.

An object of the present application is to provide an audio recognition method and system, which solves the problem of low feature point matching success rate in audio recognition in the prior art.

In order to solve the above technical problem, an audio recognition method according to an embodiment of the present invention includes: performing a diffusion process on a first feature point in a spectrogram of an audio file to be obtained, to obtain a feature point map, and the number of the first feature points. a plurality of; determining, in a spectrogram of the target audio file, whether there is a second feature point respectively corresponding to each of the first feature points after the diffusion processing in the feature point map; if yes, determining the to-be-identified audio file Is part of the target audio file.

An audio recognition system according to an embodiment of the present invention includes: a diffusion unit, configured to perform diffusion processing on a first feature point in a spectrogram of an audio file to be obtained, to obtain a feature point map, where the number of the first feature points is a plurality of; a searching unit, searching, in a spectrogram of the target audio file, whether there is a second feature point respectively corresponding to each of the first feature points after the diffusion processing in the feature point map; and determining unit, configured to be in the target audio When the second feature point corresponding to each of the first feature points after the diffusion processing in the feature point map is found in the score map of the file, the audio file to be identified is determined to be part of the target audio file.

It can be seen that the audio recognition method and system provided by the embodiment of the present application can reduce the first by performing diffusion processing on the first feature point in the spectrum map of the audio file to be identified. The deviation of the feature point caused by the noise; thereby improving the matching rate between the first feature point after the diffusion process and the target audio file, that is, improving the feature point matching success rate.

210‧‧‧Diffusion unit

220‧‧‧Search unit

230‧‧‧determination unit

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are only Some of the embodiments described in the application can be obtained by those skilled in the art from other drawings without any inventive labor.

1 is a schematic diagram of identifying a pair of feature points in the prior art; FIG. 2 is a flowchart of an audio recognition method provided in an embodiment of the present application; FIG. 3 is a schematic diagram of a chromatogram of an audio file to be identified; Schematic diagram of the first feature point before the diffusion process; FIG. 4b is a schematic diagram of the first feature point after the diffusion process; FIG. 5 is a flow chart of the method of step S120 of FIG. 1; FIG. 6 is a map of the target audio file A schematic diagram of finding a second feature point corresponding to the first feature point after the diffusion processing in the feature point map; FIG. 7 is a flowchart of the audio recognition method provided in an embodiment of the present application; FIG. 8a is determined in the score map FIG. 8 is a partial enlarged view of FIG. 8a; FIG. 9 is a schematic diagram of a module of an audio recognition system provided in an embodiment of the present application.

The technical solutions in the embodiments of the present application are clearly and completely described in the following, in which the technical solutions in the embodiments of the present application are clearly and completely described. The embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope shall fall within the scope of the present application.

FIG. 2 is a flowchart of an audio identification method provided in an embodiment of the present application. In this embodiment, the audio recognition method includes the following steps:

S110: Diffusion processing is performed on the first feature points in the spectrogram of the audio file to be obtained, to obtain a feature point map, where the number of the first feature points is plural.

The spectrogram, also known as the speech spectrogram, is typically obtained by processing the received time domain signal. In general, the abscissa of the spectrogram is used to represent time, the ordinate is used to represent frequency, and the coordinate point value is used to represent the energy of speech data. Generally, a two-dimensional plane can be used to express three-dimensional information, so the energy value of the voice data represented by the coordinate point value can be expressed by color. For example, by means of color, the darker the color, the stronger the speech energy of the coordinate point; conversely, the lighter the color, the weaker the speech energy of the coordinate point. It can also be expressed by gray scale. The closer the color is to white, the stronger the speech energy can represent the coordinate point; conversely, the closer the color is to black, the weaker the speech energy of the coordinate point.

In this way, the spectrogram can intuitively represent the spectral characteristics of the speech signal over time. The strength of any given frequency component at a given time is indicated by the shade of the corresponding point or the shade of the hue.

Specifically, the spectrogram can be obtained by the following steps:

A1: The audio file to be identified is subjected to frame processing according to a preset time.

The preset time may be an empirical value obtained by the user based on past experience. The preset time in this embodiment includes 32 milliseconds. That is, the audio file to be identified is subjected to frame processing in 32 milliseconds to obtain an audio segment of one frame every 32 milliseconds and a frame stack of 16 milliseconds.

A2: Perform short-term spectrum analysis on the segmented audio segment to obtain a spectral map.

