CN116473521B - Voice frequency spectrum identification method and system for suspected cyprocoytenoid dislocation - Google Patents
Voice frequency spectrum identification method and system for suspected cyprocoytenoid dislocation Download PDFInfo
- Publication number
- CN116473521B CN116473521B CN202310736117.5A CN202310736117A CN116473521B CN 116473521 B CN116473521 B CN 116473521B CN 202310736117 A CN202310736117 A CN 202310736117A CN 116473521 B CN116473521 B CN 116473521B
- Authority
- CN
- China
- Prior art keywords
- dislocation
- data
- normal
- sound
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001228 spectrum Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004088 simulation Methods 0.000 claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 38
- 210000003041 ligament Anatomy 0.000 claims description 48
- 239000012530 fluid Substances 0.000 claims description 14
- 206010023204 Joint dislocation Diseases 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000013527 convolutional neural network Methods 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 22
- 210000001260 vocal cord Anatomy 0.000 description 12
- 238000010586 diagram Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 206010002091 Anaesthesia Diseases 0.000 description 2
- 206010013952 Dysphonia Diseases 0.000 description 2
- 208000010473 Hoarseness Diseases 0.000 description 2
- 230000005534 acoustic noise Effects 0.000 description 2
- 230000037005 anaesthesia Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 210000002784 stomach Anatomy 0.000 description 2
- 210000003437 trachea Anatomy 0.000 description 2
- 206010002953 Aphonia Diseases 0.000 description 1
- 206010008479 Chest Pain Diseases 0.000 description 1
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000000205 arytenoid cartilage Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000003685 cricoid cartilage Anatomy 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 210000004704 glottis Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003928 nasal cavity Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 208000013220 shortness of breath Diseases 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4803—Speech analysis specially adapted for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The application discloses a suspected cyprocoytenoid dislocation voice frequency spectrum identification method and a system, comprising the following steps: collecting sound data of a target patient before an object possibly causing dislocation of the ladle joint is placed in the target patient as normal sound data; performing audio analysis on the normal sound data to obtain normal sound parameters; inputting normal sound parameters into an dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions; collecting sound data of a target patient after taking out an embedded object as abnormal sound data; and comparing the abnormal sound data with the dislocation simulation data, and taking the comparison result as a recognition result. The application provides a voice recognition scheme independent of a convolutional neural network, which requires smaller calculation force and is very suitable for a mobile terminal; meanwhile, as the identification mode is to extract parameters through normal sound of the same patient, the accuracy of final identification can be effectively improved.
Description
Technical Field
The application relates to a voice recognition technology, in particular to a voice spectrum recognition method and a voice spectrum recognition system for suspected cyprocoytenoid dislocation.
Background
The arytenoid joint consists of the arytenoid joint surface of the cricoid cartilage, the arytenoid basal plane, the arytenoid lateral muscle, the arytenoid posterior muscle and the arytenoid ligament. The arytenoid cartilage performs an inward and outward rotational movement along the vertical axis of the joint, and simultaneously slides inward and outward, so that the vocal cords on both sides are mutually close to or separated from each other, thereby making the glottis open or narrow. Dislocation of the ladle joint may cause various degrees of hoarseness or even aphonia. Hoarseness is a typical symptom of dislocation of the ladle joint, and the voice is mainly breath sound, can not speak loudly, can not speak aloud, is laborious to speak, is easy to fatigue, and even can appear shortness of breath and chest distress when speaking.
In the prior art, the paper "correlation study of voice acoustic analysis and VHI_10 of patients with single-side arytenoid dislocation" discloses the content of voice analysis of arytenoid dislocation, which studies the corresponding relation between arytenoid dislocation and Jitter and shimmer and VHI-10, but because of the difference of vocal cord characteristics of different patients, training and identification are difficult to be carried out through a common convolutional neural network, and meanwhile, the method is also unfavorable for self-checking of patients at a mobile end.
Disclosure of Invention
In order to overcome at least the above-mentioned shortcomings in the prior art, an object of the present application is to provide a method and system for voice spectrum identification of suspected dislocation of the cyprocoytenoid joint.
In a first aspect, an embodiment of the present application provides a method for identifying a suspected bowl dislocation voice spectrum, including:
collecting sound data of a target patient before an object possibly causing dislocation of the ladle joint is placed in the target patient as normal sound data;
performing audio analysis on the normal sound data to obtain normal sound parameters;
inputting the normal sound parameters into an dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions;
collecting sound data of a target patient after taking out an embedded object as abnormal sound data;
and comparing the abnormal sound data with the dislocation simulation data, and taking a comparison result as a recognition result.
When the embodiment of the application is implemented, the sound of a target patient before dislocation of the cyprocoytenoid joint does not occur, namely, the sound is collected before operations such as anesthesia trachea cannula, stomach tube insertion and the like, and the sound data is required to be used as a reference for recognition of the sound after the subsequent dislocation. After audio analysis of the normal sound data, various parameters such as formants, pitch frequencies, sound noise data, etc. can be obtained, and these parameters can be used as normal sound parameters.
