Audio processing methods and apparatus, non-transitory computer-readable storage media

Abstract

An audio processing method, an audio processing apparatus, and a non-transitory computer-readable storage medium are disclosed. The audio processing method includes: generating a control command based on a first audio signal; generating a second audio signal based on the control command; and outputting the second audio signal to suppress a third audio signal. The sum of the phases of the second and third audio signals is less than a phase threshold, and the first audio signal occurs earlier than the third audio signal.

Description

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 344,642, filed May 23, 2022; U.S. Provisional Patent Application No. 63 / 351,439, filed June 13, 2022; and U.S. Provisional Patent Application No. 63 / 352,213, filed June 14, 2022, the contents of which are incorporated herein by reference in their entirety. Technical Field

[0002] Embodiments of this disclosure relate to an audio processing method, an audio processing apparatus, and a non-transitory computer-readable storage medium. Background Technology

[0003] Currently, noise reduction methods mainly include active noise reduction and passive noise reduction. Active noise reduction works by generating an inverse signal equal to or opposite to the external noise through a noise reduction system to neutralize the noise, thereby achieving noise reduction. Passive noise reduction mainly achieves noise reduction by creating a closed space around the object or using sound-insulating materials to block external noise.

[0004] Active noise cancellation typically employs a destructive superposition of a lagging, out-of-phase audio signal with the originally received audio signal (e.g., noise) to suppress the audio. One active noise cancellation process is as follows: First, an audio signal Vn generated by a sound source is received via a microphone and sent to a processor. The processor then inverts the audio signal Vn to generate an inverted audio signal Vn' and outputs this inverted audio signal Vn' to a speaker. The speaker emits this inverted audio signal Vn'. The human ear can receive both the inverted audio signal Vn' and the original audio signal Vn, and their destructive superposition can suppress the audio. However, in this active noise cancellation, due to the time required for signal processing and transmission, the timing of the inverted audio signal Vn' output by the speaker is inevitably lagging behind the timing of the original audio signal Vn received by the microphone. Consequently, the timing of the inverted audio signal Vn' received by the human ear is also inevitably lagging behind the timing of the original audio signal Vn, resulting in poor noise cancellation or even failure to achieve noise cancellation. There is inevitably a delay between the input (microphone) and the output (speaker). The lower the input-to-output delay, the smaller the time difference between the received out-of-phase audio Vn' and the received audio Vn, resulting in better noise cancellation. Therefore, active noise cancellation has extremely stringent requirements for end-to-end latency. This necessitates the use of high-speed analog-to-digital converters and high-speed computing hardware to achieve low latency and good audio suppression, leading to high development costs and a less flexible architecture. Therefore, avoiding the impact of end-to-end latency on active noise cancellation and achieving better audio suppression are problems that need to be solved. Summary of the Invention

[0005] To address the aforementioned problems, at least one embodiment of this disclosure provides an audio processing method, comprising: generating a control command based on a first audio signal; generating a second audio signal based on the control command; and outputting the second audio signal to suppress a third audio signal, wherein the sum of the phases of the second audio signal and the third audio signal is less than a phase threshold, and the first audio signal occurs earlier than the third audio signal.

[0006] For example, in an audio processing method provided in at least one embodiment of this disclosure, the step of outputting the second audio signal to suppress the third audio signal includes: determining a first moment for outputting the second audio signal based on the control instruction; outputting the second audio signal at the first moment, wherein the third audio signal begins to appear from a second moment, and the absolute value of the time difference between the first moment and the second moment is less than a time threshold.

[0007] For example, in the audio processing method provided in at least one embodiment of this disclosure, the time difference between the first moment and the second moment is 0.

[0008] For example, in an audio processing method provided in at least one embodiment of this disclosure, generating a control command based on a first audio signal includes: acquiring the first audio signal; processing the first audio signal to predict a fourth audio signal; and generating the control command based on the fourth audio signal.

[0009] For example, in the audio processing method provided in at least one embodiment of this disclosure, the second audio signal and / or the third audio signal and / or the fourth audio signal are periodic or intermittent time-domain signals.

[0010] For example, in an audio processing method provided in at least one embodiment of this disclosure, the step of processing the first audio signal to predict a fourth audio signal includes: generating a first audio feature code based on the first audio signal; querying a lookup table based on the first audio feature code to obtain a second audio feature code; and predicting the fourth audio signal based on the second audio feature code.

[0011] For example, in the audio processing method provided in at least one embodiment of this disclosure, the lookup table includes at least one first encoded field.

[0012] For example, in the audio processing method provided in at least one embodiment of this disclosure, the lookup table further includes at least one second encoding field, and a plurality of the first encoding fields constitute a second encoding field.

[0013] For example, in the audio processing method provided in at least one embodiment of this disclosure, the second audio feature encoding includes at least one first encoding field and / or at least one second encoding field.

[0014] For example, in an audio processing method provided in at least one embodiment of this disclosure, obtaining the first audio signal includes: acquiring an initial audio signal; and performing downsampling processing on the initial audio signal to obtain the first audio signal.

[0015] For example, in an audio processing method provided in at least one embodiment of this disclosure, obtaining the first audio signal includes: acquiring an initial audio signal; and filtering the initial audio signal to obtain the first audio signal.

[0016] For example, in the audio processing method provided in at least one embodiment of this disclosure, the phase of the second audio signal is opposite to the phase of the third audio signal.

[0017] At least one embodiment of this disclosure also provides an audio processing apparatus, comprising: an instruction generation module configured to generate a control instruction based on a first audio signal; an audio generation module configured to generate a second audio signal based on the control instruction; and an output module configured to output the second audio signal to suppress a third audio signal; wherein the sum of the phases of the second audio signal and the third audio signal is less than a phase threshold, and the first audio signal occurs earlier than the third audio signal.

[0018] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the output module includes a timing determination submodule and an output submodule. The timing determination submodule is configured to determine a first timing for outputting the second audio signal based on the control command. The output submodule is configured to output the second audio signal at the first timing, wherein the third audio signal begins to appear from a second timing, and the absolute value of the time difference between the first timing and the second timing is less than a time threshold.

[0019] For example, in the audio processing apparatus provided in at least one embodiment of this disclosure, the time difference between the first moment and the second moment is 0.

[0020] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the instruction generation module includes an audio acquisition submodule, a prediction submodule, and a generation submodule. The audio acquisition submodule is configured to acquire the first audio signal; the prediction submodule is configured to process the first audio signal to predict a fourth audio signal; and the generation submodule is configured to generate the control instruction based on the fourth audio signal.