The short time spectrum analysis includes Fast Fourier Transformation (FFT). FFT is a fast algorithm of discrete Fourier transform. The FFT can be used to transform the audio signal into a spectral map that records the joint distribution information of the time domain and the frequency domain.

Since the processing is performed in 32 milliseconds, and 32 milliseconds corresponds to 8000hz sampling, 256 frequency points can be obtained after the FFT calculation.

As shown in Figure 3, the horizontal axis can represent the number of frames, that is, the number of frames after the audio file is framed, corresponding to the width of the spectral map; the vertical axis can represent the frequency, a total of 256 frequency points, corresponding to the spectrum The height of the coordinate point value represents the energy of the first feature point.

Preferably, after the short-time spectrum analysis is performed on the framing-processed audio segment, the method further includes:

A3: Extract the 300-2khz frequency segment after the short-term spectrum analysis.

Since the main frequency of the general song is concentrated on the frequency band of 300-2khz, the present embodiment can eliminate the negative influence of other frequency band noise on the frequency segment by extracting the frequency band of 300-2khz.

In another embodiment of the present application, before the step S110, the method further includes: normalizing the energy value of the first feature point of the spectrogram of the audio file to be identified into the gray value of the first feature point.

In this embodiment, since the energy value range of the first feature point after the FFT is large, sometimes it may reach 0-2^8 or even 0-2^16 (the energy value range is proportional to the signal strength of the audio file) Therefore, the energy value is normalized to a range of 0-255 here; so that 0-255 can correspond to a gray value, 0 represents black, and 255 represents white.

A general normalization method includes: traversing the energy value of the first feature point in the entire spectrogram to obtain a maximum value and a minimum value; normalizing the first feature point:

Wherein, V is the energy value of the first feature points; V _min is the minimum value; V _max is the maximum value.

The embodiment of the present application may adopt the above general normalization method. However, this normalization method, when there may be some mute, the obtained V _{min is} too small, for example, may approach 0, so that the normalization formula becomes This is irrelevant to V _min . Therefore, such V _{min is} not representative and affects the overall normalization processing result.

A new normalization method is provided in the embodiment of the present application, which may include: traversing a spectral map frame by frame with a first preset length as a window; and acquiring a local maximum value of energy values of the first feature point in the window. And a local minimum value; normalizing the energy value of the first feature point to the gray value of the first feature point according to the local maximum value and the local minimum value.

Using (2) as shown in formula, wherein, V is the energy value of the first feature points; V _min is the local minimum; V _max is the local maximum.

In this embodiment, after the framing processing, the first preset length may include a pre-T frame of the current frame to a last T frame of the current frame. That is, the first preset length is 2T frames, and the 2T+1 frames are greater than 1 second.

The normalization method provided in this embodiment can only affect the normalization result within the first preset length in which it is located, and cannot affect the normalization result outside the first preset length. So such a normalization method can reduce the impact of mute on the overall normalized result.

The diffusion process may include a Gaussian function diffusion process, that is, performing diffusion processing on the first feature point by using a Gaussian function; and may further include an amplification process of enlarging the first feature point by several times, for example, by 10 times.

Take the Gaussian function diffusion processing as an example, and use the following formula:

Where a, b and c are constants and a>0.

That is, Gaussian function diffusion processing is performed on the radius or diameter of the first feature point by using the formula (1).

Hereinafter, the first feature point enlargement processing will be taken as an example. The radius or diameter of the first feature point is magnified, for example by a 10x magnification of the radius or diameter. Of course, in some embodiments, the first feature point may be enlarged by several times to become at least one of a circle, a diamond, a rectangle, and the like.

As shown in FIG. 4a, the white point before the diffusion processing (the first feature point of the audio file to be identified) is deviated from the black point (the feature point of the target audio file), and thus the second feature point obtained by the final matching is less; As shown in Fig. 4b, the white point after the diffusion process spreads from one point to a region, and the region coincides with the black dots.

The diffusion process can make the first feature point diffuse from the point into a region, and thus can have certain anti-interference ability to noise, for example, due to the influence of noise interference, the first feature point of the recorded audio may be the first feature point of the original audio. There is a slight deviation in the position, and the deviation can be ignored after the diffusion process, and the number of second feature points obtained by the matching is increased.