In the embodiment of the application, the technical scheme is mainly applied to the mobile terminal, and in order to reduce the computational force pressure brought by a common convolutional neural network model, a scheme for dislocation simulation based on normal sound parameters is adopted. Namely, the normal sound parameters are converted into possible dislocation simulation data under different dislocation conditions through the dislocation simulation model. It should be understood that the dislocation simulation data herein is related parameters such as pitch frequency and acoustic noise data, etc., which are possibly related after dislocation generated based on normal sound parameters.
In the implementation of the application, corresponding sound data are acquired when the dislocation of the ladle joint can occur after the patient takes out the imbedded object. The difference between the abnormal sound data and the dislocation simulation data can be identified for subsequent use by comparing the abnormal sound data and the dislocation simulation data. According to the technical scheme, the voice recognition scheme independent of the convolutional neural network is provided, the required calculation force is small, and the voice recognition scheme is very suitable for mobile terminals; meanwhile, as the identification mode is to extract parameters through normal sound of the same patient, the accuracy of final identification can be effectively improved.
In one possible implementation, collecting sound data of a target patient before an object that may cause dislocation of the ladle joint is not placed as normal sound data includes:
collecting the sound of a target patient in making a first vowel as first normal data, and collecting the sound of the target patient in making a second vowel as second normal data; the first tone uses a and the second tone uses u.
In one possible implementation, performing audio analysis on the normal sound data to obtain a normal sound parameter includes:
performing audio analysis on the first normal data to obtain a first fundamental tone frequency corresponding to the first normal data; and performing audio analysis on the second normal data to obtain a second fundamental tone frequency corresponding to the second normal data.
In one possible implementation, the dislocation simulation model includes a normal model and a dislocation model;
the generating of the normal model comprises the following steps:
establishing an acoustic ligament fluid mechanics model; the acoustic ligament fluid mechanical model comprises a left ligament and a right ligament, and vibration parameters of the left ligament and the right ligament are adjustable;
adjusting vibration parameters of the left and right ligaments in the acoustic ligament fluid mechanical model and calculating as calculated pitch frequencies generated when airflow passes through the left and right ligaments;
and establishing a first simulated sound function as the normal model according to the corresponding relation between the calculated fundamental tone frequency and the corresponding vibration parameter.
In one possible implementation, the generating of the dislocation model includes:
adjusting vibration constraints of the left and right ligaments in the acoustic ligament hydrodynamic model and calculating a pitch frequency generated when different air flows pass through the left and right ligaments as an dislocated pitch frequency;
and establishing a second simulated sound function as the dislocation model according to the dislocation fundamental tone frequency, the corresponding relation between the vibration parameter and the corresponding vibration constraint condition.
In one possible implementation manner, inputting the normal sound parameter into an dislocation simulation model, and generating dislocation simulation data corresponding to a plurality of different dislocation situations includes:
selecting a vibration parameter interval corresponding to an interval between the first fundamental tone frequency and the second fundamental tone frequency from the first simulated voice function according to the first fundamental tone frequency and the second fundamental tone frequency;
selecting a plurality of groups of corresponding relations between the dislocation fundamental tone frequency corresponding to the vibration parameter interval and the corresponding vibration constraint conditions from the second simulated sound function according to the vibration parameter interval as dislocation simulated data; each set of correspondence corresponds to a different airflow through the left and right ligaments.
In one possible implementation, the abnormal sound data includes first abnormal data corresponding to a first vowel and second abnormal data corresponding to a second vowel;
comparing the abnormal sound data with the dislocation simulation data, and taking a comparison result as an identification result to comprise:
inputting the first abnormal data and the second abnormal data into a plurality of groups of corresponding relations in the dislocation simulation data, and obtaining a plurality of first output results corresponding to the first abnormal data and a plurality of second output results corresponding to the second abnormal data;
and selecting the nearest output result from the first output result and the second output result as the identification result.
In a second aspect, embodiments of the present application provide a voice spectrum identification system for suspected bowl dislocation, comprising:
a first acquisition module configured to acquire sound data of a target patient before an object that may cause dislocation of an arytenoid joint is placed therein as normal sound data;
the analysis module is configured to perform audio analysis on the normal sound data to obtain normal sound parameters;
the dislocation simulation module is configured to input the normal sound parameters into a dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions;
the second acquisition module is configured to acquire sound data of a target patient after the target patient takes out the embedded object as abnormal sound data;
and the comparison module is configured to compare the abnormal sound data with the dislocation simulation data and take the comparison result as a recognition result.
In one possible implementation, the first acquisition module is further configured to:
collecting the sound of a target patient in making a first vowel as first normal data, and collecting the sound of the target patient in making a second vowel as second normal data; the first tone uses a and the second tone uses u.
