Volume adjustment method, device and equipment and computer readable storage medium

Abstract

The invention relates to the technical field of signal processing, in particular to a volume adjustment method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining an input audio signal of audio equipment, and determining a human voice degree value and an accompaniment degree value of the input audio signal; a target gain factor is determined based on the human voice degree value and the accompaniment degree value, and the target gain factor is in positive correlation with the difference value between the human voice degree value and the accompaniment degree value; and according to the target gain factor, performing volume gain processing on a target frequency band signal in each frequency band signal of the input audio signal. According to the invention, the identification degree and definition of the input audio signal in the open type audio equipment are improved, so that the hearing feeling of a user when using the open type audio equipment is improved.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a volume adjustment method, device, equipment and computer-readable storage medium. Background Art

[0002] Open audio devices refer to audio devices whose backs of the sound-emitting units are connected to the external environment, such as head-mounted devices, smart audio glasses, and non-in-ear headphone devices. Open audio devices usually lack ANC (Active Noise Cancellation) function. In order to reduce the impact of background noise in the external environment on open audio devices and improve the user experience when using open audio devices, the current main method of adaptive volume adjustment based on background noise is to increase the overall volume of the audio signal played by the open audio device when the volume of the background noise is high; and to reduce the overall volume of the audio signal played by the open audio device when the volume of the background noise is low.

[0003] Although this adjustment method adjusts the volume of the audio signal played by the open audio device, the recognition and clarity of the audio signal may still be affected by background noise, causing the user's hearing experience to be affected when using the open audio device. Summary of the invention

[0004] The main purpose of the present invention is to provide a volume adjustment method, device, equipment and computer-readable storage medium, aiming to improve the recognition and clarity of input audio signals in open audio devices, thereby improving the user's listening experience when using the open audio devices.

[0005] To achieve the above object, the present invention provides a volume adjustment method, which comprises the following steps:

[0006] Acquire an input audio signal of an audio device, and determine a vocal level value and an accompaniment sound level value of the input audio signal;

[0007] Determining a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value;

[0008] According to the target gain factor, volume gain processing is performed on a target frequency band signal among the frequency band signals of the input audio signal, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

[0009] Optionally, before the step of determining the target gain factor based on the vocal level value and the accompaniment sound level value, the method further comprises:

[0010] Acquire an ambient sound signal of an external environment in which the audio device is located, and determine a noise level of the ambient sound signal;

[0011] The step of determining the target gain factor based on the vocal level value and the accompaniment sound level value comprises:

[0012] Determining a target signal type of the input audio signal based on the vocal level value and the accompaniment sound level value, wherein the target signal type of the input audio signal includes: a vocal type and an accompaniment sound type;

[0013] A target mapping relationship is determined from a plurality of preset mapping relationships based on the target signal type and the noise level, and a target gain factor is determined based on the target mapping relationship.

[0014] Optionally, when the target signal type is the human voice type, the step of determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level includes:

[0015] If the target frequency band signal is a medium-low frequency signal, a first mapping relationship corresponding to the noise level and the human voice type is determined from multiple preset mapping relationships as the target mapping relationship, wherein the medium-low frequency signal is a signal with a frequency less than or equal to a first preset frequency, and the first mapping relationship is a correspondence between each human voice degree value and a gain factor under the noise level.

[0016] Optionally, when the target signal type is the human voice type, the method further includes:

[0017] If the target frequency band signal is a high frequency signal, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as the target mapping relationship, wherein the high frequency signal is a signal with a frequency greater than the first preset frequency.

[0018] Optionally, when the target signal type is the accompaniment sound type, the step of determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level includes:

[0019] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is less than a second preset frequency, a second mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of preset mapping relationships as a target mapping relationship, wherein a maximum gain factor in the second mapping relationship is less than a preset threshold;

[0020] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is greater than or equal to the second preset frequency, or the target frequency band signal is a high frequency signal, a third mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of the preset mapping relationships as the target mapping relationship, wherein the third mapping relationship is a correspondence between the degree values ​​of each accompaniment sound and the gain factor under the noise level, and the minimum gain factor in the third mapping relationship is greater than or equal to the preset threshold value.

[0021] Optionally, the target signal type further includes: an unknown type, and the method further includes:

[0022] When the target signal type is the unknown type, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as a target mapping relationship.

[0023] Optionally, the step of performing volume gain processing on a target frequency band signal in each frequency band signal of the input audio signal according to the target gain factor comprises:

[0024] If the human voice level value is greater than the maximum value of the preset range, a signal greater than a preset frequency among the target frequency band signals in each frequency band signal of the input audio signal is determined as a signal to be adjusted;

[0025] Perform volume gain processing on the signal to be adjusted according to the target gain factor.

[0026] To achieve the above object, the present invention further provides a volume adjustment device, the volume adjustment device comprising:

[0027] An acquisition module, used for acquiring an input audio signal of an audio device, and determining a vocal level value and an accompaniment sound level value of the input audio signal;

[0028] A determination module, configured to determine a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value;

[0029] The adjustment module is used to perform volume gain processing on a target frequency band signal among the frequency band signals of the input audio signal according to the target gain factor, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

[0030] To achieve the above-mentioned object, the present invention further provides a volume adjustment device, which includes: a memory, a processor, and a volume adjustment program stored in the memory and executable on the processor, wherein the volume adjustment program implements the steps of the volume adjustment method described above when executed by the processor.