[0021] For example, in the audio processing apparatus provided in at least one embodiment of this disclosure, the second audio signal and / or the third audio signal and / or the fourth audio signal are periodic or intermittent time-domain signals.

[0022] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the prediction submodule includes a query unit and a prediction unit. The query unit is configured to generate a first audio feature code based on the first audio signal and to query a lookup table based on the first audio feature code to obtain a second audio feature code. The prediction unit is configured to predict the fourth audio signal based on the second audio feature code.

[0023] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the lookup table includes at least one first encoded field.

[0024] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the lookup table further includes at least one second encoding field, and a plurality of the first encoding fields constitute a second encoding field.

[0025] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the second audio feature encoding includes at least one first encoding field and / or at least one second encoding field.

[0026] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the audio acquisition submodule includes an acquisition unit and a downsampling processing unit. The acquisition unit is configured to acquire an initial audio signal; the downsampling processing unit is configured to perform downsampling processing on the initial audio signal to obtain the first audio signal.

[0027] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the audio acquisition submodule includes an acquisition unit and a filtering unit. The acquisition unit is configured to acquire an initial audio signal, and the filtering unit is configured to filter the initial audio signal to obtain the first audio signal.

[0028] For example, in an audio processing apparatus provided in at least one embodiment of this disclosure, the phase of the second audio signal is opposite to the phase of the third audio signal.

[0029] At least one embodiment of this disclosure also provides an audio processing apparatus, comprising: one or more memories storing computer-executable instructions non-transitoryly; and one or more processors configured to execute the computer-executable instructions, wherein the computer-executable instructions, when executed by the one or more processors, implement the audio processing method according to any embodiment of this disclosure.

[0030] At least one embodiment of this disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer-executable instructions that, when executed by a processor, implement the audio processing method according to any embodiment of this disclosure.

[0031] According to any embodiment of the present disclosure, the audio processing method, audio processing apparatus, and non-transient computer-readable storage medium learn the characteristics of the current audio signal (i.e., the first audio signal) to generate an inverted audio signal (i.e., the second audio signal) for the future audio signal to suppress the future audio signal (i.e., the third audio signal). This avoids the problem of the inverted audio signal and the audio signal to be suppressed being out of sync due to the delay between the input and output ends, thereby improving the noise reduction effect. It can significantly reduce or even eliminate the impact of the delay between the input and output ends on noise reduction, and the audio suppression effect is better than that of the outdated active noise reduction systems commonly used in the industry. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments will be briefly described below. Obviously, the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure.

[0033] Figure 1 A schematic block diagram of an audio processing system provided for at least one embodiment of this disclosure;

[0034] Figure 2A A schematic flowchart illustrating an audio processing method provided for at least one embodiment of this disclosure;

[0035] Figure 2B for Figure 2A A schematic flowchart of step S10 is shown;

[0036] Figure 2C for Figure 2B A schematic flowchart of step S102 is shown;

[0037] Figure 3 A schematic diagram of a first audio signal and a third audio signal provided for at least one embodiment of this disclosure;

[0038] Figure 4 A schematic diagram of a third audio signal and a fourth audio signal provided for at least one embodiment of this disclosure;

[0039] Figure 5A A schematic diagram of an audio signal provided for some embodiments of this disclosure;

[0040] Figure 5B for Figure 5A A magnified schematic diagram of the audio signal within the dashed rectangle P1 in the diagram;

[0041] Figure 6 A schematic block diagram of an audio processing apparatus provided for at least one embodiment of this disclosure;

[0042] Figure 7 A schematic block diagram of another audio processing apparatus provided for at least one embodiment of this disclosure; and

[0043] Figure 8 A schematic diagram of a non-transitory computer-readable storage medium provided for at least one embodiment of the present disclosure. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0045] Unless otherwise defined, the technical or scientific terms used in this disclosure shall have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms “first,” “second,” and similar terms used in this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as “comprising” or “including” mean that an element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as “connected” or “linked” are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0046] To keep the following description of the embodiments of this disclosure clear and concise, detailed descriptions of some known functions and known components have been omitted.

[0047] At least one embodiment of this disclosure provides an audio processing method. The audio processing method includes: generating a control command based on a first audio signal; generating a second audio signal based on the control command; and outputting the second audio signal to suppress a third audio signal. The sum of the phases of the second audio signal and the third audio signal is less than a phase threshold, and the first audio signal occurs earlier than the third audio signal.

[0048] In the audio processing method provided in the embodiments of this disclosure, by learning the characteristics of the current audio signal (i.e., the first audio signal), an inverted audio signal (i.e., the second audio signal) of the future audio signal is generated to suppress the future audio signal (i.e., the third audio signal). This avoids the problem of the inverted audio signal and the audio signal to be suppressed being out of sync due to the delay between the input and output ends, thereby improving the noise reduction effect. It can significantly reduce or even eliminate the impact of the delay between the input and output ends on noise reduction, and the audio suppression effect is better than that of the outdated active noise reduction system commonly used in the industry.

[0049] Embodiments of this disclosure also provide an audio processing apparatus and a non-transitory computer-readable storage medium. The audio processing method can be applied to the audio processing apparatus provided in the embodiments of this disclosure, and the audio processing apparatus can be configured on an electronic device. The electronic device can be a personal computer, a mobile terminal, a car headrest, etc., and the mobile terminal can be a mobile phone, headphones, a tablet computer, or other hardware device.

[0050] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings, but this disclosure is not limited to these specific embodiments.

[0051] Figure 1 This is a schematic block diagram of an audio processing system provided in at least one embodiment of the present disclosure. Figure 2A This is a schematic flowchart illustrating an audio processing method provided in at least one embodiment of the present disclosure. Figure 2B for Figure 2A The schematic flowchart of step S10 shown is as follows. Figure 2C for Figure 2B The schematic flowchart of step S102 shown is as follows. Figure 3 This is a schematic diagram of a first audio signal and a third audio signal provided for at least one embodiment of the present disclosure.

[0052] Figure 1 The audio processing system shown can be used to implement the audio processing method provided in any embodiment of this disclosure, for example, Figure 2A The audio processing method shown. Figure 1As shown, the audio processing system may include an audio receiving section, an audio processing section, and an audio output section. The audio receiving section receives the audio signal Sn1 emitted by a sound source at time t1, and then transmits Sn1 to the audio processing section. The audio processing section processes Sn1 to predict the inverse audio signal Sn2 of the future audio signal Sn3; this inverse audio signal Sn2 is then output through the audio output section. The inverse audio signal Sn2 can be used to suppress the future audio signal Sn3 generated by the sound source at time t2, which is later than t1. For example, a target object (e.g., a human ear) can simultaneously receive both the inverse audio signal Sn2 and the future audio signal Sn3, allowing them to destructively superimpose, thereby achieving noise cancellation.

