Text data transmission method and device, storage medium and electronic device

Abstract

The application discloses a text data transmission method and device, a storage medium and an electronic device. The method comprises the following steps: segmenting a to-be-analyzed audio signal according to a preset time length to obtain a group of audio signal segments; performing time-frequency domain conversion on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and determining a matching frequency of each audio signal segment according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence; based on a matching relationship between the matching frequency in the matching frequency sequence and a target frequency in a target frequency group and a corresponding relationship between the target frequency in the target frequency group and a preset character in a preset character group, the matching frequency sequence is analyzed into a preset character sequence, and the target frequency group is a preset frequency group matched with the to-be-analyzed audio signal in a plurality of preset frequency groups; and based on a corresponding relationship between a text unit and a preset character, the preset character sequence is analyzed into a target text.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home, in particular to a text data transmission method and device, a storage medium and an electronic device. BACKGROUND

[0002] Currently, when text transmission between devices is performed, a wireless network data connection between the devices is first established, and then text transmission is performed based on the established wireless network data connection. However, the connection process is limited by physical hardware chips and operating systems, and the success rate of connection establishment is low. Moreover, the connection process is relatively complex and professional, and requires users to have certain technical knowledge, which is not user-friendly.

[0003] To this end, text can be transmitted in the form of an audible voice audio waveform carrier. Since no connection needs to be established between two devices, the problems in the connection process can be avoided. At the same time, the transmission of text is completed by directly sending a certain waveform of a ciphertext carrier, which is more intuitive and secure and less likely to be intercepted.

[0004] However, the current audible voice audio waveform carrier has the disadvantages of weak anti-interference ability and poor spectrogram readability. The sending and receiving process of the audio is easily affected by noise, thereby resulting in a low audio recognition rate of the receiving device.

[0005] Therefore, the text data transmission method in the related art has the problem of low audio recognition rate due to weak anti-interference ability to noise. SUMMARY

[0006] Embodiments of the present application provide a text data transmission method and device, a storage medium and an electronic device to at least solve the problem of low audio recognition rate due to weak anti-interference ability to noise in the related art text data transmission method.

[0007] According to an aspect of the embodiments of the present application, a method for transmitting text data is provided, comprising: segmenting a to-be-analyzed audio signal according to a preset time length to obtain a group of to-be-analyzed audio signal segments, wherein the to-be-analyzed audio signal is obtained from an audio signal collected by an audio collection component; performing time-frequency domain transformation on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and determining a matching frequency of each audio signal segment according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of each audio signal segment is a frequency with the largest amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment; based on a matching relationship between the matching frequencies in the matching frequency sequence and target frequencies in a target frequency group and a corresponding relationship between the target frequencies in the target frequency group and preset characters in a preset character group, analyzing the matching frequency sequence into a preset character sequence, wherein the target frequency group is a preset frequency group in a plurality of preset frequency groups that matches the to-be-analyzed audio signal, different preset frequency groups in the plurality of preset frequency groups do not overlap in frequency segments, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups; and based on a corresponding relationship between a text unit and a preset character, analyzing the preset character sequence into a target text.

[0008] According to another aspect of the embodiments of the present application, a text data transmission apparatus is also provided, comprising: a segmenting unit configured to segment a to-be-analyzed audio signal according to a preset time length to obtain a group of to-be-analyzed audio signal segments, wherein the to-be-analyzed audio signal is obtained from an audio signal collected by an audio collecting component; an executing unit configured to perform time-frequency domain transformation on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to the each audio signal segment, and determine a matching frequency of the each audio signal segment according to the frequency spectrum data corresponding to the each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of the each audio signal segment is a frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to the each audio signal segment; a first analyzing unit configured to analyze the matching frequency sequence into a preset character sequence based on a matching relationship between the matching frequencies in the matching frequency sequence and target frequencies in a target frequency group and a corresponding relationship between the target frequencies in the target frequency group and preset characters in a preset character group, wherein the target frequency group is a preset frequency group in a plurality of preset frequency groups that matches the to-be-analyzed audio signal, different preset frequency groups in the plurality of preset frequency groups do not overlap in frequency range, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups; and a second analyzing unit configured to analyze the preset character sequence into a target text based on a corresponding relationship between a text unit and a preset character.

[0009] According to still another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which stores a computer program, wherein the computer program is configured to execute the text data transmission method when running.

[0010] According to still another aspect of the embodiments of the present application, an electronic device is also provided, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the text data transmission method through the computer program.

[0011] In the embodiment of the present application, the time-frequency domain conversion of the signal is performed in segments, and the target text is parsed by combining the preset characters corresponding to different frequencies with different texts. The audio signal to be parsed is obtained from the audio signal collected by the audio collection component. The audio signal to be parsed is segmented according to the preset time length to obtain a group of audio signal segments to be parsed. The time-frequency domain conversion is performed on each audio signal segment in the group of audio signal segments to obtain the frequency spectrum data corresponding to each audio signal segment. The matching frequency of each audio signal segment is determined according to the frequency spectrum data corresponding to each audio signal segment, and a matching frequency sequence is obtained. The matching frequency of each audio signal segment is the frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment. The matching frequency sequence is parsed into a preset character sequence based on the matching relationship between the matching frequencies in the matching frequency sequence and the target frequencies in the target frequency group and the corresponding relationship between the target frequencies in the target frequency group and the preset characters in the preset character group. The target frequency group is a preset frequency group in the plurality of preset frequency groups that matches the audio signal to be parsed. The frequency segments corresponding to different preset frequency groups in the plurality of preset frequency groups do not overlap. Different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups. The target text is parsed based on the corresponding relationship between the text unit and the preset character. Since the received audio signal is segmented and converted in the time-frequency domain, the frequency of the effective signal in the audio signal can be determined according to the matching relationship between the matching frequency of each audio signal segment and the target frequency in the target frequency group. Then, the text is parsed according to the preset character corresponding to the frequency. The frequency of the current environmental noise can be effectively avoided, the anti-interference ability to noise can be improved, the audio recognition rate can be improved, and the technical problem of low audio recognition rate caused by weak anti-interference ability to noise in the transmission method of text data in the related art can be solved. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate one embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0014] Figure 1is a hardware environment schematic diagram of a text data transmission method according to an embodiment of the application;

[0015] Figure 2 is a flow schematic diagram of an optional text data transmission method according to an embodiment of the application;

[0016] Figure 3 is a schematic diagram of an optional text data transmission method according to an embodiment of the application;

[0017] Figure 4 is a schematic diagram of another optional text data transmission method according to an embodiment of the application;

[0018] Figure 5 is a schematic diagram of yet another optional text data transmission method according to an embodiment of the application;

[0019] Figure 6 is a schematic diagram of yet another optional text data transmission method according to an embodiment of the application;

[0020] Figure 7 is a schematic diagram of yet another optional text data transmission method according to an embodiment of the application;

[0021] Figure 8 is a schematic diagram of yet another optional text data transmission method according to an embodiment of the application;

[0022] Figure 9 is a schematic diagram of yet another optional text data transmission method according to an embodiment of the application;

[0023] Figure 10 is a schematic diagram of yet another optional text data transmission method according to an embodiment of the application;

[0024] Figure 11 is a structural block diagram of an optional text data transmission device according to an embodiment of the application;

[0025] Figure 12 is a structural block diagram of an optional electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0026] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second" and the like in the description and in the claims of the present application and above-described accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the present application described herein can be carried out in other than the order shown or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that include a list of steps or units not necessarily limited to those clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products, or devices.

[0028] According to an aspect of the embodiments of the present application, a text data transmission method can be applied to a smart device. The text data transmission method is widely applied to smart home, smart home, smart home device ecology, intelligent house ecology, and whole-house intelligent digital control application scenarios. Optionally, in the present embodiment, the text data transmission method can be applied to the hardware environment composed of a terminal device 102 and a server 104 as shown in the figure. As shown in the figure, the server 104 is connected with the terminal device 102 through a network, which can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal, a database can be set on the server or independently of the server, which is used to provide data storage services for the server 104, cloud computing and / or edge computing services can be configured on the server or independently of the server, which is used to provide data operation services for the server 104. Figure 1 Figure 1 The network can include but is not limited to at least one of the following: wired network, wireless network. The wired network can include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network. The wireless network can include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 can not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart oven, smart refrigerator, smart oven, smart oven, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projection equipment, smart television, smart clothesline, smart curtain, smart audio and video, smart socket, smart sound, smart sound box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc. Voice equipment that can perform voice interaction.