[0031] In addition, to achieve the above object, the present invention further proposes a computer-readable storage medium, on which a volume adjustment program is stored, and when the volume adjustment program is executed by a processor, the steps of the volume adjustment method described above are implemented.

[0032] In the present invention, an input audio signal of an audio device is obtained, and a vocal level value and an accompaniment sound level value of the input audio signal are determined; a target gain factor is determined based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with the difference between the vocal level value and the accompaniment sound level value; and according to the target gain factor, a volume gain processing is performed on a target frequency band signal among various frequency band signals of the input audio signal, wherein the target frequency band signal is a frequency band signal with the largest signal energy among various frequency band signals of the input audio signal.

[0033] In the present invention, the greater the difference between the human voice level value and the accompaniment sound level value, the greater the possibility that the input audio signal is a human voice signal or an accompaniment sound signal. At this time, the greater the target gain factor, the greater the volume of the target frequency band signal. Compared with adjusting the volume of the input audio signal as a whole according to the size of the background noise, the present invention realizes that when it can be confirmed that the input audio signal is a human voice signal or an accompaniment sound signal, the volume of the target frequency band signal is increased as much as possible, and the contrast between the target frequency band signal and the non-target frequency band signal is improved, so that the target frequency band signal (that is, the human voice signal or the accompaniment sound signal) is clearer and easier to identify, thereby improving the user's sensitivity to the target frequency band signal and improving the user's listening experience when using an open audio device when background noise exists.

[0034] Moreover, in the present invention, the smaller the difference between the human voice level value and the accompaniment sound level value is, the more it is impossible to determine whether the input audio signal is a human voice signal or an accompaniment sound signal, and the smaller the target gain factor is, the smaller the volume of the target frequency band signal is. This avoids the situation where the target frequency band signal masks other frequency band signals due to excessive increase in the volume of the target frequency band signal when it is impossible to confirm whether the input audio signal is a human voice signal or an accompaniment sound signal, thereby avoiding the user from missing important signals, thereby improving the user experience when using an open audio device in the presence of background noise. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention;

[0036] Figure 2 It is a flow chart of a first embodiment of a volume adjustment method of the present invention;

[0037] Figure 3 A flow chart of an implementation method of a volume adjustment method of the present invention;

[0038] Figure 4 A flow chart of an implementation method of a volume adjustment method of the present invention;

[0039] Figure 5 FIG. 4 is a schematic diagram of functional modules of a preferred embodiment of a volume adjustment device of the present invention.

[0040] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0041] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0042] like Figure 1 As shown, Figure 1 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0043] It should be noted that the volume adjustment device in the embodiment of the present invention may be an open audio device, such as a head-mounted device, smart audio glasses, and non-in-ear headphone devices, or may be a smart device that establishes a communication connection with an open audio device, such as a smart phone, a personal computer, a server, and other devices, without specific limitation herein.

[0044] like Figure 1 As shown, the volume adjustment device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0045] Those skilled in the art will understand that Figure 1The device structure shown in the figure does not constitute a limitation on the volume adjustment device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0046] like Figure 1 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a volume adjustment program. The operating system is a program that manages and controls the hardware and software resources of the device and supports the operation of the volume adjustment program and other software or programs. Figure 1 In the device shown, the user interface 1003 is mainly used for data communication with the client; the network interface 1004 is mainly used for establishing a communication connection with the server; and the processor 1001 can be used to call the volume adjustment program stored in the memory 1005 and perform the following operations:

[0047] Acquire an input audio signal of an audio device, and determine a vocal level value and an accompaniment sound level value of the input audio signal;

[0048] Determining a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value;

[0049] According to the target gain factor, volume gain processing is performed on a target frequency band signal among the frequency band signals of the input audio signal, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

[0050] Further, before the operation of determining the target gain factor based on the vocal level value and the accompaniment sound level value, the processor 1001 may also be used to call a volume adjustment program stored in the memory 1005, and perform the following operations:

[0051] Acquire an ambient sound signal of an external environment in which the audio device is located, and determine a noise level of the ambient sound signal;

[0052] The operation of determining the target gain factor based on the vocal level value and the accompaniment sound level value comprises:

[0053] Determining a target signal type of the input audio signal based on the vocal level value and the accompaniment sound level value, wherein the target signal type of the input audio signal includes: a vocal type and an accompaniment sound type;

[0054] A target mapping relationship is determined from a plurality of preset mapping relationships based on the target signal type and the noise level, and a target gain factor is determined based on the target mapping relationship.

[0055] Further, when the target signal type is the human voice type, the operation of determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level includes:

[0056] If the target frequency band signal is a medium-low frequency signal, a first mapping relationship corresponding to the noise level and the human voice type is determined from multiple preset mapping relationships as the target mapping relationship, wherein the medium-low frequency signal is a signal with a frequency less than or equal to a first preset frequency, and the first mapping relationship is a correspondence between each human voice degree value and a gain factor under the noise level.

