A focusing method and system based on voice adjustment

Abstract

The present invention relates to the field of voice control technology, and relates to a focusing method based on voice adjustment, the method comprising acquiring a voice signal, the voice signal comprising a voice signal collected in an ophthalmic operating room; identifying an identity of a target user based on the voice signal to obtain a recognition result; obtaining authority information corresponding to the target user according to the recognition result, and judging whether the target user has authority to issue a control instruction to a focusing device based on the voice signal and the authority information to obtain a judgment result; preprocessing the voice signal according to the judgment result to obtain a preprocessed voice signal; focusing the focusing device according to the preprocessed voice signal, the present invention judges the authority of a user based on the voice information of the user, and when the control instruction satisfies the user authority, further preprocessing the voice signal, thereby realizing rapid focusing of a focusing mirror and improving the efficiency and accuracy of focusing.

Description

Technical Field

[0001] The present invention relates to the field of voice control technology, and in particular to a focusing method and system based on voice adjustment. Background Art

[0002] In ophthalmic surgery, the electric focusing of the focal length of the non-contact wide-angle lens system used with an ophthalmic surgical microscope requires a foot switch to be triggered. However, during surgery, foot switches for laser photocoagulators and other treatment equipment are often also prepared. It is easy to accidentally step on them during long-term surgery, resulting in hidden dangers in the surgery. At the same time, setting up more foot switches occupies a large space. Therefore, there is an urgent need for an ophthalmic surgery focusing method that can achieve fast and accurate focusing of ophthalmic surgery without the foot switch. Summary of the invention

[0003] The object of the present invention is to provide a focusing method and system based on voice adjustment to improve the above-mentioned problem.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions:

[0005] On the one hand, an embodiment of the present application provides a focusing method based on voice adjustment, the method comprising:

[0006] Acquiring a voice signal, wherein the voice signal includes a voice signal collected in an ophthalmic operating room;

[0007] Identify the identity of the target user based on the voice signal and obtain an identification result;

[0008] Obtaining authority information corresponding to the target user according to the recognition result, and judging whether the target user has authority to issue a control instruction to the focusing device based on the voice signal and the authority information, to obtain a judgment result;

[0009] Preprocessing the speech signal according to the judgment result to obtain a preprocessed speech signal;

[0010] The focusing device is focused according to the preprocessed voice signal.

[0011] In a second aspect, an embodiment of the present application provides a focusing system based on voice adjustment, the system comprising:

[0012] An acquisition module, used for acquiring a voice signal, wherein the voice signal includes a voice signal collected in an ophthalmic operating room;

[0013] A recognition module, used to recognize the identity of the target user based on the voice signal and obtain a recognition result;

[0014] A first processing module, configured to obtain permission information corresponding to the target user according to the recognition result, and determine whether the target user has permission to issue a control instruction to the focusing device based on the voice signal and the permission information, to obtain a determination result;

[0015] A second processing module, used for preprocessing the speech signal according to the judgment result to obtain a preprocessed speech signal;

[0016] The third processing module is used to adjust the focus of the focusing device according to the preprocessed voice signal.

[0017] In a third aspect, an embodiment of the present application provides a device, the device comprising a memory and a processor. The memory is used to store a computer program; the processor is used to implement the step of focusing based on voice adjustment in the above method when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned focusing method based on voice adjustment are implemented.

[0019] The beneficial effects of the present invention are:

[0020] The present invention identifies the identity information of the target user through voice signals, thereby matching the authority information corresponding to the target user and determining the control instructions that the user can take. When the user's authority matches the control instruction, the user's voice signal can be further preprocessed to obtain a preprocessed voice signal, and then the user's specific control instruction is identified based on the preprocessed voice signal to quickly focus the focusing mirror, thereby improving the efficiency and accuracy of focusing.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 The figure is a flow chart of a focusing method based on voice adjustment described in an embodiment of the present invention.

[0024] Figure 2 Schematic diagram of the structure of the focusing system based on voice adjustment described in an embodiment of the present invention.

[0025] Figure 3 The figure is a schematic diagram of the structure of a focusing device based on voice adjustment described in an embodiment of the present invention.