[0029] The network can include but is not limited to at least one of the following: wired network, wireless network. The wired network can include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network. The wireless network can include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 can not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart oven, smart refrigerator, smart oven, smart oven, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projection equipment, smart television, smart clothesline, smart curtain, smart audio and video, smart socket, smart sound, smart sound box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc. Voice equipment that can perform voice interaction.​

[0030] The text data transmission method of the embodiments of the present application can be executed by the server 104, or by the terminal device 102, or by the server 104 and the terminal device 102 jointly. Wherein, the terminal device 102 executing the text data transmission method of the embodiments of the present application can also be executed by the client installed thereon.

[0031] Taking the text data transmission method in the embodiments executed by the terminal device 102 as an example, Figure 2 is a flowchart of an optional text data transmission method according to the embodiments of the present application, as Figure 2 shown, the flow of the method can include the following steps:

[0032] Step S202, segmenting the to-be-analyzed audio signal according to a preset time length to obtain a group of to-be-analyzed audio signal segments, wherein the to-be-analyzed audio signal is obtained from the audio signal collected by the audio collection component.

[0033] The text data transmission method in the embodiments can be applied to the scene of transmitting text information between two devices through an audio carrier. The audio carrier here can be an audible voice audio waveform carrier, different carrier frequencies can represent different text information, and the transmission of text information between two devices can be realized by playing audio through an audio sending end and receiving audio through a receiving end to obtain text information. The device here can be one or more of the terminal devices 102, which can be provided with a MIC (Microphone) and a Speaker (earpiece).

[0034] In related technologies, text transmission between devices mainly relies on wireless carrier technology. Wireless carrier technology is committed to establishing a virtual network connection in a certain frequency band, and often needs to establish a TCP (Transmission Control Protocol) / IP (Internet Protocol) network connection, a Bluetooth connection, a ZigBee (a low-speed short-range wireless network protocol) connection, and other wireless network data connections before text transmission. The connection process is limited by physical hardware chips and operating systems, in addition, the connection process is complex and professional, and users need to have certain technical knowledge, which is very unfriendly.

[0035] Taking WIFI connection as an example, in the WIFI camera two-dimensional code association process, the device button or other combination button needs to be pressed for a long time to open the WIFI hotspot, and then the WIFI hotspot is connected by scanning the two-dimensional code. There is a possibility of connection failure in the connection process. After connecting the WIFI hotspot, the WIFI SSID (Service Set Identifier) and password need to be input, and then the WIFI hotspot is closed, and the WIFI router is connected. In the above all processes, there is a certain failure probability, and the above all processes are relatively cumbersome, and the user is invisible and inaudible. In order to transmit data between unassociated devices, a complex connection process must be performed to send data.

[0036] In order to at least partially solve the above problems, the text information to be transmitted can be encrypted in ciphertext and transmitted in the form of an audible voice audio waveform carrier. The sending end directly sends a certain waveform ciphertext carrier by playing audio, and the receiving end decodes the received audio accordingly, thereby realizing the transmission of text information.

[0037] Since the audible voice audio waveform carrier does not need to establish any connection between two devices during the transmission of text information, the device directly sends a certain waveform ciphertext carrier to complete the transmission of text information. Compared with the above-mentioned method of transmitting text by establishing a wireless network data connection, the transmission of text information by audible voice audio waveform carrier is more visual, intuitive, and more secure and less likely to be intercepted.

[0038] In the embodiment, in order to improve the processing efficiency of the received audio signal, the to-be-analyzed audio signal can be segmented and processed according to a preset time length to obtain a group of to-be-analyzed audio signal segments. Here, the to-be-analyzed audio signal can be an audio signal obtained from the audio signal collected by the audio collection component.

[0039] Optionally, when the audio collection component collects the audio signal, 48000 sampling rate can be used to collect the audio data. In the process of sampling the audio signal, 1 / 2 sampling defined by Nyquist is generally used in the prior art, but it is found in actual use that 1 / 2 sampling rate will cause serious frequency burying phenomenon. In the embodiment, 1 / 4 data carrier period sampling can be selected, so that an audio signal with strong readability can be obtained. For example, when the audio signal uses 100m / s value for data carrier, the receiving end can use 25ms for data separation of the audio signal, so that a relatively ideal audio signal can be obtained. Correspondingly, each audio signal can contain 6 data sampling points.

[0040] Optionally, for the audio signal, the analog signal can be converted into a digital signal by sampling the analog signal and representing the signal with a digital code, as shown in Figure 3 The digital signal refers to a physical quantity with discrete values in time and amplitude, and a digital signal waveform represented by logic 1 and 0.

[0041] In step S204, time-frequency domain transformation is performed on each audio signal segment in the set of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and a matching frequency of each audio signal segment is determined according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence. The matching frequency of each audio signal segment is the frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment.

[0042] Since the audio speech data is time-varying, a set of waveform signals (i.e., time domain data) is formed by continuously sending a signal intensity level (i.e., audio amplitude) by the speaker. As shown in Figure 4 The time domain signal is generally disordered. In this embodiment, the audio time domain data can be converted into frequency corresponding data, i.e., the time domain signal is converted into a frequency domain signal. Since the audio signal is formed by superimposing a plurality of waveforms, as shown in Figure 5 The time domain signal data can be decomposed into different frequency domain data.

[0043] In this embodiment, time-frequency domain transformation can be performed on each audio signal segment in the set of audio signal segments to obtain frequency spectrum data (i.e., the aforementioned frequency domain data) corresponding to each audio signal segment, and a matching frequency of each audio signal segment is determined according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence. Here, the matching frequency of each audio signal segment can be the frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment.

[0044] Optionally, the time-frequency domain transformation can be a Fourier transform, such as a discrete Fourier transform, or other methods capable of realizing time-frequency domain transformation of the audio signal, which is not limited in the present embodiment.

[0045] In step S206, based on the matching relationship between the matching frequencies in the matching frequency sequence and the target frequencies in the target frequency group and the corresponding relationship between the target frequencies in the target frequency group and the preset characters in the preset character group, the matching frequency sequence is parsed into a preset character sequence, wherein the target frequency group is a preset frequency group in the plurality of preset frequency groups that matches the audio signal to be parsed, the different preset frequency groups in the plurality of preset frequency groups do not overlap between the corresponding frequency segments, and the different preset characters in the preset character group correspond to the different preset frequencies in each preset frequency group of the plurality of preset frequency groups.

[0046] The current audible speech audio waveform carrier has the disadvantages of weak anti-interference ability and poor spectrogram readability. The receiving end of text transmission will also collect noise in the environment while receiving audio. In the case of weak anti-interference ability of audio to noise, errors often occur in the parsing of text information, the audio parsing recognition rate is poor, and the accuracy of text transmission is low.

[0047] To at least partially solve the above problems, when generating an audio signal to be transmitted, the frequency of the audio signal can be selected from a plurality of preset frequency groups. Different preset frequency groups in the plurality of preset frequency groups can correspond to a preset character group, and different preset characters in the preset character group can correspond to different preset frequencies in each preset frequency group of the plurality of preset frequency groups. In other words, a preset frequency in a preset frequency group corresponds to a preset character in a preset character group. The frequency segments corresponding to different preset frequency groups can not overlap, and the frequency segment corresponding to a preset frequency group can be a frequency segment from the smallest preset frequency to the largest preset frequency in the preset frequency group. The preset character group can be a pre-set character group, for example, 0-15, and the preset character can be a text unit (e.g., a character, a word, etc.) constituting the text to be transmitted, or a character that has a mapping relationship with the text unit in the text to be transmitted. One text unit in the text to be transmitted can be mapped to one or more preset characters. For example, the preset characters in the preset character group can be characters in ASCII (American Standard Code for Information Interchange), and one character in ASCII can be a value of 0-15, and two characters can represent one text unit. By using the preset characters in the preset character group to represent text information, the text information can be encrypted.