[0057] Further, when the target signal type is the human voice type, the processor 1001 may also be used to call a volume adjustment program stored in the memory 1005 and perform the following operations:

[0058] If the target frequency band signal is a high frequency signal, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as the target mapping relationship, wherein the high frequency signal is a signal with a frequency greater than the first preset frequency.

[0059] Further, when the target signal type is the accompaniment sound type, the operation of determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level includes:

[0060] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is less than a second preset frequency, a second mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of preset mapping relationships as a target mapping relationship, wherein a maximum gain factor in the second mapping relationship is less than a preset threshold;

[0061] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is greater than or equal to the second preset frequency, or the target frequency band signal is a high frequency signal, a third mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of the preset mapping relationships as the target mapping relationship, wherein the third mapping relationship is a correspondence between the degree values ​​of each accompaniment sound and the gain factor under the noise level, and the minimum gain factor in the third mapping relationship is greater than or equal to the preset threshold value.

[0062] Furthermore, the target signal type also includes: unknown type, and the processor 1001 can also be used to call the volume adjustment program stored in the memory 1005 and perform the following operations:

[0063] When the target signal type is the unknown type, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as a target mapping relationship.

[0064] Furthermore, the operation of performing volume gain processing on the target frequency band signal in each frequency band signal of the input audio signal according to the target gain factor includes:

[0065] If the human voice level value is greater than the maximum value of the preset range, a signal greater than a preset frequency among the target frequency band signals in each frequency band signal of the input audio signal is determined as a signal to be adjusted;

[0066] Perform volume gain processing on the signal to be adjusted according to the target gain factor.

[0067] Based on the above structure, various embodiments of the volume adjustment method are proposed.

[0068] Reference Figure 2 , Figure 2 FIG. 4 is a flow chart of a first embodiment of a volume adjustment method according to the present invention.

[0069] The embodiment of the present invention provides an embodiment of the volume adjustment method. It should be noted that although the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that here. In this embodiment, the execution subject of the volume adjustment method can be an audio device, such as a head-mounted device, smart audio glasses, and non-in-ear headphone devices, or it can be a smart device that establishes a communication connection with an open audio device, such as a smart phone, a personal computer, a server, etc., without specific limitation here. In this embodiment, no limitation is made. For the sake of ease of description, the execution subject is omitted to explain each embodiment. In this embodiment, the volume adjustment method includes:

[0070] Step S10, obtaining an input audio signal of an audio device, and determining a vocal level value and an accompaniment sound level value of the input audio signal;

[0071] In this embodiment, the open audio device is referred to as an audio device, and any frame of audio signal in the audio signal input to the audio device is referred to as an input audio signal. An audio signal containing human voice is referred to as a human voice signal. It should be noted that there may be non-human voice signals in the human voice signal. For example, for a pop song, the human voice signal contains a music signal as background music. An audio signal not containing human voice is referred to as an accompaniment sound signal. Specifically, the accompaniment sound signal may be a music signal or a non-music signal not containing human voice. For example, for a TV drama audio, the accompaniment sound signal may be a sound signal such as a car horn.

[0072] An input audio signal is obtained, and a vocal level value and an accompaniment sound level value of the input audio signal are determined, wherein the higher the vocal level value, the more likely the input audio signal is a vocal signal, and the higher the accompaniment sound level value, the more likely the input audio signal is an accompaniment sound signal.

[0073] In one feasible implementation, the vocal level value and the accompaniment sound level value may be calculated separately according to the input audio signal; in another feasible implementation, since a frame of audio signal is either a vocal signal or an accompaniment sound signal, that is, the vocal level value and the accompaniment sound level value are correlated, and the larger the vocal level value is, the lower the corresponding accompaniment sound level value is. Therefore, in this implementation, after the vocal level value is calculated, the accompaniment sound level value is obtained based on the relevant constraint relationship between the vocal level value and the accompaniment sound level value. Conversely, after the accompaniment sound level value is calculated, the vocal level value is obtained based on the relevant constraint relationship between the vocal level value and the accompaniment sound level value. The specific setting can be made according to actual needs and is not limited here.

[0074] In one feasible implementation, the human voice level value may be determined by a neural network model that has been machine-learned or trained, and the specific model structure and training process are not described in detail here. In another feasible implementation, the specific process of determining the human voice level value may be: extracting features from the input audio signal; identifying the human voice signal in the input audio signal based on the extracted features; then performing speech recognition based on the identified human voice signal, and determining the mapped human voice level value according to the result of speech recognition. Among them, the extracted features may include frequency domain features and time domain features of the input audio signal, and may specifically include spectral entropy (Spectral Entropy), Linear Prediction Cepstrum Coefficients (Linear Prediction Cepstrum Coefficient, LPCC) and Line Spectrum Pair (Line Spectrum Pair, LSP), short-time energy, Mel-scale Frequency Cepstral Coefficients (Mel-scale Frequency Cepstral Coefficients, MFCC), first-order difference Mel-cepstrum coefficients, loudness and glottal excitation pulse and other features. In this embodiment, the human voice degree value can be determined according to the completeness of the sentence in the speech recognition result. For example, if the speech recognition result is a paragraph with a subject, predicate and object, the human voice degree value is considered to be high. If the speech recognition result is a phrase or an interjection, etc., the human voice degree value is considered to be low. In a specific embodiment, it can be a neural network model completed by machine learning or training, and the human voice degree value mapped to it is determined according to the result of speech recognition. The specific training process is not described in detail here; it can also be by extracting keywords from the speech recognition result, matching the extracted keywords with preset keywords, and the more matches there are, the higher the human voice degree value.