[0026] Labels in the figure: 901, acquisition module; 902, recognition module; 903, first processing module; 904, second processing module; 905, third processing module; 800, focusing device based on voice adjustment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0029] Embodiment 1:

[0030] This embodiment provides a focusing method based on voice adjustment. It can be understood that a scene can be set in this embodiment, for example: in an operating room, a scene in which a doctor performs ophthalmic surgery on a patient.

[0031] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, and step S5.

[0032] Step S1, obtaining a voice signal, wherein the voice signal includes a voice signal collected in an ophthalmic operating room;

[0033] Step S2: identifying the identity of the target user based on the voice signal to obtain a recognition result;

[0034] In this step, the identity of the target user is identified by extracting the voiceprint features in the voice signal to determine whether he or she is the surgeon or other medical staff.

[0035] Step S3, obtaining authority information corresponding to the target user according to the recognition result, and judging whether the target user has the authority to issue a control instruction to the focusing device based on the voice signal and the authority information, and obtaining a judgment result;

[0036] In this step, the surgeon and other medical staff in the operating room have different permissions. The doctor can send all control instructions to the focusing device, including switch control instructions and focus control instructions, but other medical staff only have the authority to send switch instructions to the focusing device. When other medical staff send focus control instructions, the focusing device will not operate.

[0037] Step S4, preprocessing the speech signal according to the judgment result to obtain a preprocessed speech signal;

[0038] The step S4 also includes steps S41, S42, S43 and S44, which specifically include:

[0039] Step S41: When the judgment result is that the target user has the authority to issue a control instruction to the focusing device, the voice signal is processed by using a high-pass filter to obtain a first voice signal;

[0040] In this step, a high-pass filter is used to enhance the high frequencies of the speech signal.

[0041] Step S42, performing frame processing on the first voice signal to obtain a second voice signal, wherein the second voice signal includes at least two segments of the first voice signal after the frame processing;

[0042] In this step, in order to make the extracted features more effective, the speech signal is framed to improve the stability of the speech signal.

[0043] Step S43, overlapping two adjacent segments of the first speech signal after frame processing based on preset overlapping length information to obtain a third speech signal;

[0044] In this step, the preset overlap length is one quarter of the frame length.

[0045] Step S44: perform windowing processing on the third speech signal to obtain the preprocessed speech signal.

[0046] In this embodiment, in order to avoid interference and stress to patients in the operating room, the doctor needs to keep the voice as low as possible when sending voice commands. Therefore, during pre-processing, it is necessary to first use a high-pass filter to enhance it and then divide it into frames, so as to improve the recognition effect of low-volume voice signals.

[0047] Step S5: focusing the focusing device according to the preprocessed voice signal.

[0048] The step S5 also includes step S51, step S52, step S53, step S54, and step S5, which specifically include:

[0049] Step S51, obtaining an interfering voice signal;

[0050] In this step, the interfering voice signals include the noise of equipment operation, the noise of communication between the surgeon and other personnel, and the footsteps in the corridor outside the operating room.

[0051] Step S52: preprocessing the interference speech signal to obtain a preprocessed interference speech signal;

[0052] In this step, the preprocessing process of the interfering speech signal is the same as the preprocessing process of the speech signal, so it will not be described here in detail.

[0053] Step S53, sending the preprocessed interference speech signal and the preprocessed speech signal to the trained speech enhancement model to obtain an enhanced speech signal;

[0054] In this step, in order to avoid interference and stress to the patient during the operation, the target user needs to use a lower voice when sending voice commands, so the voice signal needs to be enhanced to improve the recognition accuracy.

[0055] The step S53 also includes step S531, step S532 and step S533, which specifically include:

[0056] Step S531: determining first information according to the enhanced speech signal, wherein the first information includes a speech quality perception evaluation value, a segmented signal-to-noise ratio, and a weighted spectral slope measure corresponding to the enhanced speech signal;

[0057] In this step, the speech quality perception evaluation value is based on the subjective perception of the speech signal, which compares the difference between the original speech and the enhanced speech to produce a score; the segmented signal-to-noise ratio is the signal-to-noise ratio of the speech signal segment to more carefully evaluate the performance of the speech enhancement model in different time periods; the weighted spectral slope measure is calculated based on the weighted difference between the spectral slopes of each frequency band.