In one possible implementation, the analysis module is further configured to:
performing audio analysis on the first normal data to obtain a first fundamental tone frequency corresponding to the first normal data; and performing audio analysis on the second normal data to obtain a second fundamental tone frequency corresponding to the second normal data.
Compared with the prior art, the application has the following advantages and beneficial effects:
the application provides a suspected cyprocoytenoid dislocation voice frequency spectrum recognition method and a suspected cyprocoytenoid dislocation voice frequency spectrum recognition system, which provide a voice recognition scheme independent of a convolutional neural network, have smaller calculation force and are very suitable for mobile terminals; meanwhile, as the identification mode is to extract parameters through normal sound of the same patient, the accuracy of final identification can be effectively improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a schematic diagram of steps of a method according to an embodiment of the present application;
fig. 2 is a schematic diagram of a system architecture according to an embodiment of the application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Furthermore, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1 in combination, a flow chart of a method for identifying a suspected cyprocollex joint dislocation voice spectrum according to an embodiment of the present application is shown, where the method for identifying a suspected cyprocollex joint dislocation voice spectrum may be applied to the system for identifying a suspected cyprocollex joint dislocation voice spectrum in fig. 2, and further, the method for identifying a suspected cyprocollex joint dislocation voice spectrum may specifically include the following steps S1 to S5.
S1: collecting sound data of a target patient before an object possibly causing dislocation of the ladle joint is placed in the target patient as normal sound data;
s2: performing audio analysis on the normal sound data to obtain normal sound parameters;
s3: inputting the normal sound parameters into an dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions;
s4: collecting sound data of a target patient after taking out an embedded object as abnormal sound data;
s5: and comparing the abnormal sound data with the dislocation simulation data, and taking a comparison result as a recognition result.
When the embodiment of the application is implemented, the sound of a target patient before dislocation of the cyprocoytenoid joint does not occur, namely, the sound is collected before operations such as anesthesia trachea cannula, stomach tube insertion and the like, and the sound data is required to be used as a reference for recognition of the sound after the subsequent dislocation. After audio analysis of the normal sound data, various parameters such as formants, pitch frequencies, sound noise data, etc. can be obtained, and these parameters can be used as normal sound parameters.
In the embodiment of the application, the technical scheme is mainly applied to the mobile terminal, and in order to reduce the computational force pressure brought by a common convolutional neural network model, a scheme for dislocation simulation based on normal sound parameters is adopted. Namely, the normal sound parameters are converted into possible dislocation simulation data under different dislocation conditions through the dislocation simulation model. It should be understood that the dislocation simulation data herein is related parameters such as pitch frequency and acoustic noise data, etc., which are possibly related after dislocation generated based on normal sound parameters.
In the implementation of the application, corresponding sound data are acquired when the dislocation of the ladle joint can occur after the patient takes out the imbedded object. The difference between the abnormal sound data and the dislocation simulation data can be identified for subsequent use by comparing the abnormal sound data and the dislocation simulation data. According to the technical scheme, the voice recognition scheme independent of the convolutional neural network is provided, the required calculation force is small, and the voice recognition scheme is very suitable for mobile terminals; meanwhile, as the identification mode is to extract parameters through normal sound of the same patient, the accuracy of final identification can be effectively improved.
In one possible implementation, collecting sound data of a target patient before an object that may cause dislocation of the ladle joint is not placed as normal sound data includes:
collecting the sound of a target patient in making a first vowel as first normal data, and collecting the sound of the target patient in making a second vowel as second normal data; the first tone uses a and the second tone uses u.
When the embodiment of the application is implemented, in order to accurately acquire the sound data of a target patient, two vowels are required to be acquired; the two vowels are preferably a and u, and when the vowels are pronouncing, the corresponding vocal cord states of the two vowels are greatly different, so that better differential recognition in subsequent recognition can be given, and the recognition accuracy is provided.
In one possible implementation, performing audio analysis on the normal sound data to obtain a normal sound parameter includes:
performing audio analysis on the first normal data to obtain a first fundamental tone frequency corresponding to the first normal data; and performing audio analysis on the second normal data to obtain a second fundamental tone frequency corresponding to the second normal data.
When the embodiment of the application is implemented, the audio analysis technology in the prior art can be adopted to carry out data analysis on the normal sound data so as to calculate the fundamental frequency.
In one possible implementation, the dislocation simulation model includes a normal model and a dislocation model;
the generating of the normal model comprises the following steps:
establishing an acoustic ligament fluid mechanics model; the acoustic ligament fluid mechanical model comprises a left ligament and a right ligament, and vibration parameters of the left ligament and the right ligament are adjustable;
adjusting vibration parameters of the left and right ligaments in the acoustic ligament fluid mechanical model and calculating as calculated pitch frequencies generated when airflow passes through the left and right ligaments;
and establishing a first simulated sound function as the normal model according to the corresponding relation between the calculated fundamental tone frequency and the corresponding vibration parameter.