S120: Searching, in the spectrogram of the target audio file, whether there is a second feature point corresponding to each of the first feature points after the diffusion processing in the feature point map.

As shown in FIG. 5, the step S120 may specifically include: S121: traversing a spectrum map of the target audio file frame by frame with the feature point map as a window; S122: in the window during each traversal process Determining, in the spectrogram of the target audio file, a feature point in a coordinate range of the first feature point after the diffusion processing in the window is determined as a second feature point; S123: searching for the target audio file in the window Whether there are second feature points respectively corresponding to the first feature points after the diffusion processing in the spectrogram.

As shown in FIG. 6, a schematic diagram of finding a second feature point corresponding to the first feature point after the diffusion processing in the feature point map is searched for in the spectrogram of the target audio file. It is assumed that the number of frames of the feature point map is N; the number of frames of the spectrum map of the target audio file is L, and the L is greater than or equal to N. First searching in the region of the target audio file whose frame number is [0, N]; then searching in the region of [1, N+1]; thus searching frame by frame until [LN, L] The region ends traversing. In the window of [t, t+N] of each frame in each traversal process, where t is the number of frames, the coordinates of the spectral map of the target audio file are located within the coordinate range of the first feature point after the diffusion processing. The point is determined as the second feature point. Searching, in the target audio file, each second feature point corresponding to each of the first feature points after the diffusion process.

In other embodiments, it is also possible to traverse all audio files in the database. In this way, the audio information of the audio file to be identified can be more accurately identified.

S130: If yes, determining that the to-be-identified audio file is part of the target audio file.

If the second feature point corresponding to each of the first feature points after the diffusion process is found in the spectrogram of the target audio file, the audio file to be identified may be determined to be part of the target audio file.

In this embodiment, the first feature point in the spectrogram of the audio file to be identified is subjected to diffusion processing, so that the deviation of the first feature point caused by the noise may be reduced; thereby improving the first feature point after the diffusion processing The matching rate of the target audio file can achieve an improved audio feature point matching success rate.

In an embodiment of the present application, the step S122 may specifically include: determining that a coordinate in a spectrogram of the target audio file in the window is located within a coordinate range of the first feature point after the diffusion processing in the window The matching degree of the feature point and the first feature point; determining the feature point whose matching degree is greater than the first threshold as the second feature point.

The matching degree includes a ratio of the number of feature points in the coordinate range of the first feature point after the diffusion processing in the spectral spectrum of the window to the number of the first feature points or the diffusion in the spectral spectrum in the window The sum of the energy values or the gray values of the first feature points corresponding to the feature points in the coordinate range of the first feature point after the processing. The first threshold may be a statistical result of the user according to the comprehensive related factors.

Taking the ratio of the number of feature points in the coordinate range of the first feature point after the diffusion process to the number of the first feature points in the intra-theme spectrum, for example, the first feature point after diffusion is 100. The feature points are 60; then the degree of matching between the first feature points and the feature points is 60%. If the first threshold is 80%, the feature point is determined as the second feature point.

For example, for example, the sum of the energy values of the first feature points corresponding to the feature points in the coordinate range of the first feature point after the diffusion processing in the intra-theme spectrum, for example, 10 feature points, then the 10 The energy values of the ten first feature points corresponding to the feature points are added to obtain the sum of the energy values. If the sum of the energy values is greater than the first threshold, the feature point is determined as the second feature point.

Taking the sum of the gradation values of the first feature points corresponding to the feature points in the coordinate range of the first feature point after the diffusion processing in the intra-theme spectrum, for example, if there are 10 feature points, then 10 The gray values of the ten first feature points corresponding to the feature points are added to obtain the sum of the gray values. If the sum of the grayscale values is greater than the first threshold, the feature point is determined as the second feature point.

In an embodiment of the present application, before step S110, S101 and S102 may be further included, as shown in FIG. 7: S101: the energy value or the gray value included in the spectrum map of the audio file to be identified is greater than the second. The feature point of the threshold is used as a key point; the second threshold may be a statistical result of the user according to the comprehensive correlation factor; the smaller the second threshold is, the more key points can be extracted, which may cause the subsequent matching time to be longer; The larger the threshold, the fewer key points that can be extracted, which may cause the success rate of subsequent matching to be too low.

S102: if the energy value or the gray value of the key point is a maximum value in the preset area, determining the key point as the first feature point; the preset area may be centered on the key point and a circular area determined according to a preset radius; or a rectangular area centered on the key point and determined according to a preset length and width.