[0058] Step S532: Calculate second information according to the first information, where the second information includes the degree of intrusion of the interfering voice signal into the enhanced voice signal;

[0059] In this step, the second information is calculated according to the first information as follows:

[0060] C=1.634+0.478X-0.007Y+0.063Z

[0061] In the above formula, X, Y, and Z represent the speech quality perception evaluation value, the segmented signal-to-noise ratio, and the weighted spectral slope measure corresponding to the enhanced speech signal, respectively.

[0062] Step S533: determine whether the speech enhancement model has completed training according to the second information, and obtain the trained speech enhancement model.

[0063] In this step, the degree of intrusion of the interfering speech signal on the enhanced speech signal is used to evaluate the speech quality after the speech enhancement model is enhanced, so as to judge the training degree of the speech enhancement model. When the speech quality after the speech enhancement model is enhanced is greater than the preset threshold, the training of the speech enhancement model is stopped.

[0064] The step S53 also includes steps S534, S535, S536, and S537, which specifically include:

[0065] Step S534: Map the preprocessed speech signal to the frequency domain and extract frequency domain features to obtain first feature information;

[0066] In this step, the preprocessed speech signal is processed using graph Fourier transform to obtain the first feature information. It should be noted that graph Fourier transform extracts the features of the speech signal and can effectively characterize the correlation between the sampling points of the speech time series signal.

[0067] Step S535, mapping the preprocessed interference speech signal to the frequency domain and extracting frequency domain features to obtain second feature information;

[0068] Step S536: Process the first feature information and the second feature information using a non-negative matrix decomposition algorithm to obtain processed first feature information and processed second feature information;

[0069] Step S537: enhance the speech signal according to the processed first feature information and the processed second feature information.

[0070] In this embodiment, the features of the speech signal are extracted by graph Fourier transform, which can effectively capture the phase information that is easily overlooked compared to short-time Fourier transform. The feature information is then processed using a non-negative matrix decomposition algorithm, which can enhance the speech signal while reducing the amount of data calculations and increasing the recognition speed, thereby further improving surgical efficiency.

[0071] The step S537 also includes steps S5371, S5372, S5373, S5374, and S5375, which specifically include:

[0072] Step S5371, updating the coefficient matrix in the processed second feature information to obtain an updated coefficient matrix;

[0073] In this step, the coefficient matrix is ​​updated using the Euclidean distance.

[0074] Step S5372: performing calculations based on the processed first feature information and the updated coefficient matrix to obtain calculation results;

[0075] In this step, the processed first feature information is multiplied by the updated coefficient matrix to obtain a calculation result, namely, an amplitude matrix.

[0076] Step S5373: Map the calculation result to the time domain to obtain a reconstructed speech signal;

[0077] Step S5374, performing Fourier transform on the reconstructed speech signal to obtain a speech signal after Fourier transform;

[0078] Step S5375: Send the Fourier transformed speech signal to the dual-path attention mechanism to obtain an enhanced speech signal.

[0079] In this step, the dual-path attention mechanism includes a time domain attention mechanism and a frequency domain attention mechanism. The dual-path attention mechanism first calculates two sets of attention weights through the frequency path and the time path respectively. Then, the two sets of weights are fused to form the final comprehensive attention weights, which are used to weightedly integrate the speech features in both frequency and time domains. The dual-stream attention mechanism can effectively capture the long-distance dependencies in the time-frequency domain sequences, so that the model can learn and infer more quickly. Through the organic combination of these two paths, a more comprehensive and efficient speech signal modeling is achieved, thereby enhancing the speech signal and improving the recognition accuracy of low-volume speech signals. It should be noted that this application does not limit the structure of the dual-path attention mechanism.

[0080] In this embodiment, the voice signal is enhanced so that the voice signal of the target user can be accurately and quickly recognized in an operating room with limited sound, thereby improving the efficiency of the operation without disturbing the patient.