[0075] Step S20, determining a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value;

[0076] In this embodiment, the target gain factor is determined based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with the difference between the vocal level value and the accompaniment sound level value, that is, the larger the difference between the vocal level value and the accompaniment sound level value, the larger the target gain factor, that is, the larger the difference between the vocal level value and the accompaniment sound level value, the greater the possibility that the input audio signal is a vocal signal or an accompaniment sound signal, and the larger the target gain factor; the smaller the difference between the vocal level value and the accompaniment sound level value, the more likely it is that the input audio signal is a vocal signal or an accompaniment sound signal, and the smaller the target gain factor.

[0077] In one feasible implementation, the target signal type of the input audio signal may be determined based on the vocal level value and the accompaniment sound level value, wherein the signal type of the input audio signal includes: vocal type, accompaniment sound type and an unknown type that is not determined to be vocal or accompaniment sound; a mapping relationship corresponding to the target signal type is determined from a plurality of preset mapping relationships, and a target gain factor is determined based on the mapping relationship. In another feasible implementation, the target gain factor may also be determined based on the noise level, the vocal level value and the accompaniment sound level value, which is not specifically limited here.

[0078] Step S30: performing volume gain processing on a target frequency band signal among the frequency band signals of the input audio signal according to the target gain factor, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

[0079] In this embodiment, the frequency band signal in the signal concentration among the frequency band signals of the input audio signal is called the target frequency band signal, that is, the frequency band signal with the largest signal energy among the frequency band signals of the input audio signal. In a specific implementation, the input audio signal can be divided into multiple frequency bands according to the audio frequency of the input audio signal and a preset frequency band division rule, and the frequency band with the largest signal energy is determined as the target frequency band, and the signal of the target frequency band is determined as the target frequency band signal. The target frequency band signal can also be determined in other ways, which will not be described in detail here.

[0080] A volume gain process is performed on a target frequency band signal in each frequency band signal of the input audio signal according to a target gain factor.

[0081] In this embodiment, an input audio signal of an audio device is obtained, and a vocal level value and an accompaniment sound level value of the input audio signal are determined; a target gain factor is determined based on the vocal level value and the accompaniment sound level value, wherein the larger the difference between the vocal level value and the accompaniment sound level value, the larger the target gain factor, that is, when the vocal level value is larger, the larger the difference between the two, the larger the corresponding vocal level value is also, then the larger the target gain factor is; when the accompaniment sound level value is larger, the larger the difference between the two, the larger the corresponding accompaniment sound level value is also, then the larger the target gain factor is; according to the target gain factor, a volume gain processing is performed on a target frequency band signal among each frequency band signal of the input audio signal, wherein the target frequency band signal is a frequency band signal with the largest signal energy among each frequency band signal of the input audio signal.

[0082] In this embodiment, the greater the difference between the human voice level value and the accompaniment sound level value, the greater the possibility that the input audio signal is a human voice signal or an accompaniment sound signal. At this time, the larger the target gain factor, the greater the volume of the target frequency band signal. Compared with adjusting the volume of the input audio signal as a whole according to the size of the background noise, the present invention realizes that when it can be confirmed that the input audio signal is a human voice signal or an accompaniment sound signal, the volume of the target frequency band signal is increased as much as possible, and the contrast between the target frequency band signal and the non-target frequency band signal is improved, so that the target frequency band signal (that is, the human voice signal or the accompaniment sound signal) is clearer and easier to identify, thereby improving the user's sensitivity to the target frequency band signal and improving the user's listening experience when using an open audio device when background noise is present.

[0083] Moreover, in the present invention, the smaller the difference between the human voice level value and the accompaniment sound level value is, the more it is impossible to determine whether the input audio signal is a human voice signal or an accompaniment sound signal, and the smaller the target gain factor is, the smaller the volume of the target frequency band signal is. This avoids the situation where the target frequency band signal masks other frequency band signals due to excessive increase in the volume of the target frequency band signal when it is impossible to confirm whether the input audio signal is a human voice signal or an accompaniment sound signal, thereby avoiding users from missing out, thereby improving the user experience when using open audio equipment in the presence of background noise.

[0084] Further, in one possible implementation, referring to Figure 3, the specific process of volume adjustment can be: obtaining an input sound source, framing the input sound source signal, and any frame signal after framing is called an input audio signal. Extracting time domain features of the input audio signal, windowing the input audio signal, performing FFT (fast Fourier transform) on the windowed input audio signal, and then extracting frequency domain features of the Fourier transformed input audio signal. Among them, the extracted features may include frequency domain features and time domain features of the input audio signal, and may specifically include spectral entropy, linear prediction cepstrum coefficients and line spectrum pairs, short-time energy, Mel cepstrum coefficients, first-order difference Mel cepstrum coefficients, loudness, and glottal excitation pulses, etc., and human voice recognition or accompaniment sound recognition is performed based on the extracted time domain features and frequency domain features to obtain the human voice level value and accompaniment level value of the input audio signal.