[0048] Optionally, to avoid the interference of environmental noise on audio data, when selecting the frequency of the audio signal to be transmitted, a frequency that has no intersection with the frequency of the environmental noise can be selected as the frequency of the audio signal to be transmitted.

[0049] In the embodiment, when determining the preset character corresponding to the received audio signal, the matching frequency sequence can be parsed into a preset character sequence based on the matching relationship between the matching frequency in the matching frequency sequence and the target frequency in the target frequency group and the corresponding relationship between the target frequency in the target frequency group and the preset character in the preset character group.

[0050] In step S208, the preset character sequence is parsed into the target text based on the corresponding relationship between the text unit and the preset character.

[0051] In the embodiment, the preset character sequence can be parsed into the target text based on the corresponding relationship between the text unit and the preset character. Here, the corresponding relationship between the text unit and the preset character can be pre-set and agreed by the sending end and the receiving end of the text transmission.

[0052] Through the above steps S202 to S208, the audio signal to be parsed is segmented according to the preset time length to obtain a group of audio signal segments to be parsed, wherein the audio signal to be parsed is obtained from the audio signal collected by the audio collection component; the time-frequency domain transformation is performed on each audio signal segment in the group of audio signal segments to obtain the frequency spectrum data corresponding to each audio signal segment, and the matching frequency of each audio signal segment is determined according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of each audio signal segment is the frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment; the matching frequency sequence is parsed into a preset character sequence based on the matching relationship between the matching frequency in the matching frequency sequence and the target frequency in the target frequency group and the corresponding relationship between the target frequency in the target frequency group and the preset character in the preset character group, wherein the target frequency group is a preset frequency group in a plurality of preset frequency groups that matches the audio signal to be parsed, the frequency segments corresponding to different preset frequency groups in the plurality of preset frequency groups do not overlap, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups; the preset character sequence is parsed into the target text based on the corresponding relationship between the text unit and the preset character, which solves the technical problem of low audio recognition rate caused by weak anti-interference ability to noise in the related art text data transmission method, and improves the audio recognition rate.

[0053] In one example embodiment, before the audio signal to be parsed is segmented according to the preset time length to obtain a group of audio signal segments to be parsed, the method further comprises:

[0054] S11, in a case where a starting section audio signal is identified in the audio signal collected from the audio collection component, determining, as the audio signal to be analyzed, an audio signal located after the starting section audio signal in the audio signal collected from the audio collection component, wherein the starting section audio signal is used to indicate that the audio signal after the starting section audio signal is a valid audio signal.

[0055] In order to avoid the situation that the audio receiving end cannot receive and identify the audio signal in time, resulting in missing audio signals, the signal played by the audio sending end can include a starting section audio and an audio signal corresponding to each character to be transmitted.

[0056] The above-mentioned starting section audio can be a specific frequency signal, that is, a signal pulse with a fixed frequency for a certain period of time, which can be used to indicate that the audio signal after the starting section audio is a valid audio signal (i.e., an audio signal that needs to be analyzed). Before playing the audio signal corresponding to each character to be transmitted in sequence by the audio playing component, the starting section audio with a preset time length can be played at a starting frequency. The preset time length here can be a pre-set time length, such as 1000ms.

[0057] In the embodiment, in a case where a starting section audio signal is identified in the audio signal collected from the audio collection component, an audio signal located after the starting section audio signal in the audio signal collected from the audio collection component can be determined as the audio signal to be analyzed.

[0058] Through the embodiment, by taking the audio signal after the starting section audio as the audio signal to be analyzed, the sensitivity of the receiving end to the valid audio signal can be improved, and the situation that the audio signal is not completely received can be avoided.

[0059] In one example embodiment, before the audio signal to be analyzed is segmented according to the preset time length to obtain a group of audio signal segments to be analyzed, the method further comprises:

[0060] S21, performing noise reduction processing on the audio signal to be analyzed to obtain the audio signal to be analyzed after noise reduction, wherein the noise reduction processing comprises at least one of the following: noise attenuation processing, band-pass filtering processing.

[0061] In order to improve the signal-to-noise ratio of the audio signal to be analyzed and reduce the interference of noise in the audio signal on the signal, in the embodiment, noise reduction processing can be performed on the audio signal to be analyzed to obtain the audio signal to be analyzed after noise reduction. Here. The noise reduction processing includes at least one of the following: noise attenuation processing, band-pass filtering processing.

[0062] Optionally, the noise attenuation processing described above can be an attenuation calculation processing on the audio signal to be analyzed according to a preset signal attenuation formula. The band-pass filtering processing described above can be an operation process of attenuating frequency components in a certain frequency range to a very low level, but attenuating frequency components in other ranges.

[0063] Through the embodiment, by performing the noise reduction processing on the audio signal to be analyzed, the signal-to-noise ratio of the audio signal can be improved.

[0064] In an example embodiment, the noise reduction processing on the audio signal to be analyzed to obtain the audio signal to be analyzed after noise reduction includes:

[0065] S31, determining the target frequency group from the plurality of preset frequency groups according to the center of gravity frequency of the audio signal to be analyzed and the root mean square frequency of the audio signal to be analyzed, wherein the target frequency group is a preset frequency group in the plurality of preset frequency groups, and a corresponding frequency range of the preset frequency group matches the center of gravity frequency and the root mean square frequency;

[0066] S32, performing filter parameter configuration on a preset band-pass filter according to the target frequency in the target frequency group to obtain a target band-pass filter;

[0067] S33, performing band-pass filtering processing on the spectrum data of the audio signal to be analyzed using the target band-pass filter to obtain the audio signal to be analyzed after filtering.

[0068] Considering that the center of gravity frequency can describe the frequency of the signal component with larger components in the spectrum, and reflect the distribution of the signal power spectrum, and the root mean square frequency is the arithmetic square root of the mean square frequency, the arithmetic square root of the weighted average of the square of the signal frequency, and also takes the amplitude of the power spectrum as the weight, in the embodiment, when performing the noise reduction processing on the audio signal to be analyzed, the target frequency group can be determined from the plurality of preset frequency groups according to the center of gravity frequency of the audio signal to be analyzed and the root mean square frequency of the audio signal to be analyzed. Here, the target frequency group can be a preset frequency group in the plurality of preset frequency groups, and a corresponding frequency range of the preset frequency group matches the center of gravity frequency and the root mean square frequency.

[0069] Optionally, after the center of gravity frequency and the root mean square frequency are calculated, the aforementioned noise attenuation processing can be performed, and the corresponding signal attenuation formula can be:

[0070] dBm = 20lg(E / Er)-10lg(R / Rr) (1)

[0071] Where dBm (decibel relative to one milliwatt) is a pure counting unit, which is an absolute value representing power; E is the actual measured voltage value; Er is the reference voltage value; R is the actual measured resistance; and Rr is the reference resistance.

[0072] For example, the audio spectrogram of a signal without signal attenuation processing can be as follows: Figure 6 As shown, the audio spectrogram of the signal after signal attenuation processing can be obtained as follows: Figure 7 As shown, the signal-to-noise ratio of the spectrogram after attenuation processing can be significantly increased.

[0073] Furthermore, for a given target frequency, the filter parameters of a preset bandpass filter can be configured according to the target frequencies in the target frequency group to obtain a target bandpass filter. Here, the target bandpass filter can be an FIR (Finite Impulse Response) digital filter, such as a multinomial decimation filter.

[0074] For FIR digital filters, the system function of an FIR digital filter has no denominator and is... The system frequency response can be rewritten as: Let H(e) jω )=H(ω)e jψ H(ω) is a function of amplitude, and ψ(ω) is a function of phase. This differs from the representation of magnitude and argument. For the sake of consistency and convenience, H(ω) is a real number that can be positive or negative. For example, if the frequency response of a system is sin4ω, and the representation of magnitude and argument is used, the sign change of sin4ω is equivalent to adding a phase offset, thus causing discontinuity in the phase curve and inconvenience in expression.