The preset area may be a statistical result of the user according to the comprehensive related factors; the smaller the preset area is, the more the first feature points can be determined, which may cause the subsequent matching time to be longer; the larger the preset area, the more certain The fewer the first feature points, the lower the probability of success in subsequent matching.

As shown in FIG. 8a, a schematic diagram of the determined first feature point on the spectrogram. The white point in the figure is the first feature point. Specifically, it is assumed that the second preset threshold is 30, and the preset area is 15*15 (centered on a key point, 15 frames on the abscissa and 15 on the ordinate), as shown in FIG. 8b. FIG. 8a is a partially enlarged schematic view; the energy value or the gray value of the white point in the figure is greater than the first preset threshold 30 and is still the maximum value in the preset area 15*15, and such a point is extracted as the first feature point. .

The difference between the embodiment of the present application and the previous embodiment is that the feature point with the energy value or the gray value in the spectrogram is extracted as the first feature point, so that the interference of the weak feature point on the subsequent matching can be excluded. And it can greatly reduce the amount of data for diffusion processing, thereby improving system performance.

In an embodiment of the present application, the target audio file may carry audio information. When the present application is applied to a song recognition scene, the audio information may include a song title. The user records a to-be-recognized audio file or a to-be-recognized audio file that does not know the name of the song, and is a song that does not know the name of the song. When it is determined that the to-be-identified audio file is part of the target audio file, the to-be-recognized audio can be identified. The song name of the file.

FIG. 9 is a schematic diagram of a module of an audio recognition system provided in an embodiment of the present application. In this embodiment, the audio recognition system includes: a diffusion unit 210, configured to perform a diffusion process on the first feature point in the spectrogram of the audio file to be obtained, to obtain a feature point map, where the number of the first feature points is a plurality of; the searching unit 220, searching, in the spectrogram of the target audio file, whether there is a second feature point respectively corresponding to each of the first feature points after the diffusion processing in the feature point map; the determining unit 230, configured to Determining, in the score map of the target audio file, an area of the second feature point corresponding to each of the first feature points after the diffusion processing in the feature point map, determining that the to-be-recognized audio file is the target audio Part of the file.

Preferably, before the diffusing unit 210, the method further includes: a normalization unit, configured to normalize the energy value of the first feature point of the spectrogram of the audio file to be identified into the gray of the first feature point Degree value.

Preferably, the diffusion process includes at least one of a Gaussian function diffusion process or an amplification process.

Preferably, the normalization unit may further include: a first normalization subunit, configured to traverse the spectral map frame by frame with a first preset length as a window; and a second normalization subunit, Obtaining a local maximum value and a local minimum value in the energy values of the first feature points in the window; and a third normalization subunit, configured to calculate the energy value of the first feature points according to the local maximum value and the local minimum value Normalized to the gray value of the first feature point.

Preferably, the searching unit 220 may further include: a first searching subunit, configured to traverse the spectral map of the target audio file frame by frame with the feature point map as a window; and the second searching subunit, Determining, in each traversing process, a feature point in a coordinate map of the target audio file in the window that is located within a coordinate range of the first feature point after the diffusion processing in the window as a second feature point; And a search subunit, configured to search for a second feature point corresponding to each of the first feature points after the diffusion processing in the spectrogram of the target audio file in the window.

Preferably, the second locating subunit may further include: a fourth locating subunit, configured to determine that a coordinate in the gramogram of the target audio file in the window is located after the diffusion processing in the window a matching degree of the feature point in the coordinate range of the feature point and the first feature point; and a fifth search subunit, configured to determine the feature point whose matching degree is greater than the first threshold as the second feature point.

Preferably, the matching degree includes a ratio of the number of feature points in the coordinate range of the first feature point after the diffusion processing to the number of first feature points in the spectral map in the window or the intra-window spectrum The sum of the energy values or the gray values of the first feature points corresponding to the feature points in the coordinate range of the first feature point after the diffusion processing.

Preferably, before the spreading process, the method further includes: a first processing unit, configured to use, as a key point, an energy value included in a spectrogram of the audio file to be identified or a feature point whose gray value is greater than a second threshold And a second processing unit, configured to determine the key point as the first feature point when the energy value or the gray value of the key point is a maximum value in the preset area.

Preferably, the target audio file carries audio information, and the audio information includes a song name.