[0053] For example, the audio receiving section may include a microphone, an amplifier (e.g., a microphone amplifier), an analog-to-digital converter (ADC), a downsampler, etc.; the audio processing section may include an AI engine and / or a digital signal processor (DSP), etc.; and the audio output section may include an upsampler, a digital-to-analog converter (DAC), an amplifier (e.g., a speaker amplifier), and a speaker, etc.

[0054] like Figure 2A As shown, an embodiment of this disclosure provides an audio processing method including steps S10 to S12. In step S10, a control command is generated based on a first audio signal; in step S11, a second audio signal is generated based on the control command; and in step S12, the second audio signal is output to suppress a third audio signal.

[0055] For example, the first audio signal can be Figure 1 The audio signal Sn1 shown can be the second audio signal. Figure 1 The inverted audio signal Sn2 shown can be the third audio signal. Figure 1 The future audio signal Sn3 is shown.

[0056] For example, the audio receiving section can receive a first audio signal; the audio processing section can process the first audio signal to generate control instructions, and generate a second audio signal based on the control instructions; the audio output section can output the second audio signal, thereby suppressing the third audio signal.

[0057] For example, the first audio signal appears earlier than the third audio signal. Figure 3As shown, the first audio signal begins to appear at time t11, and the third audio signal begins to appear at time t21. On the time axis t, time t11 is earlier than time t21. For example, the time period during which the first audio signal exists can be the period between time t11 and time t12, and the time period during which the third audio signal exists can be the period between time t21 and time t22. Considering factors such as the time required for signal processing, time t12 and time t21 may not be the same; time t12 is earlier than time t21.

[0058] It should be noted that, in the embodiments of this disclosure, "the time period in which the audio signal exists or the time of its occurrence" refers to the time period in which the audio signal exists or the time of its occurrence.

[0059] For example, the sum of the phases of the second and third audio signals is less than a phase threshold. The phase threshold can be set according to actual conditions, and this disclosure does not impose specific limitations on it. For example, in some embodiments, the phases of the second and third audio signals are opposite, thereby achieving complete noise cancellation, that is, completely suppressing the third audio signal. In this case, when the second and third audio signals are received by an audio acquisition device (e.g., a microphone), the error energy of the audio signal received by the audio acquisition device is 0; if the second and third audio signals are received by the human ear, it is equivalent to the person not hearing any sound.

[0060] For example, in some embodiments, the first audio signal can be a time-domain audio signal with the maximum volume (maximum amplitude) between time t11 and time t12. The first audio signal is not an audio signal of a specific frequency. Therefore, the audio processing method provided by the embodiments of this disclosure does not need to extract spectral features from the audio signal to generate a spectrogram, thereby simplifying the audio signal processing process and saving processing time.

[0061] For example, the first and third audio signals can be audio signals generated by the external environment, machines, etc., such as the sound of machines running, the sound of electric drills and chainsaws during the renovation process. For example, machines can include household appliances (air conditioners, range hoods, washing machines, etc.).

[0062] For example, in some embodiments, such as Figure 2B As shown, step S10 may include steps S101 to S103. In step S101, a first audio signal is acquired; in step S102, the first audio signal is processed to predict a fourth audio signal; and in step S103, a control command is generated based on the fourth audio signal. In the audio processing method provided in the embodiments of this disclosure, an audio signal (i.e., the fourth audio signal) is predicted by learning the characteristics of the current audio signal (i.e., the first audio signal).

[0063] For example, the fourth audio signal is a predicted future audio signal. For instance, on the timeline, the duration of the fourth audio signal lags behind the duration of the first audio signal. Alternatively, the duration of the fourth audio signal might be the same as the duration of the third audio signal, thus the duration of the fourth audio signal could also be... Figure 3 The time interval shown is between time t21 and time t22.

[0064] Figure 4 This is a schematic diagram illustrating a third audio signal and a fourth audio signal provided for at least one embodiment of this disclosure. Figure 4 In the example shown, the horizontal axis represents time, and the vertical axis represents amplitude, which can be represented as a voltage value. For example... Figure 4 As shown, in one embodiment, the predicted fourth audio signal is substantially the same as the third audio signal.

[0065] For example, in one embodiment, the third audio signal and the fourth audio signal can be exactly the same. In this case, the phase of the second audio signal finally generated based on the fourth audio signal is opposite to the phase of the third audio signal, thereby achieving complete noise cancellation.

[0066] For example, in step S102, processing the first audio signal to predict the fourth audio signal may include processing the first audio signal through a neural network to predict the fourth audio signal.

[0067] For example, neural networks may include recurrent neural networks, long short-term memory networks, or generative adversarial networks. In embodiments of this disclosure, features of audio signals can be learned based on artificial intelligence to predict audio signals for a future time period that has not yet occurred, and an inverse audio signal for that future time period can be generated accordingly to suppress the audio signal for that time period.

[0068] For example, in some embodiments, such as Figure 2C As shown, step S102 may include steps S1021 to S1023. In step S1021, a first audio feature code is generated based on the first audio signal. In step S1022, a lookup table is queried based on the first audio feature code to obtain a second audio feature code. In step S1023, a fourth audio signal is predicted based on the second audio feature code.

[0069] For example, the first audio signal can be an analog signal, which can be processed by an analog-to-digital converter to obtain a processed first audio signal. The processed first audio signal is a digital signal, and a first audio feature code can be generated based on the processed first audio signal.

[0070] For example, the first audio signal can be a digital signal, such as a PDM (Pulse-density-modulation) signal. In this case, the first audio feature code can be directly generated based on the first audio signal. The PDM signal can be represented by binary numbers 0 and 1.

[0071] For example, any suitable encoding method can be used to implement the first audio feature encoding. For example, in some embodiments, when representing an audio signal, the changing state of the audio signal can be used to describe the audio signal, and multiple bits can be used to represent the changing state of an audio signal. For example, two bits can be used to represent the changing state of the audio signal. In some examples, as shown in Table 1 below, 00 indicates that the audio signal increases, 01 indicates that the audio signal decreases, 10 indicates that there is no audio signal, and 11 indicates that the audio signal remains unchanged.

[0072] Bit Changes in audio signals 00 The audio signal becomes larger 01 The audio signal becomes smaller 10 No audio signal 11 The audio signal remains unchanged.