[0081] Step S54, determining a control instruction according to the enhanced voice signal;

[0082] In this step, the enhanced voice signal is sent to the audio recognition model to obtain the control instructions of the target user.

[0083] Step S55, focusing the focusing device according to the control instruction.

[0084] The step S55 also includes step S551, step S552, and step S553, which specifically include:

[0085] Step S551, obtaining a first control instruction, wherein the first control instruction is used to enable the focusing mirror of the focusing device to be located at a central position after quickly completing the scanning of the upper half and the lower half;

[0086] Step S552, determining third information according to the first control instruction, wherein the third information includes a position range of an optimal focal point of the fundus of the patient;

[0087] Step S553: ​​determine the position information of the best focus point according to the third information.

[0088] In this embodiment, a specific implementation is: the entire focal length adjustment range is divided into 8 steps. When the first control instruction is obtained, the focusing mirror of the focusing device responds to the first control instruction, quickly completes the upper half and the lower half of the scan, and then is located in the center position, thereby achieving a rapid screening to determine whether the best focus is located in the upper half of the scan or the lower half of the scan, thereby determining the position range of the best focus, providing a basis for subsequent focusing.

[0089] The step S553 also includes step S5531 and step S5532, which specifically include:

[0090] Step S5531, obtaining a second control instruction, where the second control instruction is used to adjust the focusing mirror to the center from bottom to top within the position range of the best focal point;

[0091] Step S5532, in response to the second control instruction, determine whether the best focus appears during the readjustment process, wherein if the best focus does not appear, obtain the third control instruction, and the third control instruction is used to adjust the focusing mirror upward by one step; if the best focus appears, obtain the fourth control instruction, and the fourth control instruction is used to adjust the focusing mirror downward by one step.

[0092] In this embodiment, a specific implementation is: if the optimal focus is in the lower half, in response to the second control instruction, the focusing mirror is centered from bottom to top. If it is close to the optimal state when centered, a fourth control instruction is sent to adjust the focusing mirror downward by one step; if the difference from the optimal state when centered is large, a fifth control instruction is sent to adjust the focusing mirror downward by two steps. The control instructions obtained by voice recognition according to the present invention are designed based on dichotomy, and can be separated from the foot switch, and focusing can be achieved quickly, thereby improving the efficiency of the operation.

[0093] It should be noted that the present application does not limit the specific settings of the control instructions, and the surgeon can set them according to his or her own habits.

[0094] Embodiment 2:

[0095] like Figure 2 As shown, this embodiment provides a focusing system based on voice adjustment, the system includes an acquisition module 901, a recognition module 902, a first processing module 903, a second processing module 904, and a third processing module 905, which specifically include:

[0096] An acquisition module 901 is used to acquire a voice signal, wherein the voice signal includes a voice signal collected in an ophthalmic operating room;

[0097] The recognition module 902 is used to recognize the identity of the target user based on the voice signal and obtain a recognition result;

[0098] The first processing module 903 is used to obtain the authority information corresponding to the target user according to the recognition result, and determine whether the target user has the authority to issue a control instruction to the focusing device based on the voice signal and the authority information to obtain a determination result;

[0099] A second processing module 904 is used to pre-process the speech signal according to the judgment result to obtain a pre-processed speech signal;

[0100] The third processing module 905 is used to adjust the focus of the focusing device according to the pre-processed voice signal.

[0101] In a specific embodiment disclosed in the present application, the second processing module further includes a first processing unit, a second processing unit, a third processing unit, and a fourth processing unit, which specifically include:

[0102] A first processing unit, configured to process the voice signal using a high-pass filter to obtain a first voice signal when the judgment result is that the target user has the authority to issue a control instruction to the focusing device;

[0103] A second processing unit, configured to perform frame processing on the first voice signal to obtain a second voice signal, wherein the second voice signal includes at least two segments of the first voice signal after the frame processing;

[0104] A third processing unit, configured to overlap two adjacent segments of the first speech signal after the frame processing based on preset overlap length information to obtain a third speech signal;

[0105] The fourth processing unit is used to perform windowing processing on the third speech signal to obtain the preprocessed speech signal.