[0085] Further, based on the above first embodiment, a second embodiment of the volume adjustment method of the present invention is proposed. In this embodiment, before step S20, the method further includes:

[0086] Step S40, obtaining an ambient sound signal of the external environment in which the audio device is located, and determining a noise level of the ambient sound signal;

[0087] In this embodiment, the loudness of the ambient sound signal in the external environment is used as a reference factor for adjusting the signal volume. Specifically, the ambient sound signal of the external environment where the audio device is located is obtained, and the noise level of the ambient sound signal is determined, wherein the louder the ambient sound signal, the higher the noise level.

[0088] In this embodiment, the noise level classification standard can be preset, and the noise level classification can be performed according to the volume of the sound signal and the level classification standard, or according to the volume, frequency and level classification standard, which is not limited here.

[0089] In this embodiment, step S20 includes:

[0090] Step S201, determining a target signal type of the input audio signal based on the vocal level value and the accompaniment sound level value, wherein the target signal type of the input audio signal includes: a vocal type and an accompaniment sound type;

[0091] In this embodiment, the target signal type of the input audio signal is determined based on the vocal level value and the accompaniment sound level value, wherein the signal type of the input audio signal includes: a vocal type and an accompaniment sound type.

[0092] In one feasible implementation, the process of determining the target signal type of the input audio signal may be: if the difference between the level value of the human voice and the level value of the accompaniment sound exceeds a preset level value range (hereinafter referred to as the first preset level value range), and the human voice level value is greater than the preset level value, the input audio signal is determined to be a human voice signal, and the target signal type of the input audio signal is determined to be a human voice type; if the difference between the level values ​​exceeds the first preset level value and the human voice level value is less than the preset level value, the input audio signal is determined to be an accompaniment sound signal, and the target signal type of the input audio signal is determined to be an accompaniment sound type. In another feasible implementation, since the human voice level value and the accompaniment sound level value are correlated, the signal type of the input audio signal may also be determined based on the human voice level value, specifically: if the human voice level value is greater than the maximum value of the preset level value range (hereinafter referred to as the second preset level value range), the input audio signal is determined to be a human voice signal, and the target signal type of the input audio signal is determined to be a human voice type; if the difference between the level values ​​is less than the minimum value of the second preset level value range, the input audio signal is determined to be an accompaniment sound signal, and the target signal type of the input audio signal is determined to be an accompaniment sound type.

[0093] Step S202, determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level, and determining a target gain factor based on the target mapping relationship, wherein, under the same target signal type, the higher the noise level, the larger the target gain factor.

[0094] In this embodiment, a target mapping relationship is determined from a plurality of preset mapping relationships based on the target signal type and the noise level, and a target gain factor is determined based on the target mapping relationship. Specifically, under the same target signal type, the higher the noise level, the greater the target gain factor.

[0095] This embodiment takes background noise into consideration and implements determination of a target gain factor based on the noise level of the ambient sound signal, wherein, under the same target signal type, the higher the noise level, the larger the target gain factor, so that the volume of the target frequency band signal increases with the increase of the ambient sound signal, making the target frequency band signal clearer and easier to identify under background noise, thereby increasing the user's sensitivity to the target frequency band signal and improving the user's listening experience when using open audio equipment when background noise is present.

[0096] Furthermore, in a feasible implementation manner, before step S40, the method further includes: filtering out transient sound signals in the ambient sound signal to obtain a filtered ambient sound signal; and determining a noise level of the filtered ambient sound signal. The specific filtering method is not limited here.

[0097] The transient sound signal is an unstable signal with impact characteristics. The signal will jump from a relatively stable range to a large value in a very short time and then decay. In addition, the transient sound signal has a large bandwidth, that is, the energy covers the entire frequency band. Therefore, the transient sound signal will interfere with the classification of noise levels. In this embodiment, by filtering out the transient sound signal and then dividing the noise level, the interference of the transient sound signal on the noise level can be eliminated, making the determined noise level more accurate, thereby improving the accuracy of signal volume adjustment.

[0098] Further, in one possible implementation, referring to Figure 4 The specific process of the volume adjustment method can be: (1) the microphone pickup module picks up the environmental sound signal; (2) the transient noise processing module filters the transient sound signal of the environmental sound signal; (3) the background sound level detection module determines the noise level of the filtered environmental sound signal; (4) the human voice recognition module recognizes the human voice of the input audio signal; (5) the accompaniment sound recognition module recognizes the accompaniment sound of the input audio signal; (6) according to the human voice recognition result and the accompaniment sound recognition result, the noise adaptive control module performs gain processing on the input audio signal.