[0073] Table 1

[0074] "Audio signal increases" means that the amplitude of the audio signal increases over time within a unit time period (each time step), "Audio signal decreases" means that the amplitude of the audio signal decreases over time within a unit time period, "Audio signal remains unchanged" means that the amplitude of the audio signal remains unchanged over time within a unit time period, and "No audio signal" means that there is no audio signal within a unit time period, that is, the amplitude of the audio signal is 0.

[0075] Figure 5A This is a schematic diagram of an audio signal provided in some embodiments of this disclosure. Figure 5B for Figure 5A A magnified schematic diagram of the audio signal within the dashed rectangle P1.

[0076] exist Figure 5A In the graph, the horizontal axis represents time (ms), and the vertical axis represents the amplitude of the audio signal (volts). For example... Figure 5A As shown, the audio signal V is a periodically changing signal, and the periodic pattern of the audio signal V is the pattern shown in the dashed rectangle P2.

[0077] like Figure 5BAs shown, the amplitude of the audio signal represented by waveform segment 30 remains constant with time t, and the time corresponding to waveform segment 30 is one unit time interval. Therefore, waveform segment 30 can be represented as audio feature code (11). Similarly, the amplitude of the audio signal represented by waveform segment 31 gradually increases with time t, and the time corresponding to waveform segment 31 is four unit time intervals. Therefore, waveform segment 31 can be represented as audio feature code (00,00,00,00). The amplitude of the audio signal represented by waveform segment 32 remains constant with time t, and the time corresponding to waveform segment 32 is one unit time interval. Therefore, waveform segment 32 can be represented as audio feature code (11). The amplitude of the audio signal represented by waveform segment 33 gradually decreases with time t, and the time corresponding to waveform segment 33 is six unit time intervals. Therefore, waveform segment 33 can be represented as audio feature code (01,01,01,01,01,01,01). The amplitude of the audio signal represented by segment 34 remains constant with time t. The time corresponding to waveform segment 34 is one unit time interval, so waveform segment 34 can be represented as audio feature code (11); the amplitude of the audio signal represented by waveform segment 35 gradually increases with time t. The time corresponding to waveform segment 35 is eight unit time intervals, so waveform segment 35 can be represented as audio feature code (00,00,00,00,00,00,00,00); and so on, waveform segment 36 can be represented as audio feature code (01,01,01,01,01,01,01,01,01,01,01,01,01,01,01), waveform segment 37 can be represented as audio feature code (11), and waveform segment 38 can be represented as audio feature code (00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00). Therefore, Figure 5B The audio feature encoding corresponding to the audio signal shown can be represented as {11,00,00,00,00,11,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,01,01,01,01,01,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,…}.

[0078] For example, in some embodiments, the codebook includes at least one first encoded field. In other embodiments, the codebook further includes at least one second encoded field, with multiple first encoded fields forming a single second encoded field, thereby enabling the formation of dimensionality-reduced high-order features from combinations of low-level features. For example, the encoding method of the encoded field (codeword, which may include both first and second encoded fields) in the codebook can be the same as the encoding method of the first audio feature described above.

[0079] For example, in some embodiments, when using two bits to represent the changing state of an audio signal to achieve feature encoding, the first encoding field can be one of 00, 01, 10, and 11. The second encoding field can be formed by combining 00, 01, 10, and 11. For example, a second encoding field can be represented as {00,00,00,01,01,01,11,11,01,…}, which is composed of combinations of 00, 01, and 11.

[0080] For example, when a lookup table includes multiple second-encoded fields, the number of first-encoded fields included in each of the multiple second-encoded fields can be different.

[0081] It should be noted that when more bits (e.g., 3 bits, 4 bits, etc.) are used to represent the changing state of the audio signal to achieve feature encoding, the number of types of the first encoding field can be greater. For example, when 3 bits are used to represent the changing state of the audio signal, the number of types of the first encoding field can be up to 8. In this case, the first encoding field can be some or all of 000, 001, 010, 011, 100, 101, 110, and 111.

[0082] For example, one or more second encoded fields can be combined to obtain a third encoded field, or one or more second encoded fields and one or more first encoded fields can be combined to obtain a third encoded field. Similarly, one or more third encoded fields can be combined, or one or more third encoded fields can be combined with first and / or second encoded fields to obtain higher-order encoded fields. In embodiments of this disclosure, low-order feature codes can be combined to obtain high-order feature codes, thereby achieving more efficient and longer-term prediction.

[0083] For example, the second audio feature encoding includes at least one first encoded field and / or at least one second encoded field. For example, in some embodiments, the second audio feature encoding may include one or more complete second encoded fields, or the second audio feature encoding may include a portion of a first encoded field within a second encoded field.

[0084] It should be noted that when the lookup table includes a third encoding field, the second audio feature encoding may include at least one first encoding field and / or at least one second encoding field and / or at least one third encoding field.

[0085] For example, in one embodiment, the lookup table includes a second encoded field W1, a second encoded field W2, and a second encoded field W3, and W1 = {11,00,00,00,00,11,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,01,01,01,01,01,01,01,01,01,01,01,11,00,00,0 0,00,00,00,00,00,00,00,00,00,00,00,00,00,….}, W2={11,01,00,00,01,01,01,01,01,01 ,01,….}, W3={11,00,01,00,00,01,01,01,11,00,00,00,01,01,01,01,01,01,01,01,01,….}.

[0086] In one embodiment, such as Figure 5B As shown, starting from time t31, the audio acquisition device continuously acquires the first audio signal. When the first feature encoding field corresponding to the first audio signal acquired by the audio acquisition device is represented as {11}, corresponding to waveform segment 30, a lookup table is used to determine whether there is a certain encoding field (including the first encoding field and the second encoding field) that includes {11}. In the above example, the lookup table shows that the second encoding field W1, the second encoding field W2, and the second encoding field W3 all include {11}. At this time, the second encoding field W1, the second encoding field W2, and the second encoding field W3 are all used as the output encoding fields in the output encoding field list.

[0087] Then, as Figure 5B As shown, when the second feature encoding field corresponding to the first audio signal acquired by the audio acquisition device is represented as {00}, corresponding to the first unit time period in waveform segment 31, the lookup table is queried again (at this time, only the output encoding fields in the output encoding field column can be queried, thus saving query time; however, the entire lookup table can also be queried) to determine whether there is an encoding field in the lookup table that includes {11,00}. In the above example, the second encoding field W1 and the second encoding field W3 in the lookup table are both found to include {11,00}. Since the second encoding field W2 includes {11,01} but not {11,00}, it does not meet the feature of the first audio signal acquired by the audio acquisition device. Therefore, the second encoding field W2 can be deleted from the output encoding field list. At this time, the second encoding field W1 and the second encoding field W3 are the output encoding fields in the output encoding field list.