[0075] The basic principle of the aforementioned multi-phase decimation filter can be that a set of N prototype filter coefficients is mapped to M multiphase sub-filters. For example... Figure 8 The diagram shows the polyphase decimation filter option, which implements a computationally efficient M-to-1 polyphase decimation filter. Starting from the Mth sub-filter, each sub-filter takes an output sample x(n) as input. After the first input, a cycle is completed, meaning that M samples are fed into each of the M polyphase sub-filters, and the output is the sum of the outputs of the M polyphase sub-filters. The output sampling rate is 1 / M of the input data stream sampling rate. Because the output samples are fed into each polyphase sub-filter in turn, the polyphase filter operates at a lower frequency (relative to a higher input sampling rate), with N operations at each output point.

[0076] The target band-pass filter is used to perform band-pass filtering on the spectrum data of the audio signal to be parsed, so that the audio signal to be parsed after filtering is obtained.

[0077] By the noise reduction and filtering, the noise signal is processed, the signal-to-noise ratio of the audio signal is improved, and the parsing accuracy of the audio signal is improved.

[0078] In one example embodiment, the audio signal to be parsed has interval audio signals corresponding to target interval frequencies between adjacent preset characters.

[0079] The matching frequency sequence is parsed into a preset character sequence based on a matching relationship between the matching frequencies in the matching frequency sequence and the target frequencies in the target frequency group and a corresponding relationship between the target frequencies in the target frequency group and the preset characters in the preset character group, and the method comprises the following steps.

[0080] S41, in the case where the target interval frequency is less than the frequency range corresponding to the target frequency group, the step of sequentially determining the step frequencies in the matching frequency sequence to obtain a step frequency sequence, wherein the step frequency is a matching frequency in the matching frequency sequence that is greater than a previous matching frequency and has a frequency difference greater than or equal to a first frequency difference threshold with the previous matching frequency; and the step of parsing each step frequency in the step frequency sequence into a preset character corresponding to a target frequency matching the each step frequency to obtain the preset character sequence, wherein the target frequency matching the each step frequency is a target frequency in the target frequency group that has the smallest frequency difference with the each step frequency.

[0081] S42, in the case where the target interval frequency is greater than the frequency range corresponding to the target frequency group, the step of sequentially determining the step-down frequencies in the matching frequency sequence to obtain a step-down frequency sequence, wherein the step-down frequency is a matching frequency in the matching frequency sequence that is less than a previous matching frequency and has a frequency difference greater than or equal to a second frequency difference threshold with the previous matching frequency; and the step of parsing each step-down frequency in the step-down frequency sequence into a preset character corresponding to a target frequency matching the each step-down frequency to obtain the preset character sequence, wherein the target frequency matching the each step-down frequency is a target frequency in the target frequency group that has the smallest frequency difference with the each step-down frequency.

[0082] In view of the continuous audio data carrier, the recognition processing capability for signal distortion and noise surge is very limited. Before playing the audio signal, the high frequency interval or low frequency interval mode can be used to play the high frequency or low frequency interval of the audio signal corresponding to each to-be-transmitted character according to the noise frequency of the current environmental noise.

[0083] In the embodiment, the interval audio signal corresponding to the target interval frequency can be arranged between the audio signals corresponding to the adjacent preset characters in the audio signal to be analyzed. The target interval frequency and the frequency segment corresponding to the target frequency group can not intersect.

[0084] Optionally, the target interval frequency can be positively correlated with the noise frequency of the current environmental noise, and the interval frequency with the smallest frequency difference from the noise frequency of the current environmental noise can be selected from a group of interval frequencies according to the noise frequency of the current environmental noise, for example, the corresponding high frequency or low frequency is selected according to the high or low of the noise frequency of the current environmental noise, and the noise recognition rate is improved by fixed time domain data interval. The playing time of the interval audio data according to the target interval frequency can be a pre-set fixed interval time.

[0085] In the embodiment, when the matching frequency sequence is analyzed into the preset character sequence, in the case that the target interval frequency is less than the frequency segment corresponding to the target frequency group, the step frequency in the matching frequency sequence can be determined in sequence to obtain a step frequency sequence. And each step frequency in the step frequency sequence is analyzed into a preset character corresponding to a target frequency matched with the step frequency to obtain the preset character sequence. Here, the step frequency can be a matching frequency in the matching frequency sequence, which is greater than the previous matching frequency, and the frequency difference between the step frequency and the previous matching frequency is greater than or equal to the first frequency difference threshold. The target frequency matched with each step frequency can be the target frequency in the target frequency group with the smallest frequency difference from the step frequency.

[0086] For example, it is determined that the received frequency sequence is a group of frequency spectrum data as follows:

[0087] 432, 312, 322, 8000, 8000, 8022, 222, 100, 230, 9012, 9012, 9012, 9000, 212, 212, 213, 8400, 8400, 8407, 200, 300, 100, 330

[0088] Wherein, the interval frequency is less than the frequency range corresponding to the target frequency group, and the analysis of the frequency spectrum diagram can be the same as the high and low level digital carrier mode of the digital circuit, in which the rising edge is the effective digital carrier and the falling edge is the anti-interference digital interval. Taking 8000, 9000, and 8400 as the effective digital carriers as an example, according to the preset ASCII code, 8000, 9000, and 8400 correspond to "a", "e", and "k" respectively, and the carrier data is aek.

[0089] In addition, in the case where the target interval frequency is greater than the frequency range corresponding to the target frequency group, the order-reduced frequencies in the matching frequency sequence can be determined in sequence to obtain an order-reduced frequency sequence, and each order-reduced frequency in the order-reduced frequency sequence can be analyzed to obtain a preset character corresponding to a target frequency matching the order-reduced frequency, thereby obtaining the preset character sequence. Here, the order-reduced frequency can be a matching frequency in the matching frequency sequence, which is less than a previous matching frequency and has a frequency difference with the previous matching frequency greater than or equal to a second frequency difference threshold. The target frequency matching each order-reduced frequency can be a target frequency in the target frequency group, which has the smallest frequency difference with the order-reduced frequency.

[0090] For example, it is determined that the received frequency sequence is a group of frequency spectrum data as follows:

[0091] 13500, 13500, 13485, 8000, 8000, 8022, 13485, 13512, 13512, 9012, 9012, 9012, 9000, 13500, 13500, 13500, 8400, 8400, 8407, 13523, 13500, 13500, 13530

[0092] Wherein, the interval frequency is greater than the frequency range corresponding to the target frequency group, and the analysis of the frequency spectrum diagram can be the same as the high and low level digital carrier mode of the digital circuit, in which the rising edge is the anti-interference digital interval and the falling edge is the effective digital carrier. Taking 8000, 9000, and 8400 as the effective digital carriers as an example, according to the preset ASCII code, 8000, 9000, and 8400 correspond to "a", "e", and "k" respectively, and the carrier data is aek.

[0093] According to the size relationship between the interval frequency and the target frequency, the effective frequency in the audio signal is determined, and the text information corresponding to the effective frequency is determined, thereby improving the readability of the audio signal carrier.

[0094] In one exemplary embodiment, the time-frequency domain transformation of each audio signal segment in the group of audio signal segments to obtain the frequency spectrum data corresponding to each audio signal segment comprises:

[0095] S51, performing the following transformation operation on the each audio signal segment as a current audio signal to obtain the spectral data corresponding to the each audio signal segment:

[0096] sampling the current audio signal according to a preset sampling frequency to obtain N sampling points corresponding to the current audio signal, wherein the N is a positive integer greater than or equal to 2;

[0097] generating a cosine basis signal corresponding to each sampling point in the N sampling points based on the each sampling point to obtain N cosine basis signals, and sequentially calculating the similarity between the current audio signal and the N cosine basis signals to obtain N cosine similarity values;

[0098] generating a sine basis signal corresponding to each sampling point in the N sampling points based on the each sampling point to obtain N sine basis signals, and sequentially calculating the similarity between the current audio signal and the N sine basis signals to obtain N sine similarity values;

[0099] performing discrete Fourier transform on the current audio signal based on the N cosine similarity values and the N sine similarity values to obtain the spectral data corresponding to the current audio signal.