[0099] Further, in a feasible implementation manner, the step S30 includes:

[0100] Step S301, if the human voice level value is greater than the maximum value of a preset range, a signal greater than a preset frequency among target frequency band signals in each frequency band signal of the input audio signal is determined as a signal to be adjusted;

[0101] If the human voice level value is greater than the maximum value of the preset range, the input audio signal is determined to be a human voice signal. Since the fundamental frequency range of human voice is generally between 500Hz and 1KHz, the sound signal below 500Hz can be considered not to be a human voice signal. In order to highlight the human voice signal in the input audio signal and improve the user's hearing experience, a preset frequency is set in this embodiment, and the signal greater than the preset frequency in the target frequency band signal in each frequency band signal of the input audio signal is determined as the signal to be adjusted, that is, the non-human voice signal in the target frequency band signal is not adjusted, and only the volume of the human voice signal is adjusted. Specifically, in a feasible implementation, the preset frequency can be set according to actual needs, for example, it can be set to 400Hz.

[0102] Step S302: performing volume gain processing on the signal to be adjusted according to the target gain factor.

[0103] The signal to be adjusted is processed for volume gain according to the target gain factor. This embodiment improves the contrast between the target frequency band signal (i.e., the human voice signal) and the non-target frequency band signal when the input audio signal is a human voice signal, and makes the target frequency band signal (i.e., the human voice signal) clearer and easier to identify, thereby improving the user's sensitivity to the target frequency band signal and improving the user's listening experience when using an open audio device in the presence of background noise.

[0104] In this embodiment, an ambient sound signal of the external environment in which the audio device is located is obtained, and the noise level of the ambient sound signal is determined, wherein the louder the ambient sound signal is, the higher the noise level is; a target signal type of the input audio signal is determined based on a vocal level value and an accompaniment sound level value, wherein the signal type of the input audio signal includes: a vocal type and an accompaniment sound type; a target mapping relationship is determined from a plurality of preset mapping relationships based on the target signal type and the noise level, and a target gain factor is determined based on the target mapping relationship.

[0105] This embodiment realizes determining the target gain factor according to the noise level of the ambient sound signal, wherein, under the same target signal type, the higher the noise level, the larger the target gain factor, so that the volume of the target frequency band signal increases with the increase of the ambient sound signal, making the target frequency band signal clearer and easier to identify under background noise, thereby improving the user's sensitivity to the target frequency band signal and improving the user's listening experience when using open audio equipment when background noise is present.

[0106] Further, based on the above-mentioned first and / or second embodiments, a third embodiment of the volume adjustment method of the present invention is proposed. In this embodiment, when the target signal type is the human voice type, the step S202 includes:

[0107] Step S2021, if the target frequency band signal is a medium-low frequency signal, determine a first mapping relationship corresponding to the noise level and the human voice type from multiple preset mapping relationships as the target mapping relationship, wherein the medium-low frequency signal is a signal with a frequency less than or equal to the first preset frequency, and the first mapping relationship is the correspondence between each human voice degree value and the gain factor under the noise level.

[0108] In this embodiment, a signal with a frequency less than or equal to the first preset frequency is called a medium-low frequency signal, and a signal with a frequency greater than the first preset frequency is called a high-frequency signal. Specifically, the division of the medium-low frequency signal and the high-frequency signal can be divided according to conventional rules, or can be set according to the actual needs of the user, and there is no limitation here. For example, in a feasible implementation, for the sound range of 20-20000 Hz audible to the human ear, the first preset frequency is set to 6000 Hz, that is, the medium-low frequency signal is 20-6000 Hz, and the high-frequency signal is 6000 Hz to 20000 Hz.

[0109] If the target frequency band signal is a medium-low frequency signal, the first mapping relationship corresponding to the noise level and the human voice type among multiple preset mapping relationships is used as the target mapping relationship, wherein the first mapping relationship is the correspondence between each human voice degree value and the gain factor under the noise level. Specifically, the greater the human voice recognition degree value, the greater the gain factor.

[0110] Furthermore, in a feasible implementation manner, when the target signal type is the human voice type, the method further includes:

[0111] Step S2022: If the target frequency band signal is a high frequency signal, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as the target mapping relationship, wherein the high frequency signal is a signal having a frequency greater than the first preset frequency.

[0112] Since the human ear can easily perceive high-frequency signals, the target gain factor can be determined based on the human ear's sensitivity to sound. That is, if the target frequency band signal is a high-frequency signal, the Bark frequency scale formula in the multiple preset mapping relationships is used as the target mapping relationship. The Bark frequency scale formula is:

[0113]

[0114] Where f is the frequency of the input audio signal.

[0115] Further, in a feasible implementation manner, when the target signal type is the accompaniment sound type, step S202 includes:

[0116] Step S2023, if the target frequency band signal is a mid-low frequency signal and the maximum frequency of the target frequency band signal is less than a second preset frequency, determining a second mapping relationship corresponding to the noise level and the accompaniment sound type from a plurality of preset mapping relationships as a target mapping relationship, wherein a maximum gain factor in the second mapping relationship is less than a preset threshold;

[0117] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is less than the second preset frequency, it is determined that the target frequency band signal is in a low-frequency state. In order to avoid excessive enhancement of the low-frequency component and thus reach the maximum amplitude of the speaker and ensure the normal use of the open audio device, when the target signal type is an accompaniment sound type and the target frequency band signal is in a low-frequency state, only a small amount of enhancement of the low frequency is required, that is, the maximum gain factor in the second mapping relationship corresponding to the noise level and the accompaniment sound type is set to be less than the preset threshold.