In the implementation of the embodiment of the application, in order to perform more data simulation analysis, the analysis of sound data is converted into fluid analysis, namely, the acoustic ligaments on two sides are simulated through an acoustic ligament fluid mechanics model. Wherein the vibration parameters of the acoustic ligament can be adjusted by adjusting the opening and closing angle of the acoustic ligament and the parameters of the acoustic ligament. By adjusting the vibration parameters and performing simulated calculation of airflow through the vocal ligaments, the vibration frequency of the vocal ligaments can be calculated, thereby further calculating the pitch frequency and generating a first simulated sound function.
In one possible implementation, the generating of the dislocation model includes:
adjusting vibration constraints of the left and right ligaments in the acoustic ligament hydrodynamic model and calculating a pitch frequency generated when different air flows pass through the left and right ligaments as an dislocated pitch frequency;
and establishing a second simulated sound function as the dislocation model according to the dislocation fundamental tone frequency, the corresponding relation between the vibration parameter and the corresponding vibration constraint condition.
When the embodiment of the application is implemented, because different people have different pronunciation habits when making pronunciation and the vocal cords have larger difference, the embodiment of the application converts the problem of sounding into the problem of fluid vibration to solve the problem of sounding. In the simulation calculation of the dislocation model, dislocation simulation is performed by adjusting vibration constraint of the acoustic ligament, that is, relaxing the constraint. It should be appreciated that the constraint may be relaxed by either the vocal ligaments on one side or both sides. Under the condition that constraint is relaxed, the vibration condition of the vocal cords becomes complex, and besides the vibration of the vocal cords, the vibration of the vocal cords accompanied by the constraint is possible, and at the moment, the change of the air flow can influence the pitch frequency, so that different air flows are required to be used for simulation experiments to obtain the dislocation pitch frequency. It should be understood that the second pseudo-sound function is a four-parameter function, i.e. the airflow parameter, the dislocation pitch frequency, the corresponding vibration parameter and the corresponding vibration constraint, which is different from the first pseudo-sound function; the second simulated sound function may be a function group, that is, each function in the function group corresponds to an airflow parameter.
In one possible implementation manner, inputting the normal sound parameter into an dislocation simulation model, and generating dislocation simulation data corresponding to a plurality of different dislocation situations includes:
selecting a vibration parameter interval corresponding to an interval between the first fundamental tone frequency and the second fundamental tone frequency from the first simulated voice function according to the first fundamental tone frequency and the second fundamental tone frequency;
selecting a plurality of groups of corresponding relations between the dislocation fundamental tone frequency corresponding to the vibration parameter interval and the corresponding vibration constraint conditions from the second simulated sound function according to the vibration parameter interval as dislocation simulated data; each set of correspondence corresponds to a different airflow through the left and right ligaments.
When the embodiment of the application is implemented, because the voicing modes corresponding to the vowels a and u have larger difference, the possible vibration parameter interval can be screened out from the first simulated voicing function according to the first fundamental tone frequency and the second fundamental tone frequency. And selecting vibration constraint conditions corresponding to different airflow parameters from the second simulated sound function through the vibration parameter interval selected through the screen, and forming a new function group as dislocation simulated data by directly correlating dislocation fundamental tone frequency.
In one possible implementation, the abnormal sound data includes first abnormal data corresponding to a first vowel and second abnormal data corresponding to a second vowel;
comparing the abnormal sound data with the dislocation simulation data, and taking a comparison result as an identification result to comprise:
inputting the first abnormal data and the second abnormal data into a plurality of groups of corresponding relations in the dislocation simulation data, and obtaining a plurality of first output results corresponding to the first abnormal data and a plurality of second output results corresponding to the second abnormal data;
and selecting the nearest output result from the first output result and the second output result as the identification result.
When the embodiment of the application is implemented, in the specific comparison process, the first abnormal data and the second abnormal data are the fundamental frequency, the two abnormal data are respectively input into the function group of the dislocation simulation data, and the vibration constraint conditions corresponding to different air flows can be calculated as output results, namely, a first output result corresponding to the first abnormal data and a second output result corresponding to the second abnormal data; since the dislocation of the ladle joint should be consistent for the same target patient, the nearest output result of the first output result and the second output result can be selected as the final recognition result. It should be understood that, for different people, the vocal cords and speaking modes are different, and even when the same syllable is sent out, the air output is greatly different, so in the embodiment of the application, the recognition accuracy can be effectively improved by converting voice recognition into a fluid calculation mode. Meanwhile, for human voice, the sound production process is generated by joint vibration of the sound channel and the nasal cavity, and the change of the sound channel also brings the change of sound noise, so that the problem is difficult to overcome by common neural network learning, namely the vibration generated by the change of the sound channel cannot be avoided. After the problem is converted into the fluid problem, the embodiment of the application can start with the fundamental tone frequency to perform basic analysis of the vocal cord structure, thereby determining the final identification data. The identification data may be characterized as vibration constraints for subsequent use.