[0100] When performing time-frequency domain transformation on each audio signal segment in the group of audio signal segments, it can be completed by respectively determining the frequency information and the phase information of each audio signal segment. The frequency information can be determined by calculating the similarity between the audio signal segment and its cosine basis signal, and the phase information can be determined by calculating the similarity between the audio signal segment and its sine basis signal.

[0101] In this embodiment, the following transformation operation can be performed on the each audio signal segment as a current audio signal:

[0102] sampling the current audio signal according to a preset sampling frequency to obtain N sampling points corresponding to the current audio signal. Based on each sampling point in the N sampling points, a cosine basis signal corresponding to the each sampling point can be generated to obtain N cosine basis signals. Sequentially calculating the similarity between the current audio signal and the N cosine basis signals can obtain N cosine similarity values. Here, N can be a positive integer greater than or equal to 2.

[0103] Based on each sampling point in the N sampling points, a sine basis signal corresponding to the each sampling point can be generated to obtain N sine basis signals. Sequentially calculating the similarity between the current audio signal and the N sine basis signals can obtain N sine similarity values.

[0104] Since the determined N cosine similarity values and N sine similarity values, the frequency and phase information of the current audio signal can be determined. Based on the N cosine similarity values and the N sine similarity values, the discrete Fourier transform of the current audio signal can be obtained, and the frequency spectrum data corresponding to the current audio signal can be obtained.

[0105] For example, taking a preset sampling frequency F=48000 as an example, the sampling points are N, in order to obtain the frequency information of the original signal, N groups of cosine basis signals are needed, which are 0~N-1 periods of vibration in N sampling points. Then calculate the similarity of the original signal and the N cosine basis signals in turn N groups of C cos The array X cos exists, then

[0106]

[0107] Wherein, x is the original signal, is the basis signal of 0 periods of vibration in N sampling points, is the basis signal of N-1 periods of vibration in N sampling points.

[0108] For example, taking a preset sampling frequency F=48000 as an example, the sampling points are N, in order to obtain the phase information of the original signal, N groups of sine basis signals are needed, which are 0~N-1 periods of vibration in N sampling points, then calculate the similarity of the original signal and the N sine basis signals in turn sin N groups of C sin The array X sin exists, then

[0109]

[0110] Correspondingly, the DFT formula is

[0111]

[0112] Therefore, the component amplitude is The phase is The frequency is iF / N.

[0113] In summary, according to the frequency of the audio data of Haier is 48000Hz, the frequency of 23Hz is used to divide the audio data into packets with a length of 1 / 4 carrier cycle, that is, 20ms, and the frequency spectrum data obtained by performing Fourier transform on each segment of data can be as shown in the following table: Figure 9 The maximum amplitude frequency data obtained by segmenting and deriving is the carrier data, and the final obtained data is as follows:

[0114] [[8.2183762e+01+0.0000000e+00j, 1.4908797e+02+0.0000000e+00j, 1.6384016e+02+0.0000000e+00j,..., 1.6383990e+02+0.0000000e+00j, 1.6356868e+02+0.0000000e+00j, 1.3654887e+02+0.0000000e+00j],

[0115] [-4.1223682e+01+5.2152092e+01j, -8.7516121e+01+1.2906033e+01j, -8.1920006e+01+7.8829187e-05j,..., -8.1919937e+01-1.8807315e-05j, -8.2178398e+01-7.9389378e-02j, -8.4950920e+01-2.5094332e+01j],

[0116] [2.6348916e-01-3.4768208e+01j, 8.5602512e+00+8.6922989e+00j, -1.8893274e-05-1.4590098e-04j,..., -7.5825425e-05+2.9275074e-05j, -2.2173138e-01-1.5039884e-01j, 1.9730429e+01-3.7702971e+00j],

[0117] ...,

[0118] [5.8779787e-02-1.7322031e-04j, -2.9229000e-02+1.8904553e-05j,

[0119] -4.9659222e-05-9.5613796e-06j,...,

[0120] 2.1927297e-04-2.1001688e-05j, -1.9529454e-03+1.7574687e-03j,

[0121] 2.8996611e-02-2.9261442e-02j],

[0122] [-5.8906291e-02+3.3094955e-05j, -7.0455855e-05+2.9488415e-02j,

[0123] 1.5496729e-04+1.7768919e-04j,...,

[0124] -9.1423726e-06+8.9934176e-05j, -1.8922212e-03+7.8019936e-04j,

[0125] 1.5654806e-02+3.7746921e-02j],

[0126] [5.8963832e-02+0.0000000e+00j, 2.9438598e-02+0.0000000e+00j,

[0127] -2.3485458e-04+0.0000000e+00j,...,

[0128] -1.6169799e-04+0.0000000e+00j, -2.4339526e-03+0.0000000e+00j,

[0129] -4.0957816e-02+0.0000000e+00j]].

[0130] In addition, in the discrete Fourier transform algorithm, the Fourier transform pair of the analog signal xn(t) is X(jΩ) = {-∞,+∞} x(t) * exp^-jΩt dt and X(t) = 1 / 2π {-∞,+∞} X(JΩ) * e^jΩt dΩ, and the method for calculating the pair of transforms by using the DFT method is as follows:

[0131] xn(t) is sampled at intervals of T, that is, xn(t) | t = nT = xa(nT) = x(n), since t→nT, dt→T, {-∞,+∞}→∑n = {-∞,+∞}, therefore X(jΩ) ≈ ∑n = {-∞,+∞} x(nT) * exp^-jΩnT * T, x(nT) ≈ 1 / 2π {0,Ωs} X(JΩ) * e^jΩnT dω;

[0132] The sequence x(n) = xn(t) is truncated into a finite-length sequence containing N sampling points, X(jΩ) ≈ T∑n={0,N-1}x(nT)*exp^-jΩnT*T, due to time-domain sampling, the sampling frequency is fs=1 / T, then the frequency domain generates a periodic extension with a period of fs, if the frequency domain is a band-limited signal, it is possible to not generate spectral aliasing, and become a continuous periodic spectrum sequence, and the period of the spectrum is fs=1 / T.

[0133] For numerical calculation, sampling is also required in the frequency domain, that is, N sampling points are taken in one period of the frequency domain, fs=NF0, and each sampling point is separated by F0. Frequency domain sampling changes the integral form of the frequency domain into a summation form, and the periodic extension of the originally truncated discrete-time sequence is obtained in the time domain, and the time period is T0=1 / F0=N / fs=NT, Ω0=2ΠF0, Ω0T=Ω0 / fs=2π / N, X(jkΩ0) ≈ T∑n={0,N-1}x(nT)*exp^-jkΩ0nT.

[0134] Through this embodiment, by respectively determining the cosine similarity value and the sine similarity value of the audio signal, the audio signal can be converted from time domain data to frequency domain data through Fourier transform of the audio signal, and the readability of the audio signal can be improved.

[0135] In one exemplary embodiment, after the matching frequency sequence is obtained by determining the matching frequency of each audio signal segment according to the frequency spectrum data corresponding to each audio signal segment, the method further comprises:

[0136] S61, window processing is performed on the matching frequency sequence using a preset window function to obtain an updated matching frequency sequence, wherein the preset window function is a window function with a time length that is an integer multiple of a preset signal time length of an audio signal corresponding to a preset character and a pulse width that is the preset signal time length.

[0137] Considering that noise bursts often occur in environments with high noise frequencies, in order to avoid errors in the analysis of the audio signal due to the presence of burst noise, in this embodiment, after the matching frequency sequence is obtained by determining the matching frequency of each audio signal segment according to the frequency spectrum data corresponding to each audio signal segment, the matching frequency sequence can be windowed using a preset window function to obtain an updated matching frequency sequence. Here, the preset window function can be a window function with a time length that is an integer multiple of a preset signal time length of an audio signal corresponding to a preset character and a pulse width that is the preset signal time length.

[0138] The window function method, also known as the Fourier series method, is designed in the time domain. The function is generally infinite and non-causal. Using a suitable window function to cut the data into a finite causal sequence can make the corresponding frequency response (Fourier transform) as close as possible to the ideal frequency response.