[0106] In a specific implementation manner disclosed in the present application, the third processing module further includes a first acquisition unit, a fifth processing unit, an enhancement unit, a sixth processing unit, and a seventh processing unit, which specifically include:

[0107] A first acquisition unit, used to acquire an interfering speech signal;

[0108] A fifth processing unit, configured to preprocess the interference speech signal to obtain a preprocessed interference speech signal;

[0109] An enhancement unit, used for sending the preprocessed interference speech signal and the preprocessed speech signal to the trained speech enhancement model to obtain an enhanced speech signal;

[0110] a sixth processing unit, configured to determine a control instruction according to the enhanced voice signal;

[0111] The seventh processing unit is used to focus the focusing device according to the control instruction.

[0112] In a specific implementation manner disclosed in the present application, the enhancement unit further includes an eighth processing unit, a ninth processing unit, a tenth processing unit, and an eleventh processing unit, which specifically include:

[0113] An eighth processing unit, configured to map the preprocessed speech signal into a frequency domain and extract frequency domain features to obtain first feature information;

[0114] A ninth processing unit, configured to map the preprocessed interference speech signal to the frequency domain and extract frequency domain features to obtain second feature information;

[0115] a tenth processing unit, configured to process the first feature information and the second feature information by using a non-negative matrix decomposition algorithm to obtain processed first feature information and processed second feature information;

[0116] The eleventh processing unit is used to enhance the speech signal according to the processed first feature information and the processed second feature information.

[0117] In a specific implementation manner disclosed in the present application, the eleventh processing unit further includes a twelfth processing unit, a first calculation unit, a thirteenth processing unit, a fourteenth processing unit, and a fifteenth processing unit, which specifically include:

[0118] A twelfth processing unit, used for updating the coefficient matrix in the processed second feature information to obtain an updated coefficient matrix;

[0119] A first calculation unit, used to perform calculation according to the processed first feature information and the updated coefficient matrix to obtain a calculation result;

[0120] A thirteenth processing unit, used for mapping the calculation result into the time domain to obtain a reconstructed speech signal;

[0121] A fourteenth processing unit, configured to perform Fourier transform on the reconstructed speech signal to obtain a speech signal after Fourier transform;

[0122] The fifteenth processing unit is used to send the speech signal after Fourier transformation to the dual-path attention mechanism to obtain the enhanced speech signal.

[0123] In a specific implementation manner disclosed in the present application, the enhancement unit further includes a sixteenth processing unit, a second calculation unit, and a seventeenth processing unit, which specifically include:

[0124] A sixteenth processing unit, configured to determine first information according to the enhanced speech signal, wherein the first information includes a speech quality perception evaluation value, a segmented signal-to-noise ratio, and a weighted spectral slope measure corresponding to the enhanced speech signal;

[0125] A second calculation unit, configured to calculate second information according to the first information, wherein the second information includes a degree of intrusion of the interfering speech signal into the enhanced speech signal;

[0126] The seventeenth processing unit is used to determine whether the speech enhancement model has completed training based on the second information, and obtain the trained speech enhancement model.

[0127] In a specific implementation manner disclosed in the present application, the seventh processing unit further includes a second acquisition unit, an eighteenth processing unit, and a nineteenth processing unit, which specifically include:

[0128] A second acquisition unit is used to acquire a first control instruction, where the first control instruction is used to enable the focusing mirror of the focusing device to be located at a central position after quickly completing the scanning of the upper half and the lower half;

[0129] an eighteenth processing unit, configured to determine third information according to the first control instruction, wherein the third information includes a position range of an optimal focal point of a fundus of a patient;

[0130] The nineteenth processing unit is used to determine the position information of the best focus point according to the third information.

[0131] In a specific implementation manner disclosed in the present application, the nineteenth processing unit further includes a third acquisition unit and a response unit, which specifically include:

[0132] A third acquisition unit is used to acquire a second control instruction, where the second control instruction is used to adjust the focusing mirror to center from bottom to top within the position range of the best focal point;

[0133] A response unit is used to respond to the second control instruction and determine whether an optimal focus appears during the readjustment process, wherein if the optimal focus does not appear, a third control instruction is obtained, and the third control instruction is used to adjust the focusing mirror upward by one step; if the optimal focus appears, a fourth control instruction is obtained, and the fourth control instruction is used to adjust the focusing mirror downward by one step.