In the 1990s, improvements to a technology could clearly distinguish between hardware improvements (eg, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (for method flow). Improve). However, as technology advances, many of today's method flow improvements can be seen as direct improvements in hardware circuit architecture. Designers almost always get the corresponding hardware structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented by a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic functions are determined by the user programming the device. Designers program themselves to "integrate" a digital system on a single PLD without requiring the chip manufacturer to design and fabricate a dedicated integrated circuit die. Moreover, today, instead of manually making integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in programming development, but before compiling The original code has to be written in a specific programming language. This is called the Hardware Description Language (HDL). HDL is not the only one, but there are many kinds, such as ABEL (Advanced Boolean Expression Language). ), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are used. It should also be apparent to those skilled in the art that the hardware process for implementing the logic method flow can be easily obtained by simply programming the method flow into the integrated circuit with a few logic description languages.

The controller can be implemented in any suitable manner, for example, the controller can be computer readable by, for example, a microprocessor or processor and storing computer readable program code (eg, software or firmware) executable by the (micro)processor. Media, logic gates, switches, Application Specific Integrated Circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic. Those skilled in the art will also appreciate that in addition to implementing the controller in purely computer readable program code, it is entirely possible to logically program the method steps to enable the controller to use logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedding. The form of a microcontroller or the like to achieve the same function. Thus such a controller can be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component. Or even a device for implementing various functions can be considered as either a software module implementing the method or a structure within the hardware component.

The system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.

For the convenience of description, the above devices are described separately by function into various units. Of course, the functions of each unit can be implemented in the same software or software and/or hardware in the implementation of the present application.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Thus, the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining the software and hardware. Moreover, the present invention can take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.).

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor or other programmable data processing device to produce a machine for generating instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can boot a computer or other programmable data processing device to operate in a particular manner, such that instructions stored in the computer readable memory produce an article of manufacture including the instruction device. The instruction means implements the functions specified in one or more blocks of the flow or in a flow or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device to perform a series of operational steps on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, a network interface, and memory.

The memory may include non-permanent memory, random access memory (RAM) and/or non-volatile memory in computer readable media such as read only memory (ROM) or flash memory (flash) RAM). Memory is an example of a computer readable medium.

Computer readable media including both permanent and non-permanent, removable and non-removable media can be stored by any method or technology. Information can be computer readable instructions, data structures, modules of programs, or other materials. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access memory (RAM). Read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM only, digital versatile disc (DVD) or other optical storage, magnetic tape cartridge, magnetic tape storage or other magnetic storage device or any other non-transportable media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device including the element.

Those skilled in the art will appreciate that embodiments of the present application can be provided as a method, system, or computer program product. Thus, the present application can take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining the software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable code. .

The application can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, a program module includes routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types. The present application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices that are connected through a communication network. In a decentralized computing environment, program modules can be located in local and remote computer storage media, including storage devices.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The above description is only an embodiment of the present application and is not intended to limit the application. Various changes and modifications can be made to the present application by those skilled in the art. Any modifications, equivalents, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the appended claims.

Claims (18)