In order to facilitate the description of the above-mentioned voice spectrum identification system for suspected cyprocollex joint dislocation, please refer to fig. 2, a schematic communication architecture diagram of the voice spectrum identification system for suspected cyprocollex joint dislocation disclosed in the embodiment of the present application is provided. Wherein, suspected ladle joint dislocation voice frequency spectrum identification system includes:
a first acquisition module configured to acquire sound data of a target patient before an object that may cause dislocation of an arytenoid joint is placed therein as normal sound data;
the analysis module is configured to perform audio analysis on the normal sound data to obtain normal sound parameters;
the dislocation simulation module is configured to input the normal sound parameters into a dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions;
the second acquisition module is configured to acquire sound data of a target patient after the target patient takes out the embedded object as abnormal sound data;
and the comparison module is configured to compare the abnormal sound data with the dislocation simulation data and take the comparison result as a recognition result.
When the embodiment of the application is implemented, the first acquisition module and the second acquisition module can use the same acquisition module, in particular, the same sound acquisition module of a mobile phone or a tablet personal computer can be used, and the analysis module, the dislocation simulation module and the comparison module can adopt the CPU of the mobile phone or the tablet personal computer, and can also adopt a remote server.
In one possible implementation, the first acquisition module is further configured to:
collecting the sound of a target patient in making a first vowel as first normal data, and collecting the sound of the target patient in making a second vowel as second normal data; the first tone uses a and the second tone uses u.
In one possible implementation, the analysis module is further configured to:
performing audio analysis on the first normal data to obtain a first fundamental tone frequency corresponding to the first normal data; and performing audio analysis on the second normal data to obtain a second fundamental tone frequency corresponding to the second normal data.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The elements described as separate components may or may not be physically separate, and it will be apparent to those skilled in the art that elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the elements and steps of the examples have been generally described functionally in the foregoing description so as to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a grid device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. A method for voice-frequency spectrum identification of a suspected bowl dislocation, comprising:
collecting sound data of a target patient before an object possibly causing dislocation of the ladle joint is placed in the target patient as normal sound data;
performing audio analysis on the normal sound data to obtain normal sound parameters;
inputting the normal sound parameters into an dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions;
collecting sound data of a target patient after taking out an embedded object as abnormal sound data;
and comparing the abnormal sound data with the dislocation simulation data, and taking a comparison result as a recognition result.
2. The method for identifying a suspected bowl-shaped dislocation of a joint as a voice spectrum according to claim 1, wherein collecting voice data of a target patient before an object that may cause the bowl-shaped dislocation is not placed as normal voice data comprises:
collecting the sound of a target patient in making a first vowel as first normal data, and collecting the sound of the target patient in making a second vowel as second normal data; the first tone uses a and the second tone uses u.
3. The method for identifying a suspected cyprocoytenoid dislocation voice spectrum according to claim 2, wherein the audio analysis of the normal voice data to obtain normal voice parameters comprises:
performing audio analysis on the first normal data to obtain a first fundamental tone frequency corresponding to the first normal data; and performing audio analysis on the second normal data to obtain a second fundamental tone frequency corresponding to the second normal data.
4. The method for voice-frequency spectrum identification of a suspected cyprocoytenoid dislocation according to claim 3, wherein the dislocation simulation model comprises a normal model and a dislocation model;
the generating of the normal model comprises the following steps:
establishing an acoustic ligament fluid mechanics model; the acoustic ligament fluid mechanical model comprises a left ligament and a right ligament, and vibration parameters of the left ligament and the right ligament are adjustable;
adjusting vibration parameters of the left ligament and the right ligament in the acoustic ligament fluid mechanical model, and calculating a pitch frequency generated when airflow passes through the left ligament and the right ligament as the calculated pitch frequency;
and establishing a first simulated sound function as the normal model according to the corresponding relation between the calculated fundamental tone frequency and the corresponding vibration parameter.
5. The method for voice-frequency spectrum identification of a suspected cyprocoytenoid dislocation of claim 4 wherein the generation of the dislocation model comprises:
adjusting vibration constraints of the left and right ligaments in the acoustic ligament hydrodynamic model and calculating a pitch frequency generated when different air flows pass through the left and right ligaments as an dislocated pitch frequency;
and establishing a second simulated sound function as the dislocation model according to the dislocation fundamental tone frequency, the corresponding relation between the vibration parameter and the corresponding vibration constraint condition.
6. The method for identifying a suspected ladle joint dislocation voice spectrum as recited in claim 5, wherein inputting the normal voice parameters into a dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions comprises:
selecting a vibration parameter interval corresponding to an interval between the first fundamental tone frequency and the second fundamental tone frequency from the first simulated voice function according to the first fundamental tone frequency and the second fundamental tone frequency;
selecting a plurality of groups of corresponding relations between the dislocation fundamental tone frequency corresponding to the vibration parameter interval and the corresponding vibration constraint conditions from the second simulated sound function according to the vibration parameter interval as dislocation simulated data; each set of correspondence corresponds to a different airflow through the left and right ligaments.