[0134] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0135] Embodiment 3:

[0136] Corresponding to the above method embodiment, this embodiment also provides a focusing device based on voice adjustment. The focusing device based on voice adjustment described below and the focusing method based on voice adjustment described above can refer to each other.

[0137] Figure 3 8 is a block diagram of a focusing device 800 based on voice adjustment according to an exemplary embodiment. Figure 3 As shown, the focus adjustment device 800 based on voice adjustment may include: a processor 801 and a memory 802. The focus adjustment device 800 based on voice adjustment may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0138] The processor 801 is used to control the overall operation of the voice-adjustment-based focusing device 800 to complete all or part of the steps in the above-mentioned voice-adjustment-based focusing method. The memory 802 is used to store various types of data to support the operation of the voice-adjustment-based focusing device 800, and these data may include, for example, instructions for any application or method operating on the voice-adjustment-based focusing device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the voice-adjustable focusing device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0139] In an exemplary embodiment, the voice-adjustment-based focusing device 800 can be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned voice-adjustment-based focusing method.

[0140] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned focusing method based on voice adjustment are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the focusing device 800 based on voice adjustment to complete the above-mentioned focusing method based on voice adjustment.

[0141] Embodiment 4:

[0142] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the focusing method based on voice adjustment described above can refer to each other.

[0143] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the focusing method based on voice adjustment in the above method embodiment are implemented.

[0144] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0145] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0146] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A focusing method based on voice adjustment, characterized in that: include: Acquiring a voice signal, wherein the voice signal includes a voice signal collected in an ophthalmic operating room; Identify the identity of the target user based on the voice signal and obtain an identification result; Obtaining authority information corresponding to the target user according to the recognition result, and determining whether the target user has authority to issue a control instruction to the focusing device based on the voice signal and the authority information, to obtain a determination result; Preprocessing the speech signal according to the judgment result to obtain a preprocessed speech signal; focusing a focusing device according to the preprocessed voice signal; The method of preprocessing the speech signal according to the judgment result to obtain the preprocessed speech signal includes: When the judgment result is that the target user has the authority to issue a control instruction to the focusing device, the voice signal is processed by using a high-pass filter to obtain a first voice signal; Performing frame processing on the first voice signal to obtain a second voice signal, wherein the second voice signal includes at least two segments of the first voice signal after the frame processing; Overlapping two adjacent segments of the first speech signal after frame processing based on preset overlapping length information to obtain a third speech signal; Performing windowing processing on the third speech signal to obtain the preprocessed speech signal; The focusing device is focused according to the preprocessed voice signal, comprising: Obtaining an interfering voice signal; Preprocessing the interfering speech signal to obtain a preprocessed interfering speech signal; Sending the preprocessed interference speech signal and the preprocessed speech signal to the trained speech enhancement model to obtain an enhanced speech signal; Determining a control instruction according to the enhanced voice signal; focusing the focusing device according to the control instruction; The focusing device is focused according to the control instruction, comprising: Acquire a first control instruction, where the first control instruction is used to enable a focusing mirror of the focusing device to be located at a center position after quickly completing scanning of an upper half and a lower half; Determine third information according to the first control instruction, wherein the third information includes a position range of an optimal focal point of the patient's fundus; Determine the position information of the best focal point according to the third information; Wherein, determining the position information of the best focal point according to the third information includes: Obtaining a second control instruction, where the second control instruction is used to adjust the focusing mirror to center from bottom to top within the position range of the best focal point; In response to the second control instruction, it is determined whether an optimal focus appears during the readjustment process, wherein if the optimal focus does not appear, a third control instruction is obtained, and the third control instruction is used to adjust the focusing mirror upward by one step; if the optimal focus appears, a fourth control instruction is obtained, and the fourth control instruction is used to adjust the focusing mirror downward by one step.