[0139] For example, in the case of 100ms per value of audio carrier data, according to the time interval of the aforementioned frequency, and the comprehensive consideration of the amplitude-frequency characteristics, sampling frequency or other hardware parameters of the transmitting and receiving end devices, a square wave with a periodic window position of 300ms can be selected as shown in the following table. Figure 10 For example, in the case of 100ms per value of audio carrier data, according to the time interval of the aforementioned frequency, and the comprehensive consideration of the amplitude-frequency characteristics, sampling frequency or other hardware parameters of the transmitting and receiving end devices, a square wave with a periodic window position of 300ms can be selected as shown in the following table.

[0140] Through this embodiment, by performing windowing processing on the frequency sequence, the waveform data can be corrected after fitting the waveform data, thereby improving the recognition rate of the audio signal.

[0141] The text data transmission method in the embodiments of the present application will be explained and described below in combination with optional examples. In this optional example, the audio signal to be analyzed is audio carrier data.

[0142] The sound ciphertext carrier noise reduction and ciphertext decoding method provided in this optional example converts the received audio signal segments into time-frequency domain, reduces noise through filtering, and determines the text information in the audio data by combining the high-frequency interval method, the low-frequency interval method, and the window function method. This method improves the readability of the audio data while increasing the anti-interference ability of the audio data.

[0143] The flow of the text data transmission method in this optional example can include the following steps:

[0144] Step 1, after calculating the derivative center frequency and root mean square frequency of the audio carrier data, the signal attenuation formula is used to complete the attenuation calculation of the audio carrier data.

[0145] Step 2, band-pass filtering is completed by using a FIR decimator filter, and audio carrier data with relatively small noise is obtained.

[0146] Step 3, audio data segments are converted into frequency domain data by Fourier transform.

[0147] Step 4, data segments are intercepted according to high-order and low-order interval characteristics.

[0148] Since the audio signal is high-frequency or low-frequency interval according to the high or low of the noise frequency of the current environment noise, at the receiving end, the effective frequency can be determined according to the corresponding interval frequency.

[0149] Step 5, the frequency sequence is windowed and the square wave data is corrected.

[0150] Step 6, the corresponding character is determined according to the frequency, and the transmitted text information is determined.

[0151] Through the optional example, the two devices do not need to establish a connection in advance, and the ciphertext can be sent only by MIC and Speaker. Meanwhile, the frequency arbitration interval is adopted, which not only increases the readability of the complex audio carrier, but also increases the anti-interference ability of the audio carrier.

[0152] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0153] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and a necessary general hardware platform, and of course it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM (Read-Only Memory) / RAM (Random Access Memory), a magnetic disk, an optical disk), and includes a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method of each embodiment of the present application.

[0154] According to another aspect of the embodiments of the present application, there is also provided a text data transmission device for implementing the text data transmission method described above, which can be applied to a smart device. Figure 11 is a structural block diagram of an optional text data transmission device according to the embodiments of the present application, as shown in Figure 11 The device can include:

[0155] The segmentation unit 1102 is configured to segment a to-be-analyzed audio signal according to a preset time length, to obtain a group of to-be-analyzed audio signal segments, wherein the to-be-analyzed audio signal is an audio signal to be analyzed, which is acquired from an audio acquisition component.

[0156] The execution unit 1104, connected to the segmentation unit 1102, is configured to perform time-frequency domain transformation on each audio signal segment in the group of audio signal segments, to obtain frequency spectrum data corresponding to the each audio signal segment, and determine a matching frequency of the each audio signal segment according to the frequency spectrum data corresponding to the each audio signal segment, to obtain a matching frequency sequence, wherein the matching frequency of the each audio signal segment is a frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to the each audio signal segment.

[0157] The first analysis unit 1106, connected to the execution unit 1104, is configured to analyze the matching frequency sequence into a preset character sequence based on a matching relationship between the matching frequencies in the matching frequency sequence and target frequencies in a target frequency group, and a corresponding relationship between the target frequencies in the target frequency group and preset characters in a preset character group, wherein the target frequency group is a preset frequency group in a plurality of preset frequency groups that matches the to-be-analyzed audio signal, different preset frequency groups in the plurality of preset frequency groups do not overlap between frequency segments corresponding to the different preset frequency groups, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups.

[0158] The second analysis unit 1108, connected to the first analysis unit 1106, is configured to analyze the preset character sequence into a target text based on a corresponding relationship between a text unit and a preset character.

[0159] It should be noted that the segmentation unit 1102 in this embodiment can be configured to perform the step S202 described above, the execution unit 1104 in this embodiment can be configured to perform the step S204 described above, the first analysis unit 1106 in this embodiment can be configured to perform the step S206 described above, and the second analysis unit 1108 in this embodiment can be configured to perform the step S208 described above.

[0160] The above module segments the audio signal to be analyzed according to a preset time length to obtain a group of audio signal segments to be analyzed, wherein the audio signal to be analyzed is obtained from audio signals collected by an audio collection component; a time-frequency domain transformation is performed on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and a matching frequency of each audio signal segment is determined according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of each audio signal segment is a frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment; the matching frequency sequence is analyzed into a preset character sequence based on a matching relationship between the matching frequencies in the matching frequency sequence and target frequencies in a target frequency group and a corresponding relationship between the target frequencies in the target frequency group and preset characters in a preset character group, wherein the target frequency group is a preset frequency group matching the audio signal to be analyzed in a plurality of preset frequency groups, different preset frequency groups in the plurality of preset frequency groups do not overlap in frequency range, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups; and the preset character sequence is analyzed into target text based on a corresponding relationship between a text unit and a preset character, thereby solving the problem of low audio recognition rate caused by weak anti-interference ability to noise in the related art transmission method of text data, and improving the audio recognition rate.

[0161] In one example embodiment, the apparatus further includes:

[0162] The determining unit is configured to, before the segmenting the audio signal to be analyzed according to the preset time length to obtain the group of audio signal segments to be analyzed, in a case where a starting segment audio signal is identified from the audio signals collected by the audio collection component, determine, as the audio signal to be analyzed, an audio signal located after the starting segment audio signal in the audio signals collected by the audio collection component, wherein the starting segment audio signal is used to indicate that the audio signal after the starting segment audio signal is a valid audio signal.

[0163] In one example embodiment, the apparatus further includes:

[0164] The noise reduction unit is configured to, before the segmenting the audio signal to be analyzed according to the preset time length to obtain the group of audio signal segments to be analyzed, perform noise reduction processing on the audio signal to be analyzed to obtain the audio signal to be analyzed after noise reduction, wherein the noise reduction processing includes at least one of noise attenuation processing and band-pass filtering processing.

[0165] In one example embodiment, the noise reduction unit includes:

[0166] determining a target frequency group from the plurality of preset frequency groups according to a center frequency of the audio signal to be parsed and a root mean square frequency of the audio signal to be parsed, wherein the target frequency group is a preset frequency group in the plurality of preset frequency groups, and a corresponding frequency range of the preset frequency group matches the center frequency and the root mean square frequency;

[0167] configuring a preset band-pass filter according to a target frequency in the target frequency group to obtain a target band-pass filter;

[0168] filtering the spectrum data of the audio signal to be parsed using the target band-pass filter to obtain a filtered audio signal to be parsed.

[0169] In an example embodiment, the audio signal to be parsed and the audio signal corresponding to an adjacent preset character are separated by an interval audio signal corresponding to a target interval frequency, and the target interval frequency and a frequency range corresponding to the target frequency group are disjoint; and the first parsing unit comprises:

[0170] a first execution module configured to, in a case where the target interval frequency is less than the frequency range corresponding to the target frequency group, sequentially determine step frequencies in the sequence of matching frequencies to obtain a sequence of step frequencies, wherein the step frequency is a matching frequency in the sequence of matching frequencies, which is greater than a previous matching frequency and has a frequency difference with the previous matching frequency greater than or equal to a first frequency difference threshold; and parse each step frequency in the sequence of step frequencies into a preset character corresponding to a target frequency matching the step frequency to obtain the sequence of preset characters, wherein the target frequency matching the step frequency is a target frequency in the target frequency group, which has a minimum frequency difference with the step frequency;

[0171] a second execution module configured to, in a case where the target interval frequency is greater than the frequency range corresponding to the target frequency group, sequentially determine step-down frequencies in the sequence of matching frequencies to obtain a sequence of step-down frequencies, wherein the step-down frequency is a matching frequency in the sequence of matching frequencies, which is less than a previous matching frequency and has a frequency difference with the previous matching frequency greater than or equal to a second frequency difference threshold; and parse each step-down frequency in the sequence of step-down frequencies into a preset character corresponding to a target frequency matching the step-down frequency to obtain the sequence of preset characters, wherein the target frequency matching the step-down frequency is a target frequency in the target frequency group, which has a minimum frequency difference with the step-down frequency.