7. The method for identifying a suspected cyprocoytenoid dislocation voice spectrum according to claim 6, wherein the abnormal voice data includes first abnormal data corresponding to a first vowel and second abnormal data corresponding to a second vowel;
comparing the abnormal sound data with the dislocation simulation data, and taking a comparison result as an identification result to comprise:
inputting the first abnormal data and the second abnormal data into a plurality of groups of corresponding relations in the dislocation simulation data, and obtaining a plurality of first output results corresponding to the first abnormal data and a plurality of second output results corresponding to the second abnormal data;
and selecting the nearest output result from the first output result and the second output result as the identification result.
8. A suspected cyprocoytenoid dislocation voice spectrum recognition system using the method of any one of claims 1-7, comprising:
a first acquisition module configured to acquire sound data of a target patient before an object that may cause dislocation of an arytenoid joint is placed therein as normal sound data;
the analysis module is configured to perform audio analysis on the normal sound data to obtain normal sound parameters;
the dislocation simulation module is configured to input the normal sound parameters into a dislocation simulation model to generate dislocation simulation data corresponding to a plurality of different dislocation conditions;
the second acquisition module is configured to acquire sound data of a target patient after the target patient takes out the embedded object as abnormal sound data;
and the comparison module is configured to compare the abnormal sound data with the dislocation simulation data and take the comparison result as a recognition result.
9. The suspected cyprocoytenoid dislocation voice-spectrum recognition system of claim 8, wherein the first acquisition module is further configured to:
collecting the sound of a target patient in making a first vowel as first normal data, and collecting the sound of the target patient in making a second vowel as second normal data; the first tone uses a and the second tone uses u.
10. The suspected cyprocoytenoid dislocation voice-spectrum recognition system of claim 9, wherein the analysis module is further configured to:
performing audio analysis on the first normal data to obtain a first fundamental tone frequency corresponding to the first normal data; and performing audio analysis on the second normal data to obtain a second fundamental tone frequency corresponding to the second normal data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310736117.5A CN116473521B (en) | 2023-06-21 | 2023-06-21 | Voice frequency spectrum identification method and system for suspected cyprocoytenoid dislocation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310736117.5A CN116473521B (en) | 2023-06-21 | 2023-06-21 | Voice frequency spectrum identification method and system for suspected cyprocoytenoid dislocation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116473521A CN116473521A (en) | 2023-07-25 |
| CN116473521B true CN116473521B (en) | 2023-08-18 |
Family
ID=87227205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310736117.5A Active CN116473521B (en) | 2023-06-21 | 2023-06-21 | Voice frequency spectrum identification method and system for suspected cyprocoytenoid dislocation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116473521B (en) |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0841800A2 (en) * | 1996-11-11 | 1998-05-13 | Instromedix, Inc. | Concurrent medical patient data and voice communication method and apparatus |
| JP2005091727A (en) * | 2003-09-17 | 2005-04-07 | Advanced Telecommunication Research Institute International | Program, apparatus, and method for speech synthesis |
| CN1875877A (en) * | 2006-05-15 | 2006-12-13 | 西安交通大学 | A method for obtaining subglottic pressure value and calculating phonation efficiency |
| RU2010114985A (en) * | 2010-04-14 | 2011-10-20 | Государственное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный медицинский | METHOD FOR ENDOSCOPIC MEDIALIZATION OF PARALIZED VOICE FOLDING |
| CN202198940U (en) * | 2010-04-21 | 2012-04-25 | 邱春元 | Device and system for endotracheal intubation |
| WO2013057637A1 (en) * | 2011-10-20 | 2013-04-25 | Koninklijke Philips Electronics N.V. | A system and method for characterizing an upper airway using speech characteristics |
| CN103093759A (en) * | 2013-01-16 | 2013-05-08 | 东北大学 | Device and method of voice detection and evaluation based on mobile terminal |