2. The focusing method based on voice adjustment according to claim 1, characterized in that: Sending the preprocessed interference speech signal and the preprocessed speech signal to the trained speech enhancement model includes: Mapping the preprocessed speech signal to the frequency domain and extracting frequency domain features to obtain first feature information; Mapping the preprocessed interference speech signal to the frequency domain and extracting the frequency domain features to obtain the second feature information; Processing the first feature information and the second feature information using a non-negative matrix decomposition algorithm to obtain processed first feature information and processed second feature information; The speech signal is enhanced according to the processed first feature information and the processed second feature information.

3. The focusing method based on voice adjustment according to claim 1, characterized in that: Before sending the preprocessed interference speech signal and the preprocessed speech signal to the trained speech enhancement model, the method further includes: Determining first information according to the enhanced speech signal, the first information including a speech quality perception evaluation value, a segmented signal-to-noise ratio, and a weighted spectral slope measure corresponding to the enhanced speech signal; Calculating second information according to the first information, the second information including the degree of intrusion of the interfering speech signal into the enhanced speech signal; Determine whether the speech enhancement model has been trained according to the second information, and obtain a trained speech enhancement model; The calculation of the second information according to the first information is specifically as follows: C=1.634+0.478X-0.007Y+0.063Z In the above formula, X, Y, and Z represent the speech quality perception evaluation value, the segmented signal-to-noise ratio, and the weighted spectral slope measure corresponding to the enhanced speech signal, respectively.

4. A focusing system based on voice adjustment, characterized in that: include: An acquisition module, used for acquiring a voice signal, wherein the voice signal includes a voice signal collected in an ophthalmic operating room; A recognition module, used to recognize the identity of the target user based on the voice signal and obtain a recognition result; A first processing module, configured to obtain permission information corresponding to the target user according to the recognition result, and determine whether the target user has permission to issue a control instruction to the focusing device based on the voice signal and the permission information, to obtain a determination result; A second processing module, used for preprocessing the speech signal according to the judgment result to obtain a preprocessed speech signal; A third processing module, used for adjusting the focus of the focusing device according to the preprocessed voice signal; Wherein, the second processing module includes: A first processing unit, configured to process the voice signal using a high-pass filter to obtain a first voice signal when the judgment result is that the target user has the authority to issue a control instruction to the focusing device; A second processing unit, configured to perform frame processing on the first voice signal to obtain a second voice signal, wherein the second voice signal includes at least two segments of the first voice signal after the frame processing; A third processing unit, configured to overlap two adjacent segments of the first speech signal after the frame processing based on preset overlap length information to obtain a third speech signal; a fourth processing unit, configured to perform windowing processing on the third speech signal to obtain the preprocessed speech signal; Wherein, the third processing module includes: A first acquisition unit, used to acquire an interfering speech signal; A fifth processing unit, configured to preprocess the interference speech signal to obtain a preprocessed interference speech signal; An enhancement unit, used for sending the preprocessed interference speech signal and the preprocessed speech signal to the trained speech enhancement model to obtain an enhanced speech signal; a sixth processing unit, configured to determine a control instruction according to the enhanced voice signal; a seventh processing unit, configured to adjust the focus of the focusing device according to the control instruction; Wherein, the seventh processing unit comprises: A second acquisition unit is used to acquire a first control instruction, where the first control instruction is used to enable the focusing mirror of the focusing device to be located at a central position after quickly completing the scanning of the upper half and the lower half; an eighteenth processing unit, configured to determine third information according to the first control instruction, wherein the third information includes a position range of an optimal focal point of a fundus of a patient; A nineteenth processing unit, configured to determine position information of an optimal focal point according to the third information; Wherein, the nineteenth processing unit comprises: A third acquisition unit is used to acquire a second control instruction, where the second control instruction is used to adjust the focusing mirror to center from bottom to top within the position range of the best focal point; A response unit is used to respond to the second control instruction and determine whether an optimal focus appears during the readjustment process, wherein if the optimal focus does not appear, a third control instruction is obtained, and the third control instruction is used to adjust the focusing mirror upward by one step; if the optimal focus appears, a fourth control instruction is obtained, and the fourth control instruction is used to adjust the focusing mirror downward by one step.

Images