[0088] Then, when the third feature encoding field corresponding to the first audio signal acquired by the audio acquisition device is represented as {00}, corresponding to the second unit time period in waveform segment 31, the lookup table is queried again to determine whether there exists an encoding field in the lookup table that includes {11,00,00}. In the example above, the lookup table is found to contain the second encoding field W1, which includes {11,00,00}. Therefore, it can be predicted that the following audio signal should follow the pattern of the second encoding field W1. For the first three encoded fields {11,00,00} in the second encoded field W1, since their corresponding audio signals have passed in time, all subsequent encoded fields starting from the fourth field (i.e., {00}) in the second encoded field W1 can be output as the predicted second audio encoded features. At this time, the second audio feature encoding is represented as {00,00,11,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,01,01,01,01,01,01,01,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,…….}.

[0089] It should be noted that in practical applications, the number of feature coding fields that need to be matched to determine the second audio feature code can be adjusted according to factors such as the actual application scenario and design requirements. For example, in the example above, the second audio feature code can be determined when 3 feature coding fields are matched (in practical applications, 10, 20, 50, etc. can be matched).

[0090] For example, in the example above, the first audio feature code corresponding to the first audio signal includes three feature code fields, represented as {11,00,00}, as shown below. Figure 5B As shown, the time period corresponding to the first audio signal is from time t31 to time t32. Considering factors such as the system's signal processing time, the system actually needs to output the second audio signal at time t33, which is later than time t32. At this time, the time period corresponding to the first two feature coding fields {00,00} in the second audio feature coding (i.e., the time period between time t32 and time t33) has passed. Therefore, the audio feature coding corresponding to the predicted fourth audio signal is actually represented as {11,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,01,01,01,01,01,01,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,….}.

[0091] For example, if the third audio signal and the fourth audio signal are exactly the same, then the audio feature code corresponding to the third audio signal is also represented as {11,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,01,01,01,01,01,01,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,….}.

[0092] For example, the second audio signal is the signal obtained by inverting the fourth audio signal. That is, the second audio signal can be the inverted audio signal of the pattern {11,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,01,01,01,01,01,01,01,01,01,01,01,01,11,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,00,….}.

[0093] For example, in some embodiments, the durations of the second audio signal, the third audio signal, and the fourth audio signal are approximately the same, for example, completely identical.

[0094] For example, in some embodiments, a leading feature encoding field can be set for at least a portion of the first encoding field and / or the second encoding field in the lookup table. For instance, a leading feature encoding {11,00,00} can be set for the second encoding field W1. When this leading feature encoding field is detected, the second encoding field W1 is output as the second audio feature encoding. In this case, when the first audio feature encoding corresponding to the first audio signal is detected to be {11,00,00}, the first audio feature encoding corresponding to the first audio signal matches the leading feature encoding field {11,00,00}, thereby the second encoding field W1 can be output as the second audio feature encoding.

[0095] For example, a leading feature encoding field {11,00,00,01,01} can be set for the second encoding field W1. When a portion of the fields in this leading feature encoding field is detected, the second encoding field W1 and the remaining fields in the leading feature encoding field are output as the second audio feature encoding. In this case, when the first audio feature encoding corresponding to the first audio signal is detected as {11,00,00}, this first audio feature encoding matches the first three fields {11,00,00} in the leading feature encoding field. Therefore, the remaining fields {01,01} in the leading feature encoding field and the output of the second encoding field W1 can be used as the second audio feature encoding. At this time, the time corresponding to the first two feature encoding fields {01,01} in the second audio feature encoding (i.e., the remaining fields in the leading feature encoding field) can be the time when the system processes the signal. Thus, the audio feature encoding corresponding to the predicted fourth audio signal can actually be the complete second encoding field W1.

[0096] It should be noted that the length of the leading feature encoding field can be adjusted according to the actual situation, and this disclosure does not impose any restrictions on it.

[0097] It's worth noting that, for lookup tables, when the memory used to store the lookup table is large enough and the content stored in the lookup table is rich enough (i.e., there are enough combinations of encoded fields in the lookup table), all types of audio signals that the user wants to eliminate can be eliminated. Similarly, for neural networks, when the samples used to train the neural network are rich enough and the types of samples are rich enough, it is also possible to predict any type of audio signal that the user wants to eliminate based on the neural network.

[0098] For example, the lookup table can be stored in memory in the form of a table or the like, and the embodiments of this disclosure do not limit the specific form of the lookup table.

[0099] For example, predictions in neural networks can be achieved by using lookup tables.

[0100] For example, the second, third, and / or fourth audio signals are periodic or intermittent time-domain signals. Their signal characteristics are periodic or intermittent time-domain amplitude variations; that is, they possess continuous or intermittent repetition characteristics and have a fixed pattern. For intermittent audio signals, since there is no audio signal during the pauses, no spectral features can be extracted during the pauses. However, the pauses can become one of the time-domain features of the intermittent audio signal.

[0101] For example, in some embodiments, step S101 may include: acquiring an initial audio signal; and downsampling the initial audio signal to obtain a first audio signal.

[0102] Since the initial audio signal acquired by the audio acquisition device has a high sampling rate, it is not conducive to the processing of the back-end audio signal processing device (such as the Artificial Intelligence Engine, Digital Signal Processor, etc.). Therefore, the initial audio signal can be downsampled to achieve frequency reduction, making it easier for the audio signal processing device to process. For example, it can be downsampled to 48kHz or even lower.

[0103] For example, in some other embodiments, step S101 may include: acquiring an initial audio signal; filtering the initial audio signal to obtain a first audio signal.

[0104] In some applications, excessive quiet is unsafe. Therefore, bandwidth controllers can be used for filtering to suppress audio signals within a specific frequency range. For continuous and intermittent audio signals (e.g., knocking or dripping noises), the effective bandwidth of the first audio signal is set within the frequency range corresponding to the audio signal to be suppressed, such as 1kHz to 6kHz. This ensures that the user can still hear important sounds. For example, in the automotive field, it is essential to ensure that the driver can hear the horn, thus improving driving safety.