| CN103519785A (en) * | 2013-09-24 | 2014-01-22 | 泰亿格电子（上海）有限公司 | Multi-dimensional voice disorder measuring system based on multi-dimensional real-time voice modeling and method thereof |
| JP2014130227A (en) * | 2012-12-28 | 2014-07-10 | Mie Univ | Phonation evaluation device, phonation evaluation method and program |
| WO2014178749A1 (en) * | 2013-04-29 | 2014-11-06 | Общество С Ограниченной Ответственностью "Эм Ди Войс" | Method for determining an individual's risk of developing disorders on the basis of the individual's voice, and hardware and software system for implementing same |
| CA2931662A1 (en) * | 2015-11-03 | 2017-05-03 | University Health Network | Acoustic upper airway assessment system and method, and sleep apnea assessment system and method relying thereon |
| CN106999143A (en) * | 2014-12-12 | 2017-08-01 | 皇家飞利浦有限公司 | acoustic monitoring system, monitoring method and monitoring computer program |
| CN108053470A (en) * | 2017-12-28 | 2018-05-18 | 昆明医科大学第附属医院 | One kind is based on MRI difficult airways three-dimensional rebuilding method and application |
| CN110074759A (en) * | 2019-04-23 | 2019-08-02 | 平安科技（深圳）有限公司 | Voice data aided diagnosis method, device, computer equipment and storage medium |
| CN110831497A (en) * | 2017-05-05 | 2020-02-21 | 瑞思迈私人有限公司 | Screening, diagnosis and monitoring of respiratory disorders |
| CN111420208A (en) * | 2009-04-02 | 2020-07-17 | 呼吸科技公司 | Methods, systems and apparatus for non-invasive open ventilation using a gas delivery nozzle within an outer tube |
| CN111816278A (en) * | 2020-06-17 | 2020-10-23 | 成都慢乐科技有限公司 | System and method for simulating treatment process and analyzing compliance through augmented reality |
| CN112294253A (en) * | 2019-07-26 | 2021-02-02 | 深圳百诺明医说科技有限公司 | Disease diagnosis system based on user voice change and household intelligent robot |
| CN212729838U (en) * | 2020-04-13 | 2021-03-19 | 中国人民解放军海军特色医学中心 | Monitor and monitor system |
| CN112562650A (en) * | 2020-10-31 | 2021-03-26 | 苏州大学 | Voice recognition classification method based on vocal cord characteristic parameters |
| CN213283303U (en) * | 2020-09-04 | 2021-05-28 | 四川大学华西医院 | Ring-bail joint resetting forceps |
| EP3875034A1 (en) * | 2020-03-03 | 2021-09-08 | Cordio Medical Ltd. | Diagnosis of medical conditions using voice recordings and auscultation |
| CN114664325A (en) * | 2020-12-24 | 2022-06-24 | 沈阳新松机器人自动化股份有限公司 | Abnormal sound identification method, system, terminal equipment and computer readable storage medium |
| CN115211873A (en) * | 2022-07-18 | 2022-10-21 | 首都医科大学附属北京同仁医院 | Arytenoid cartilage movement regulation system and method based on laryngeal muscle electrical signals |
| WO2023047391A1 (en) * | 2022-10-19 | 2023-03-30 | Rezaee Mehdi | Endotracheal tube with interior multi-layered sputum-collecting sheath |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8394031B2 (en) * | 2000-10-06 | 2013-03-12 | Biomedical Acoustic Research, Corp. | Acoustic detection of endotracheal tube location |
| US20080300867A1 (en) * | 2007-06-03 | 2008-12-04 | Yan Yuling | System and method of analyzing voice via visual and acoustic data |
| US9589107B2 (en) * | 2014-11-17 | 2017-03-07 | Elwha Llc | Monitoring treatment compliance using speech patterns passively captured from a patient environment |
| US20220346725A1 (en) * | 2021-04-30 | 2022-11-03 | Medtronic, Inc. | Voice-assisted acute health event monitoring |
-
2023
- 2023-06-21 CN CN202310736117.5A patent/CN116473521B/en active Active
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0841800A2 (en) * | 1996-11-11 | 1998-05-13 | Instromedix, Inc. | Concurrent medical patient data and voice communication method and apparatus |
| JP2005091727A (en) * | 2003-09-17 | 2005-04-07 | Advanced Telecommunication Research Institute International | Program, apparatus, and method for speech synthesis |
| CN1875877A (en) * | 2006-05-15 | 2006-12-13 | 西安交通大学 | A method for obtaining subglottic pressure value and calculating phonation efficiency |
| CN111420208A (en) * | 2009-04-02 | 2020-07-17 | 呼吸科技公司 | Methods, systems and apparatus for non-invasive open ventilation using a gas delivery nozzle within an outer tube |
| RU2010114985A (en) * | 2010-04-14 | 2011-10-20 | Государственное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный медицинский | METHOD FOR ENDOSCOPIC MEDIALIZATION OF PARALIZED VOICE FOLDING |
| CN202198940U (en) * | 2010-04-21 | 2012-04-25 | 邱春元 | Device and system for endotracheal intubation |
| WO2013057637A1 (en) * | 2011-10-20 | 2013-04-25 | Koninklijke Philips Electronics N.V. | A system and method for characterizing an upper airway using speech characteristics |
| JP2014130227A (en) * | 2012-12-28 | 2014-07-10 | Mie Univ | Phonation evaluation device, phonation evaluation method and program |