[0172] In an example embodiment, the execution unit comprises:

[0173] a third executing module, configured to perform the following transform operation on the each audio signal segment as a current audio signal to obtain the spectrum data corresponding to the each audio signal segment:

[0174] sample the current audio signal according to a preset sampling frequency to obtain N sampling points corresponding to the current audio signal, wherein the N is a positive integer greater than or equal to 2;

[0175] generate a cosine basis signal corresponding to each sampling point in the N sampling points based on the each sampling point to obtain N cosine basis signals, and sequentially calculate the similarity between the current audio signal and the N cosine basis signals to obtain N cosine similarity values;

[0176] generate a sine basis signal corresponding to each sampling point in the N sampling points based on the each sampling point to obtain N sine basis signals, and sequentially calculate the similarity between the current audio signal and the N sine basis signals to obtain N sine similarity values;

[0177] perform a discrete Fourier transform on the current audio signal based on the N cosine similarity values and the N sine similarity values to obtain the spectrum data corresponding to the current audio signal.

[0178] In an example embodiment, the apparatus further comprises:

[0179] a windowing unit, configured to, after determining the matching frequency sequence of the each audio signal segment according to the spectrum data corresponding to the each audio signal segment, perform windowing processing on the matching frequency sequence using a preset window function to obtain an updated matching frequency sequence, wherein the preset window function is a window function with a time length being an integer multiple of a preset signal time length of an audio signal corresponding to one preset character and a pulse width being the preset signal time length.

[0180] It should be noted that the above modules and the examples and application scenarios realized by the corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules as part of the apparatus can run in the hardware environment as shown in Figure 1 , which can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0181] According to another aspect of the embodiments of the present application, a storage medium is provided, which can be located on a smart device. Optionally, in the present embodiment, the above-mentioned storage medium can be used to execute the program code of any one of the above-mentioned text data transmission methods in the embodiments of the present application.

[0182] Optionally, in the embodiment, the storage medium can be located on at least one of the network devices in the network shown in the above embodiment.

[0183] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps:

[0184] S1, segmenting a to-be-resolved audio signal according to a preset time length to obtain a group of to-be-resolved audio signal segments, wherein the to-be-resolved audio signal is an audio signal to be resolved, which is obtained from an audio acquisition component;

[0185] S2, performing time-frequency domain transformation on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and determining a matching frequency of each audio signal segment according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of each audio signal segment is a frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment;

[0186] S3, based on a matching relationship between the matching frequencies in the matching frequency sequence and target frequencies in a target frequency group and a corresponding relationship between the target frequencies in the target frequency group and preset characters in a preset character group, resolving the matching frequency sequence into a preset character sequence, wherein the target frequency group is a preset frequency group in a plurality of preset frequency groups that matches the to-be-resolved audio signal, different preset frequency groups in the plurality of preset frequency groups do not overlap between frequency segments corresponding to each other, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups;

[0187] S4, based on a corresponding relationship between a text unit and a preset character, resolving the preset character sequence into a target text.

[0188] Optionally, specific examples in the embodiment can refer to the examples described in the above embodiments, and the embodiment will not be described here.

[0189] Optionally, in the embodiment, the storage medium can include but is not limited to a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0190] According to another aspect of the embodiment of the application, an electronic device for implementing the text data transmission method is also provided, and the electronic device can be a smart device, a server, a terminal, or a combination thereof.

[0191] Figure 12This is a structural block diagram of an optional electronic device according to an embodiment of this application, such as... Figure 12 As shown, it includes a processor 1202, a communication interface 1204, a memory 1206, and a communication bus 1208. The processor 1202, communication interface 1204, and memory 1206 communicate with each other via the communication bus 1208.

[0192] Memory 1206 is used to store computer programs;

[0193] When processor 1202 executes a computer program stored in memory 1206, it performs the following steps:

[0194] S1, the audio signal to be analyzed is segmented according to a preset duration to obtain a set of audio signal segments to be analyzed, wherein the audio signal to be analyzed is the audio signal to be analyzed obtained from the audio signal collected by the audio acquisition unit;

[0195] S2, perform time-frequency domain transformation on each audio signal segment in the set of audio signal segments to obtain the spectrum data corresponding to each audio signal segment, and determine the matching frequency of each audio signal segment based on the spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of each audio signal segment is the frequency with the largest amplitude-frequency characteristic in the spectrum data corresponding to each audio signal segment;

[0196] S3, based on the matching relationship between the matching frequency in the matching frequency sequence and the target frequency in the target frequency group, and the correspondence between the target frequency in the target frequency group and the preset character in the preset character group, the matching frequency sequence is parsed into a preset character sequence. The target frequency group is a preset frequency group that matches the audio signal to be parsed among multiple preset frequency groups. The frequency segments corresponding to different preset frequency groups in the multiple preset frequency groups do not overlap. The different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group of the multiple preset frequency groups.

[0197] S4. Based on the correspondence between text units and preset characters, the preset character sequence is parsed into target text.

[0198] Optionally, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 12Only one bus is shown among the various buses in the figure, but there can be two or more buses depending on the design of the apparatus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0199] The memory can include a RAM and can also include a non-volatile memory such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0200] As an example, the above-mentioned memory 1206 can include, but is not limited to, the segmentation unit 1102, the execution unit 1104, the first parsing unit 1106 and the second parsing unit 1108 in the push device of the above-mentioned resource information. In addition, other module units in the push device of the above-mentioned resource information can also be included, but not limited to, which will not be described in detail in this example.

[0201] The above-mentioned processor can be a general-purpose processor, which can include, but is not limited to, a CPU (Central Processing Unit), a NP (Network Processor), etc. It can also be a DSP (Digital Signal Processing), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0202] Optionally, the specific examples in the present embodiment can refer to the examples described in the above-mentioned embodiments, which will not be described in detail in the present embodiment.

[0203] Those skilled in the art can understand that Figure 12 The structure shown is only schematic, and the apparatus for implementing the above-mentioned method of transmitting text data can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD terminal device, etc. Figure 12 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device can further include more or less components (such as a network interface, a display device, etc.) than Figure 12 The structure shown is only schematic, and the apparatus for implementing the above-mentioned method of transmitting text data can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD terminal device, etc. Figure 12 different from the structure shown.

[0204] Those skilled in the art can understand that all or part of the steps of various methods in the above embodiments can be completed by a program instructing the terminal device related hardware, and the program can be stored in a computer readable storage medium, which can include a flash disk, a ROM, a RAM, a magnetic disk or an optical disk, etc.

[0205] The serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0206] The integrated units in the above embodiments, if realized in the form of software function units and sold or used as independent products, can be stored in the above computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or the whole or part of the technical solutions can be embodied in the form of software products, which are stored in the storage medium and include a plurality of instructions for causing one or more computer devices (which can be personal computers, servers or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0207] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0208] In the several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0209] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the scheme provided in the embodiments.

[0210] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or at least two units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or software function unit.