[0105] For example, in some embodiments, filtering and downsampling can be used in combination, and this disclosure does not limit the processing order of filtering and downsampling. For example, in some embodiments, acquiring the first audio signal may include: acquiring an initial audio signal; filtering the initial audio signal to obtain an audio signal within a predetermined frequency range; downsampling the audio signal within the predetermined frequency range to obtain the first audio signal; or, acquiring the first audio signal may include: acquiring an initial audio signal; downsampling the initial audio signal; and filtering the downsampled audio signal to obtain the first audio signal.

[0106] For example, control instructions may include the timing of the second audio signal output, the fourth audio signal, and a control signal indicating that the fourth audio signal should be inverted.

[0107] For example, in some embodiments, step S11 may include: determining a fourth audio signal and a control signal indicating that the fourth audio signal is inverted based on a control command; and inverting the fourth audio signal based on the control signal to generate a second audio signal.

[0108] For example, in some embodiments, step S12 may include: determining a first moment for outputting the second audio signal based on control instructions; and outputting the second audio signal at the first moment.

[0109] For example, the third audio signal begins to appear at the second moment, and the absolute value of the time difference between the first and second moments is less than the time threshold. It should be noted that the time threshold can be set according to the actual situation, and this disclosure does not impose any restrictions on it. The smaller the time threshold, the better the noise reduction effect.

[0110] For example, in some embodiments, the time difference between the first and second moments is 0, meaning the moment the second audio signal begins output is the same as the moment the third audio signal begins to appear. Figure 3 In the example shown, the time when the second audio signal begins to be output and the time when the third audio signal begins to appear are both time t21.

[0111] For example, the time difference between the first and second moments can be set according to the actual situation. For instance, the first and second moments can be set to ensure that the second and third audio signals are transmitted to the target object simultaneously, thereby avoiding the problem of the second and third audio signals being out of sync due to audio signal transmission, and further improving the noise reduction effect. For example, the target object can be a person's ear, a microphone, etc.

[0112] For example, the second audio signal can be output through a device such as a speaker that can convert electrical signals into sound signals.

[0113] It should be noted that if the audio acquisition device does not acquire an audio signal, the audio processing method provided in this disclosure may not be executed until the audio acquisition device acquires an audio signal, thereby saving power consumption.

[0114] In embodiments of this disclosure, the audio processing method can reduce or eliminate periodic audio signals (e.g., noise) in the ambient audio signal. For example, in an application scenario like a library, it can eliminate the sound of construction work at a nearby construction site. In such scenarios, it's not necessary to specifically know which audio signal to retain; the goal is simply to reduce the target noise to be eliminated in the environment. These target noises typically have characteristics of continuous repetition or intermittent repetition, and therefore can be predicted. It should be noted that the "target noise" can be determined based on the actual situation. For example, in an application scenario like a library, when there is a construction site nearby, the ambient audio signal can include two types of audio signals: the first is the sound of drilling at the construction site, and the second is the sound of people discussing things nearby. Typically, the sound of drilling at the construction site is periodic and usually has a fixed pattern, while the sound of people discussing things is unlikely to have a fixed pattern or periodicity. In this case, the target noise to be eliminated is the sound of drilling at the construction site. The audio processing method provided in the embodiments of this disclosure can predict the sound of drilling at the construction site, thereby eliminating or reducing it.

[0115] The audio processing method provided in this disclosure can be applied to car headrests to create a quiet zone near the driver's ears, preventing unnecessary external audio signals (e.g., engine noise, road noise, wind noise, and tire noise during vehicle operation) from interfering with the driver. For example, this audio processing method can also be applied to devices such as hair dryers, range hoods, vacuum cleaners, and non-inverter air conditioners to reduce the operating noise of these devices, allowing users to remain in noisy environments without being affected by ambient noise. This audio processing method can also be applied to headphones to reduce or eliminate external sounds, allowing users to better receive the sound emitted by the headphones (music or conversations, etc.).

[0116] At least one embodiment of this disclosure also provides an audio processing apparatus. Figure 6 This is a schematic block diagram of an audio processing apparatus provided for at least one embodiment of the present disclosure.

[0117] like Figure 6 As shown, the audio processing device 600 includes an instruction generation module 601, an audio generation module 602, and an output module 603. Figure 6 The components and structure of the audio processing device 600 shown are exemplary and not limiting. The audio processing device 600 may also include other components and structures as needed.

[0118] The instruction generation module 601 is configured to generate control instructions based on the first audio signal. The instruction generation module 601 is used to execute... Figure 2A Step S10 is shown.

[0119] The audio generation module 602 is configured to generate a second audio signal based on control commands. The audio generation module 602 is used to execute... Figure 2A Step S11 is shown.

[0120] Output module 603 is configured to output a second audio signal to suppress the third audio signal. Output module 603 is used to perform... Figure 2A Step S12 is shown.

[0121] For a detailed explanation of the functions implemented by the instruction generation module 601, please refer to the embodiments of the audio processing method described above. Figure 2A The description of step S10 shown, and the specific explanation of the functions implemented by the audio generation module 602, can be found in the embodiments of the audio processing method described above. Figure 2A The description of step S11 shown, and the specific explanation of the function implemented by the output module 603, can be found in the embodiments of the audio processing method described above. Figure 2A The relevant description of step S12 is shown below. The audio processing device can achieve similar or the same technical effects as the aforementioned audio processing method, and will not be repeated here.

[0122] For example, the first audio signal appears earlier than the third audio signal.

[0123] For example, the sum of the phases of the second audio signal and the third audio signal is less than a phase threshold. In some embodiments, the phases of the second audio signal and the third audio signal are opposite, thereby completely suppressing the third audio signal.

[0124] For example, in some embodiments, the instruction generation module 601 may include an audio acquisition submodule, a prediction submodule, and a generation submodule. The audio acquisition submodule is configured to acquire a first audio signal; the prediction submodule is configured to process the first audio signal to predict a fourth audio signal; and the generation submodule is configured to generate control instructions based on the fourth audio signal.

[0125] For example, the second audio signal and / or the third audio signal and / or the fourth audio signal are periodic or intermittent time-domain signals.

[0126] For example, the third audio signal and the fourth audio signal can be exactly the same.

[0127] For example, in some embodiments, the prediction submodule may process the first audio signal based on a neural network to predict the fourth audio signal. For example, the prediction submodule may include... Figure 1The AI ​​engine and / or digital signal processor in the audio processing section shown may include a neural network, such as a recurrent neural network, a long short-term memory network, or a generative adversarial network.

[0128] For example, in some implementations, the prediction submodule includes a query unit and a prediction unit. The query unit is configured to generate a first audio feature code based on a first audio signal and to query a lookup table based on the first audio feature code to obtain a second audio feature code. The prediction unit is configured to predict a fourth audio signal based on the second audio feature code.