[0118] Specifically, in this implementation, a second mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of preset mapping relationships as the target mapping relationship.

[0119] Step S2024: If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is greater than or equal to the second preset frequency, or the target frequency band signal is a high frequency signal, a third mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of preset mapping relationships as a target mapping relationship, wherein the third mapping relationship is a correspondence between the degree values ​​of each accompaniment sound and the gain factor under the noise level, and the minimum gain factor in the third mapping relationship is greater than or equal to the preset threshold value.

[0120] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is greater than or equal to the second preset frequency, or the target frequency band signal is a high frequency signal, it is determined that the target frequency band signal is not in a low-frequency state. At this time, a third mapping relationship corresponding to the noise level and the accompaniment sound type is determined from multiple preset mapping relationships as the target mapping relationship, wherein the third mapping relationship is a correspondence between each accompaniment sound degree value and a gain factor under the noise level, and the minimum gain factor in the third mapping relationship is greater than or equal to a preset threshold.

[0121] Furthermore, in a feasible implementation manner, the target signal type further includes: an unknown type, and the method further includes:

[0122] Step S2025: When the target signal type is the unknown type, a Bark frequency scale formula in the plurality of preset mapping relationships is used as a target mapping relationship.

[0123] When the difference between the accompaniment sound level value and the human voice level value is less than the preset range, the target signal type is an unknown type. At this time, it is impossible to accurately distinguish whether the input audio signal is a human voice signal or an accompaniment sound signal. If the target gain factor is determined based on the human voice level value or the accompaniment sound level value, the volume of the target frequency band signal may be increased to mask the non-target frequency band signal, causing the user to miss important signals. Therefore, this embodiment determines the target gain factor based on the human ear's perception sensitivity to sound, and uses the Bark frequency scale formula in multiple preset mapping relationships as the target mapping relationship. Specifically, the greater the noise level, the target gain factor of different frequencies is controlled to increase according to the Bark frequency scale formula; the smaller the noise level, the target gain factor of different frequencies is controlled to decrease according to the Bark frequency scale formula. The Bark frequency scale formula is not repeated here.

[0124] In this embodiment, if the target frequency band signal is a medium-low frequency signal, the first mapping relationship corresponding to the noise level and the human voice type among the multiple preset mapping relationships is used as the target mapping relationship, wherein the first mapping relationship is the correspondence between each human voice level value and the gain factor under the noise level. In this embodiment, the target mapping relationship is determined according to the frequency characteristics of the target frequency band signal, so that the determined target gain factor conforms to the actual frequency characteristics of the target frequency band signal, thereby improving the user experience when using the open audio device.

[0125] In addition, the embodiment of the present invention also provides a volume adjustment device, referring to Figure 5 , the volume adjustment device comprises:

[0126] An acquisition module 10 is used to acquire an input audio signal of an audio device and determine a vocal level value and an accompaniment sound level value of the input audio signal;

[0127] A determination module 20, configured to determine a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value;

[0128] The adjustment module 30 is used to perform volume gain processing on a target frequency band signal among the frequency band signals of the input audio signal according to the target gain factor, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

[0129] Furthermore, the acquisition module 10 is also used for:

[0130] Acquire an ambient sound signal of an external environment in which the audio device is located, and determine a noise level of the ambient sound signal;

[0131] The determining module 20 is further used for:

[0132] Determining a target signal type of the input audio signal based on the vocal level value and the accompaniment sound level value, wherein the target signal type of the input audio signal includes: a vocal type and an accompaniment sound type;

[0133] A target mapping relationship is determined from a plurality of preset mapping relationships based on the target signal type and the noise level, and a target gain factor is determined based on the target mapping relationship.

[0134] Further, when the target signal type is the human voice type, the determination module 20 is further configured to:

[0135] If the target frequency band signal is a medium-low frequency signal, a first mapping relationship corresponding to the noise level and the human voice type is determined from multiple preset mapping relationships as the target mapping relationship, wherein the medium-low frequency signal is a signal with a frequency less than or equal to a first preset frequency, and the first mapping relationship is a correspondence between each human voice degree value and a gain factor under the noise level.

[0136] Further, when the target signal type is the human voice type, the determination module 20 is further configured to:

[0137] If the target frequency band signal is a high frequency signal, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as the target mapping relationship, wherein the high frequency signal is a signal with a frequency greater than the first preset frequency.

[0138] Further, when the target signal type is the accompaniment sound type, the determination module 20 is further configured to:

[0139] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is less than a second preset frequency, a second mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of preset mapping relationships as a target mapping relationship, wherein a maximum gain factor in the second mapping relationship is less than a preset threshold;

[0140] If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is greater than or equal to the second preset frequency, or the target frequency band signal is a high frequency signal, a third mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of the preset mapping relationships as the target mapping relationship, wherein the third mapping relationship is a correspondence between the degree values ​​of each accompaniment sound and the gain factor under the noise level, and the minimum gain factor in the third mapping relationship is greater than or equal to the preset threshold value.

[0141] Furthermore, the target signal type further includes: an unknown type, and the determination module 20 is further configured to:

[0142] When the target signal type is the unknown type, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as a target mapping relationship.