 An audio recognition method, comprising: performing a diffusion process on a first feature point in a spectrogram of an audio file to be obtained, to obtain a feature point map, the number of the first feature points being plural; in the target audio file Finding, in the spectrogram, whether there is a second feature point respectively corresponding to each of the first feature points after the diffusion processing in the feature point map; if yes, determining that the to-be-identified audio file is part of the target audio file.    The method of claim 1, wherein before the first feature point in the spectrogram of the audio file to be identified is subjected to diffusion processing, the method further includes: in the spectrogram of the audio file to be identified The energy value of the first feature point is normalized to the gray value of the first feature point.    The method of claim 1 or 2, wherein the diffusion process comprises at least one of a Gaussian function diffusion process or an amplification process.    The method of claim 2, wherein the energy value of the first feature point in the spectrogram of the audio file to be identified is normalized to the gray value of the first feature point, specifically: a preset length is a window traversing the spectral map frame by frame; acquiring a local maximum value and a local minimum value in the energy value of the first feature point in the window; and the energy of the first feature point according to the local maximum value and the local minimum value The value is normalized to the gray value of the first feature point.    The method of claim 1 or 2, wherein the finding in the spectrogram of the target audio file whether there is a second corresponding to each of the first feature points after the diffusion processing in the feature point map The feature point specifically includes: traversing the spectrum map of the target audio file frame by frame with the feature point map as a window; the coordinates of the spectrum map of the target audio file in the window are diffused in the window during each traversal process The feature point in the coordinate range of the first feature point is determined as the second feature point; whether there is a second map corresponding to each of the first feature points after the diffusion process in the spectrum map of the target audio file in the window Feature points.    The method of claim 5, wherein the feature point in the spectral map of the target audio file in the window is located within a coordinate range of the first feature point after the diffusion processing in the window is determined as The second feature point includes: determining a matching degree between the feature point in the coordinate map of the target audio file in the window and the first feature point in the coordinate range of the first feature point after the diffusion processing in the window; The feature point whose matching degree is greater than the first threshold is determined as the second feature point.    The method of claim 6, wherein the matching degree includes the number of feature points and the number of first feature points in the coordinate range of the first feature point after the diffusion process in the spectral spectrum of the window The ratio or the sum of the energy values or the gray values of the first feature points corresponding to the feature points located in the coordinate range of the first feature point after the diffusion processing in the intra-spectral spectrum.    The method of claim 1 or 2, wherein before the first feature point of the spectrogram of the audio file to be identified is subjected to diffusion processing, the method further comprises: in the spectrogram of the audio file to be identified The feature value of the included energy value or the gray value is greater than the second threshold as a key point; if the energy value or the gray value of the key point is a maximum value in the preset area, the key point is determined as the first feature point .    The method of claim 1, wherein the target audio file carries audio information, and the audio information includes a song name.    An audio recognition system, comprising: a diffusion unit, configured to perform diffusion processing on a first feature point in a spectrogram of an audio file to be obtained, to obtain a feature point map, where the number of the first feature points is multiple; a searching unit, searching, in a spectrogram of the target audio file, whether there is a second feature point respectively corresponding to each of the first feature points after the diffusion processing in the feature point map; and determining unit, configured to be used in the target audio file When the second feature point corresponding to each of the first feature points in the feature point map is found, the audio file to be identified is determined to be part of the target audio file.    The system of claim 10, wherein before the diffusing unit, further comprising: a normalization unit for normalizing energy values of the first feature points in the spectrogram of the audio file to be identified The gray value is converted into the first feature point.    The system of claim 10, wherein the diffusion process comprises at least one of a Gaussian function diffusion process or an amplification process.    The system of claim 11, wherein the normalization unit comprises: a first normalization sub-unit, configured to traverse the spectrogram frame by frame with a first preset length as a window; a normalized subunit for obtaining a local maximum and a local minimum in the energy value of the first feature point in the window; and a third normalization subunit for using the local maximum and the local minimum The energy value of a feature point is normalized to the gray value of the first feature point.    The system of claim 10, wherein the searching unit comprises: a first searching subunit, configured to traverse the spectral map of the target audio file frame by frame with the feature point map as a window; a second search subunit, configured to determine, in the traversal process, a feature point in a coordinate map of the target audio file in the window that is within a coordinate range of the first feature point after the diffusion processing in the window as a second feature a third search subunit, configured to search for a second feature point corresponding to each of the first feature points after the diffusion process in the spectrogram of the target audio file in the window.    The system of claim 14, wherein the second lookup subunit comprises: a fourth lookup subunit, configured to determine that coordinates in the spectrogram of the target audio file in the window are located in the window The matching degree of the feature point in the coordinate range of the first feature point after the diffusion process and the first feature point; the fifth search sub-unit is configured to determine the feature point whose matching degree is greater than the first threshold as the second feature point.    The system of claim 15, wherein the matching degree comprises the number of feature points and the number of first feature points in the coordinate range of the first feature point after the diffusion process in the spectral spectrum of the window. The ratio or the sum of the energy values or the gray values of the first feature points corresponding to the feature points located in the coordinate range of the first feature point after the diffusion processing in the intra-spectral spectrum.    The system of claim 10 or 11, wherein before the diffusion processing, the method further includes: a first processing unit, configured to: use the energy value or the gray value included in the spectrogram of the audio file to be identified A feature point that is greater than the second threshold is used as a key point; and the second processing unit is configured to determine the key point as the first feature point when the energy value or the gray value of the key point is a maximum value in the preset area.    The system of claim 10, wherein the target audio file carries audio information, the audio information including a song name.