[0129] For example, a query unit may include memory for storing lookup tables.

[0130] For example, in some embodiments, the lookup table may include at least one first encoded field. In other embodiments, the lookup table may also include at least one second encoded field, with multiple first encoded fields forming a single second encoded field. For details regarding the specific contents of the lookup table, please refer to the relevant descriptions in the embodiments of the above audio processing method; repeated descriptions will not be repeated here.

[0131] For example, the second audio feature encoding includes at least one first encoding field and / or at least one second encoding field.

[0132] For example, in some embodiments, the audio acquisition submodule includes an acquisition unit and a downsampling processing unit. The acquisition unit is configured to acquire an initial audio signal; the downsampling processing unit is configured to downsample the initial audio signal to obtain a first audio signal.

[0133] For example, in some embodiments, the audio acquisition submodule includes an acquisition unit and a filtering unit, wherein the acquisition unit is configured to acquire an initial audio signal; and the filtering unit is configured to filter the initial audio signal to obtain a first audio signal.

[0134] For example, the audio acquisition submodule can be implemented as follows: Figure 1 The audio receiving section is shown. For example, the acquisition unit may include an audio acquisition device, such as... Figure 1 The audio receiving section shown includes a microphone, etc. For example, the acquisition unit may also include an amplifier, an analog-to-digital converter, etc.

[0135] For example, in some embodiments, the output module 603 may include a timing determination submodule and an output submodule. The timing determination submodule is configured to determine a first timing for outputting the second audio signal based on control instructions; the output submodule is configured to output the second audio signal at the first timing.

[0136] For example, output module 603 can be implemented as Figure 1 The audio output section is shown.

[0137] For example, the third audio signal begins to appear at the second moment, and the absolute value of the time difference between the first and second moments is less than the time threshold.

[0138] For example, the time difference between the first moment and the second moment can be 0.

[0139] For example, the output submodule may include audio output devices such as speakers. The output submodule may also include digital-to-analog converters, etc.

[0140] For example, the instruction generation module 601, audio generation module 602, and / or output module 603 can be hardware, software, firmware, or any feasible combination thereof. For example, the instruction generation module 601, audio generation module 602, and / or output module 603 can be dedicated or general-purpose circuits, chips, or devices, or a combination of a processor and memory. The embodiments of this disclosure do not limit the specific implementation of the above-described modules, submodules, and units.

[0141] At least one embodiment of this disclosure also provides an audio processing apparatus. Figure 7 A schematic block diagram of another audio processing apparatus provided for at least one embodiment of the present disclosure.

[0142] For example, such as Figure 7 As shown, the audio processing apparatus 700 includes one or more memories 701 and one or more processors 702. The one or more memories 701 are configured to non-transitory store computer-executable instructions; the one or more processors 702 are configured to execute the computer-executable instructions. The computer-executable instructions, when executed by the one or more processors 702, implement the audio processing method according to any of the above embodiments. For specific implementation details and explanations of the various steps of this audio processing method, please refer to the description of the embodiments of the audio processing method described above, and will not be repeated here.

[0143] For example, in some embodiments, the audio processing apparatus 700 may further include a communication interface and a communication bus. The memory 701, processor 702, and communication interface can communicate with each other via the communication bus, and components such as the memory 701, processor 702, and communication interface can also communicate via a network connection. This disclosure does not limit the type and function of the network.

[0144] For example, a communication bus can be a Peripheral Component Interconnect Standard (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into address bus, data bus, control bus, etc.

[0145] For example, the communication interface is used to enable communication between the audio processing device 700 and other devices. The communication interface can be a Universal Serial Bus (USB) interface, etc.

[0146] For example, processor 702 and memory 701 can be located on the server side (or in the cloud).

[0147] For example, processor 702 can control other components in audio processing device 700 to perform desired functions. Processor 702 can be a central processing unit (CPU), network processor (NP), etc.; it can also be a digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. The central processing unit (CPU) can be based on x86 or ARM architecture, etc.

[0148] For example, memory 701 may include any combination of one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), USB memory, flash memory, etc. One or more computer-executable instructions may be stored on the computer-readable storage medium, and processor 702 may execute the computer-executable instructions to implement various functions of audio processing device 700. Various application programs and various data may also be stored in the storage medium.

[0149] For example, a detailed description of the audio processing process performed by the audio processing device 700 can be found in the relevant description in the embodiments of the audio processing method, and repeated descriptions will not be repeated here.

[0150] For example, in some embodiments, the audio processing device 700 may be presented in the form of a chip, a small device / equipment, etc.

[0151] Figure 8 This is a schematic diagram of a non-transitory computer-readable storage medium provided for at least one embodiment of the present disclosure. For example, such as... Figure 8 As shown, one or more computer-executable instructions 1001 may be stored non-transitory on the non-transitory computer-readable storage medium 1000. For example, when the computer-executable instructions 1001 are executed by a processor, one or more steps in the audio processing method described above may be performed.

[0152] For example, the non-transitory computer-readable storage medium 1000 can be applied to the audio processing apparatus 700 described above, and may include, for example, the memory 701 in the audio processing apparatus 700.

[0153] For details regarding the non-transitory computer-readable storage medium 1000, please refer to [link / reference]. Figure 7 The description of the memory 701 in the embodiment of the audio processing device 600 shown will not be repeated here.

[0154] At least one embodiment of this disclosure provides an audio processing method, an audio processing apparatus, and a non-transient computer-readable storage medium. By learning the characteristics of a current audio signal, an audio signal (i.e., a fourth audio signal) is predicted. Based on this predicted audio signal, an inverted audio signal of a future audio signal is generated to suppress the future audio signal. This avoids the problem of asynchrony between the inverted audio signal and the audio signal to be suppressed due to the delay between the input and output ends, improving the noise reduction effect. It can significantly reduce or even eliminate the impact of the input-to-output delay on noise reduction, and the audio suppression effect is better than that of commonly used, outdated active noise reduction systems. Since the first audio signal is a time-domain signal and not an audio signal of a specific frequency, the implementation of this disclosure... The audio processing method provided in this example does not require extracting spectral features from the audio signal to generate a spectrogram, thereby simplifying the audio signal processing process and saving processing time. In the lookup table, low-order feature codes can be combined to obtain high-order feature codes, thereby achieving more efficient and longer-term prediction. Furthermore, in this audio processing method, filtering can be performed through a bandwidth controller to suppress audio signals within a specific frequency range, ensuring that the user can still hear important sounds. For example, when applied in the automotive field, it is necessary to ensure that the driver can hear the horn, etc., to improve driving safety. In addition, if no audio signal is acquired, the audio processing method provided in this disclosure can be left unexecuted until an audio signal is acquired, thereby saving power consumption.