[0143] Furthermore, the adjustment module 30 is also used for:

[0144] If the human voice level value is greater than the maximum value of the preset range, a signal greater than a preset frequency among the target frequency band signals in each frequency band signal of the input audio signal is determined as a signal to be adjusted;

[0145] Perform volume gain processing on the signal to be adjusted according to the target gain factor.

[0146] The various embodiments of the volume adjustment device of the present invention can refer to the various embodiments of the volume adjustment method of the present invention, which will not be described in detail here.

[0147] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a volume adjustment program is stored. When the volume adjustment program is executed by a processor, the steps of the volume adjustment method described below are implemented.

[0148] The various embodiments of the volume adjustment device and the computer-readable storage medium of the present invention can all refer to the various embodiments of the volume adjustment method of the present invention, which will not be described in detail here.

[0149] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0150] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0152] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A volume adjustment method, characterized in that: The volume adjustment method comprises the following steps: Acquire an input audio signal of an audio device, and determine a vocal level value and an accompaniment sound level value of the input audio signal; Determining a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value; According to the target gain factor, volume gain processing is performed on a target frequency band signal among the frequency band signals of the input audio signal, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

2. The volume adjustment method according to claim 1, wherein: Before the step of determining the target gain factor based on the vocal level value and the accompaniment sound level value, the method further includes: Acquire an ambient sound signal of an external environment in which the audio device is located, and determine a noise level of the ambient sound signal; The step of determining the target gain factor based on the vocal level value and the accompaniment sound level value comprises: Determining a target signal type of the input audio signal based on the vocal level value and the accompaniment sound level value, wherein the target signal type of the input audio signal includes: a vocal type and an accompaniment sound type; A target mapping relationship is determined from a plurality of preset mapping relationships based on the target signal type and the noise level, and a target gain factor is determined based on the target mapping relationship.

3. The volume adjustment method according to claim 2, characterized in that: When the target signal type is the human voice type, the step of determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level includes: If the target frequency band signal is a medium-low frequency signal, a first mapping relationship corresponding to the noise level and the human voice type is determined from multiple preset mapping relationships as the target mapping relationship, wherein the medium-low frequency signal is a signal with a frequency less than or equal to a first preset frequency, and the first mapping relationship is a correspondence between each human voice degree value and a gain factor under the noise level.

4. The volume adjustment method according to claim 3, characterized in that: When the target signal type is the human voice type, the method further includes: If the target frequency band signal is a high frequency signal, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as the target mapping relationship, wherein the high frequency signal is a signal with a frequency greater than the first preset frequency.

5. The volume adjustment method according to claim 2, characterized in that: When the target signal type is the accompaniment sound type, the step of determining a target mapping relationship from a plurality of preset mapping relationships based on the target signal type and the noise level comprises: If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is less than a second preset frequency, a second mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of preset mapping relationships as a target mapping relationship, wherein a maximum gain factor in the second mapping relationship is less than a preset threshold; If the target frequency band signal is a medium-low frequency signal and the maximum frequency of the target frequency band signal is greater than or equal to the second preset frequency, or the target frequency band signal is a high frequency signal, a third mapping relationship corresponding to the noise level and the accompaniment sound type is determined from a plurality of the preset mapping relationships as the target mapping relationship, wherein the third mapping relationship is a correspondence between the degree values ​​of each accompaniment sound and the gain factor under the noise level, and the minimum gain factor in the third mapping relationship is greater than or equal to the preset threshold value.

6. The volume adjustment method according to claim 2, characterized in that: The target signal type further includes: unknown type, and the method further includes: When the target signal type is the unknown type, a Bark frequency scale formula in a plurality of the preset mapping relationships is used as a target mapping relationship.

7. The volume adjustment method according to any one of claims 1 to 6, characterized in that: The step of performing volume gain processing on the target frequency band signal in each frequency band signal of the input audio signal according to the target gain factor comprises: If the human voice level value is greater than the maximum value of the preset range, a signal greater than a preset frequency among the target frequency band signals in each frequency band signal of the input audio signal is determined as a signal to be adjusted; Perform volume gain processing on the signal to be adjusted according to the target gain factor.

8. A volume adjustment device, characterized in that: The volume adjustment device comprises: An acquisition module, used for acquiring an input audio signal of an audio device, and determining a vocal level value and an accompaniment sound level value of the input audio signal; A determination module, configured to determine a target gain factor based on the vocal level value and the accompaniment sound level value, wherein the target gain factor is positively correlated with a difference between the vocal level value and the accompaniment sound level value; The adjustment module is used to perform volume gain processing on a target frequency band signal among the frequency band signals of the input audio signal according to the target gain factor, wherein the target frequency band signal is a frequency band signal with the largest signal energy among the frequency band signals of the input audio signal.

9. A volume adjustment device, characterized in that: The volume adjustment device comprises: a memory, a processor, and a volume adjustment program stored in the memory and executable on the processor. When the volume adjustment program is executed by the processor, the steps of the volume adjustment method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a volume adjustment program, and when the volume adjustment program is executed by the processor, the steps of the volume adjustment method according to any one of claims 1 to 7 are implemented.

Images