[0211] The above merely describes the preferred embodiments of the present application, and it should be pointed out that, for those skilled in the art, some improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method of transmitting text data, characterized by, The method comprises the following steps: segmenting a to-be-analyzed audio signal according to a preset time length to obtain a group of to-be-analyzed audio signal segments, wherein the to-be-analyzed audio signal is an audio signal to be analyzed obtained from an audio acquisition component; performing time-frequency domain transformation on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and determining a matching frequency of each audio signal segment according to the frequency spectrum data corresponding to each audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of each audio signal segment is a frequency with the maximum amplitude-frequency characteristic in the frequency spectrum data corresponding to each audio signal segment; analyzing the matching frequency sequence into a preset character sequence based on a matching relationship between the matching frequencies in the matching frequency sequence and target frequencies in a target frequency group and a corresponding relationship between the target frequencies in the target frequency group and preset characters in a preset character group, wherein the target frequency group is a preset frequency group matching the to-be-analyzed audio signal in a plurality of preset frequency groups, different preset frequency groups in the plurality of preset frequency groups do not overlap between the corresponding frequency segments, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group of the plurality of preset frequency groups; and analyzing the preset character sequence into target text based on a corresponding relationship between a text unit and a preset character.

2. The method of claim 1, wherein, Before the step of segmenting the to-be-analyzed audio signal according to the preset time length to obtain the group of to-be-analyzed audio signal segments, the method further comprises: in a case where a starting segment audio signal is identified in the audio signal collected from the audio acquisition component, determining the audio signal located after the starting segment audio signal in the audio signal collected by the audio acquisition component as the to-be-analyzed audio signal, wherein the starting segment audio signal is used to indicate that the audio signal after the starting segment audio signal is a valid audio signal.

3. The method of claim 1, wherein, Before the step of segmenting the to-be-analyzed audio signal according to the preset time length to obtain the group of to-be-analyzed audio signal segments, the method further comprises: performing noise reduction processing on the to-be-analyzed audio signal to obtain the to-be-analyzed audio signal after noise reduction, wherein the noise reduction processing comprises at least one of the following: noise attenuation processing, band-pass filtering processing.

4. The method of claim 3, wherein, The step of performing noise reduction processing on the to-be-analyzed audio signal to obtain the to-be-analyzed audio signal after noise reduction comprises: determining the target frequency group from the plurality of preset frequency groups according to a center frequency of the to-be-analyzed audio signal and a root mean square frequency of the to-be-analyzed audio signal, wherein the target frequency group is a preset frequency group in the plurality of preset frequency groups, and the corresponding frequency segment of the preset frequency group matches the center frequency and the root mean square frequency; performing filter parameter configuration on a preset band-pass filter according to the target frequencies in the target frequency group to obtain a target band-pass filter; performing band-pass filtering processing on the frequency spectrum data of the to-be-analyzed audio signal using the target band-pass filter to obtain the to-be-analyzed audio signal after filtering.

5. The method of claim 1, wherein, The audio signals in the to-be-resolved audio signal corresponding to adjacent preset characters are separated by interval audio signals corresponding to a target interval frequency, and the target interval frequency does not intersect with a frequency range corresponding to the target frequency group; The matching frequency sequence is resolved into a preset character sequence based on a matching relationship between a matching frequency in the matching frequency sequence and a target frequency in the target frequency group and a corresponding relationship between the target frequency in the target frequency group and a preset character in a preset character group, and the method comprises the following steps: In a case where the target interval frequency is less than a frequency range corresponding to the target frequency group, a step frequency in the matching frequency sequence is sequentially determined to obtain a step frequency sequence, wherein the step frequency is a matching frequency in the matching frequency sequence that is greater than a previous matching frequency and has a frequency difference with the previous matching frequency that is greater than or equal to a first frequency difference threshold; each step frequency in the step frequency sequence is resolved into a preset character corresponding to a target frequency matching the step frequency to obtain the preset character sequence, wherein the target frequency matching the step frequency is a target frequency in the target frequency group that has the smallest frequency difference with the step frequency. In a case where the target interval frequency is greater than a frequency range corresponding to the target frequency group, a step-down frequency in the matching frequency sequence is sequentially determined to obtain a step-down frequency sequence, wherein the step-down frequency is a matching frequency in the matching frequency sequence that is less than a previous matching frequency and has a frequency difference with the previous matching frequency that is greater than or equal to a second frequency difference threshold; each step-down frequency in the step-down frequency sequence is resolved into a preset character corresponding to a target frequency matching the step-down frequency to obtain the preset character sequence, wherein the target frequency matching the step-down frequency is a target frequency in the target frequency group that has the smallest frequency difference with the step-down frequency.

6. The method of claim 1, wherein, The time-frequency domain transformation is performed on each audio signal segment in the group of audio signal segments to obtain frequency spectrum data corresponding to each audio signal segment, and the method comprises the following steps: The following transformation operations are performed on the current audio signal to obtain frequency spectrum data corresponding to each audio signal segment: The current audio signal is sampled at a preset sampling frequency to obtain N sampling points corresponding to the current audio signal, wherein N is a positive integer greater than or equal to 2; Based on each sampling point in the N sampling points, a cosine basis signal corresponding to the sampling point is generated to obtain N cosine basis signals, and the similarity between the current audio signal and the N cosine basis signals is sequentially calculated to obtain N cosine similarity values; Based on each sampling point in the N sampling points, a sine basis signal corresponding to the sampling point is generated to obtain N sine basis signals, and the similarity between the current audio signal and the N sine basis signals is sequentially calculated to obtain N sine similarity values; and The frequency spectrum data corresponding to each audio signal segment is obtained by performing the following transformation operations on the current audio signal: The current audio signal is sampled at a preset sampling frequency to obtain N sampling points corresponding to the current audio signal, wherein N is a positive integer greater than or equal to 2; Based on each sampling point in the N sampling points, a cosine basis signal corresponding to the sampling point is generated to obtain N cosine basis signals, and the similarity between the current audio signal and the N cosine basis signals is sequentially calculated to obtain N cosine similarity values; Based on each sampling point in the N sampling points, a sine basis signal corresponding to the sampling point is generated to obtain N sine basis signals, and the similarity between the current audio signal and the N sine basis signals is sequentially calculated to obtain N sine similarity values; and The frequency spectrum data corresponding to each audio signal segment is obtained by performing the following transformation operations on the current audio signal: Discrete Fourier transform is performed on the current audio signal based on the N cosine similarity values and the N sine similarity values to obtain spectral data corresponding to the current audio signal.

7. The method according to any one of claims 1 to 6, characterized in that, After the matching frequency sequence is obtained by determining the matching frequency of each audio signal segment according to the spectral data corresponding to the audio signal segment, the method further comprises: The matching frequency sequence is windowed using a preset window function to obtain an updated matching frequency sequence, wherein the preset window function is a window function with a time length being an integer multiple of a preset signal time length of an audio signal corresponding to one preset character and a pulse width being the preset signal time length.

8. A text data transmission apparatus characterized by comprising: Comprise: The segmenting unit is configured to segment a to-be-analyzed audio signal according to a preset time length to obtain a group of to-be-analyzed audio signal segments, wherein the to-be-analyzed audio signal is an audio signal to be analyzed and is acquired from an audio acquisition component; The executing unit is configured to perform time-frequency domain transformation on each audio signal segment in the group of audio signal segments to obtain spectral data corresponding to the audio signal segment, and determine a matching frequency of the audio signal segment according to the spectral data corresponding to the audio signal segment to obtain a matching frequency sequence, wherein the matching frequency of the audio signal segment is a frequency with the largest amplitude-frequency characteristic in the spectral data corresponding to the audio signal segment; The first analyzing unit is configured to analyze the matching frequency sequence into a preset character sequence based on a matching relationship between the matching frequency in the matching frequency sequence and a target frequency in a target frequency group and a corresponding relationship between the target frequency in the target frequency group and a preset character in a preset character group, wherein the target frequency group is a preset frequency group matching the to-be-analyzed audio signal in a plurality of preset frequency groups, different preset frequency groups in the plurality of preset frequency groups do not overlap in a frequency segment, and different preset characters in the preset character group correspond to different preset frequencies in each preset frequency group in the plurality of preset frequency groups; The second analyzing unit is configured to analyze the preset character sequence into a target text based on a corresponding relationship between a text unit and a preset character.

9. A computer readable storage medium, characterized in that, The computer-readable storage medium comprises a stored program, wherein the program performs the method of any one of claims 1 to 7 when executed. 10.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 by using the computer program.

Images