[0155] The following points should be noted regarding this disclosure:

[0156] (1) The accompanying drawings of the embodiments of this disclosure only involve the structures involved in the embodiments of this disclosure. Other structures can be referred to the general design.

[0157] (2) Where there is no conflict, the embodiments of this disclosure and the features in the embodiments can be combined with each other to obtain new embodiments.

[0158] The above description is only a specific embodiment of this disclosure, but the protection scope of this disclosure is not limited thereto. The protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. An audio processing method, comprising: generating a control instruction based on a first audio signal; generating a second audio signal based on the control instruction; outputting the second audio signal to suppress a third audio signal, wherein a sum of a phase of the second audio signal and a phase of the third audio signal is less than a phase threshold, and the first audio signal occurs earlier in time than the third audio signal; wherein the generating the control instruction based on the first audio signal comprises: obtaining the first audio signal; processing the first audio signal to predict a fourth audio signal; generating the control instruction based on the fourth audio signal, wherein the processing the first audio signal to predict the fourth audio signal comprises: generating a first audio feature code based on the first audio signal, wherein the first audio feature code is used to indicate a change state of a waveform of the first audio signal; querying a lookup table based on the first audio feature code to obtain a leading feature code field matching the first audio feature code; determining a second audio feature code corresponding to the leading feature code field based on the leading feature code field; predicting the fourth audio signal based on a partial feature code field in the second audio feature code, wherein the partial feature code field is a remaining field other than a first N feature code field in the second audio feature code, and N is a positive integer.

2. The audio processing method of claim 1, wherein, the outputting the second audio signal to suppress the third audio signal comprises: determining a first time instant for outputting the second audio signal based on the control instruction; outputting the second audio signal at the first time instant, wherein the third audio signal occurs from a second time instant, and an absolute value of a time difference between the first time instant and the second time instant is less than a time threshold.

3. The audio processing method of claim 2, wherein, the time difference between the first time instant and the second time instant is 0.

4. The audio processing method of claim 1, wherein, the second audio signal and / or the third audio signal and / or the fourth audio signal is a periodic or intermittent time-domain signal.

5. The audio processing method of claim 1, wherein, the lookup table comprises at least one first code field.

6. The audio processing method of claim 5, wherein, the lookup table further comprises at least one second code field, and a plurality of the first code fields constitute one second code field.

7. The audio processing method of claim 6, wherein, the second audio feature code comprises at least one first code field and / or at least one second code field.

8. The audio processing method of any one of claims 1-7, wherein, the obtaining the first audio signal comprises: collecting an initial audio signal; performing down-sampling processing on the initial audio signal to obtain the first audio signal.

9. The audio processing method of any one of claims 1-7, wherein, the obtaining the first audio signal comprises: collecting an initial audio signal; performing filtering processing on the initial audio signal to obtain the first audio signal.

10. The audio processing method of any one of claims 1-7, wherein, the phase of the second audio signal is opposite to the phase of the third audio signal.

11. An audio processing apparatus, comprising: an instruction generation module configured to generate a control instruction based on a first audio signal; an audio generation module configured to generate a second audio signal based on the control instruction; an output module configured to output the second audio signal to suppress a third audio signal. wherein a sum of a phase of the second audio signal and a phase of the third audio signal is less than a phase threshold, and the first audio signal occurs earlier than the third audio signal; wherein the instruction generation module comprises an audio acquisition submodule, a prediction submodule, and a generation submodule, the audio acquisition submodule is configured to acquire the first audio signal; the prediction submodule is configured to process the first audio signal to predict a fourth audio signal; the generation submodule is configured to generate the control instruction based on the fourth audio signal; wherein the prediction submodule comprises a query unit and a prediction unit, the query unit is configured to generate a first audio feature code based on the first audio signal, query a lookup table based on the first audio feature code to obtain a leading feature code field matching the first audio feature code, and determine a second audio feature code corresponding to the leading feature code field based on the leading feature code field, wherein the first audio feature code is used to indicate a change state of a waveform of the first audio signal; the prediction unit is configured to predict the fourth audio signal based on a part of the second audio feature code, wherein the part of the second audio feature code is a remaining field other than the first N feature code fields in the second audio feature code, and N is a positive integer.

12. The audio processing device of claim 11, wherein, the output module comprises a time point determination submodule and an output submodule, the time point determination submodule is configured to determine a first time point for outputting the second audio signal based on the control instruction; the output submodule is configured to output the second audio signal at the first time point, wherein the third audio signal starts to occur at a second time point, and an absolute value of a time difference between the first time point and the second time point is less than a time threshold.

13. The audio processing device of claim 12, wherein, The time difference between the first time point and the second time point is 0.

14. The audio processing device of claim 11, wherein, The second audio signal and / or the third audio signal and / or the fourth audio signal is a periodic or intermittent time domain signal.

15. The audio processing device of claim 11, wherein, The lookup table comprises at least one first code field.

16. The audio processing device of claim 15, wherein, The lookup table further comprises at least one second code field, and a plurality of the first code fields constitute one second code field.

17. The audio processing device of claim 16, wherein, The second audio feature code comprises at least one first code field and / or at least one second code field.

18. The audio processing device of any one of claims 11-17, wherein, The audio acquisition submodule comprises a collection unit and a down-sampling processing unit, the collection unit is configured to collect an initial audio signal; the down-sampling processing unit is configured to perform down-sampling processing on the initial audio signal to obtain the first audio signal.

19. The audio processing device of any one of claims 11-17, wherein, The audio acquisition submodule comprises a collection unit and a filtering unit, the collection unit is configured to collect an initial audio signal; the filtering unit is configured to perform filtering processing on the initial audio signal to obtain the first audio signal.

20. The audio processing device of any one of claims 11-17, wherein, The phase of the second audio signal is opposite to the phase of the third audio signal.

21. An audio processing apparatus, comprising: one or more memories non-transitorily storing computer-executable instructions; one or more processors configured to execute the computer-executable instructions, wherein the computer-executable instructions, when executed by the one or more processors, implement the audio processing method according to any one of claims 1-10.

22. A non-transitory computer-readable storage medium, wherein, The non-transitory computer-readable storage medium stores computer-executable instructions that, when executed by a processor, implement the audio processing method according to any one of claims 1-10.

Images