| CN103093759A (en) * | 2013-01-16 | 2013-05-08 | 东北大学 | Device and method of voice detection and evaluation based on mobile terminal |
| WO2014178749A1 (en) * | 2013-04-29 | 2014-11-06 | Общество С Ограниченной Ответственностью "Эм Ди Войс" | Method for determining an individual's risk of developing disorders on the basis of the individual's voice, and hardware and software system for implementing same |
| CN103519785A (en) * | 2013-09-24 | 2014-01-22 | 泰亿格电子（上海）有限公司 | Multi-dimensional voice disorder measuring system based on multi-dimensional real-time voice modeling and method thereof |
| CN106999143A (en) * | 2014-12-12 | 2017-08-01 | 皇家飞利浦有限公司 | acoustic monitoring system, monitoring method and monitoring computer program |
| CA2931662A1 (en) * | 2015-11-03 | 2017-05-03 | University Health Network | Acoustic upper airway assessment system and method, and sleep apnea assessment system and method relying thereon |
| CN110831497A (en) * | 2017-05-05 | 2020-02-21 | 瑞思迈私人有限公司 | Screening, diagnosis and monitoring of respiratory disorders |
| CN108053470A (en) * | 2017-12-28 | 2018-05-18 | 昆明医科大学第附属医院 | One kind is based on MRI difficult airways three-dimensional rebuilding method and application |
| CN110074759A (en) * | 2019-04-23 | 2019-08-02 | 平安科技（深圳）有限公司 | Voice data aided diagnosis method, device, computer equipment and storage medium |
| CN112294253A (en) * | 2019-07-26 | 2021-02-02 | 深圳百诺明医说科技有限公司 | Disease diagnosis system based on user voice change and household intelligent robot |
| EP3875034A1 (en) * | 2020-03-03 | 2021-09-08 | Cordio Medical Ltd. | Diagnosis of medical conditions using voice recordings and auscultation |
| CN212729838U (en) * | 2020-04-13 | 2021-03-19 | 中国人民解放军海军特色医学中心 | Monitor and monitor system |
| CN111816278A (en) * | 2020-06-17 | 2020-10-23 | 成都慢乐科技有限公司 | System and method for simulating treatment process and analyzing compliance through augmented reality |
| CN213283303U (en) * | 2020-09-04 | 2021-05-28 | 四川大学华西医院 | Ring-bail joint resetting forceps |
| CN112562650A (en) * | 2020-10-31 | 2021-03-26 | 苏州大学 | Voice recognition classification method based on vocal cord characteristic parameters |
| CN114664325A (en) * | 2020-12-24 | 2022-06-24 | 沈阳新松机器人自动化股份有限公司 | Abnormal sound identification method, system, terminal equipment and computer readable storage medium |
| CN115211873A (en) * | 2022-07-18 | 2022-10-21 | 首都医科大学附属北京同仁医院 | Arytenoid cartilage movement regulation system and method based on laryngeal muscle electrical signals |
| WO2023047391A1 (en) * | 2022-10-19 | 2023-03-30 | Rezaee Mehdi | Endotracheal tube with interior multi-layered sputum-collecting sheath |
Non-Patent Citations (1)
| Title |
|---|
| 声谱图在喉科的临床应用;王明方, 常捷燕, 李宁;《中国医疗前沿》(第12期);6-7 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116473521A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Flanagan | Speech analysis synthesis and perception | |
| Cernak et al. | Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features | |
| Patel et al. | Speech recognition and verification using MFCC & VQ | |
| Tran et al. | Improvement to a NAM-captured whisper-to-speech system | |
| Baghai-Ravary et al. | Automatic speech signal analysis for clinical diagnosis and assessment of speech disorders | |
| US20160314781A1 (en) | Computer-implemented method, computer system and computer program product for automatic transformation of myoelectric signals into audible speech | |
| JP2000504849A (en) | Speech coding, reconstruction and recognition using acoustics and electromagnetic waves | |
| AU2013274940B2 (en) | Cepstral separation difference | |
| Lulich et al. | Subglottal resonances of adult male and female native speakers of American English | |
| Borsky et al. | Modal and nonmodal voice quality classification using acoustic and electroglottographic features | |
| Wand et al. | The EMG-UKA corpus for electromyographic speech processing. | |
| CN109727608A (en) | A kind of ill voice appraisal procedure based on Chinese speech | |
| Kadiri et al. | Analysis and Detection of Phonation Modes in Singing Voice using Excitation Source Features and Single Frequency Filtering Cepstral Coefficients (SFFCC). | |
| El Emary et al. | Towards developing a voice pathologies detection system | |
| KR20230017135A (en) | Difficult airway evaluation method and device based on machine learning voice technology | |
| CN113496696A (en) | Speech function automatic evaluation system and method based on voice recognition | |
| Usman | On the performance degradation of speaker recognition system due to variation in speech characteristics caused by physiological changes | |
| Liao | An acoustic study of vowels produced by alaryngeal speakers in Taiwan | |
| CN116473521B (en) | Voice frequency spectrum identification method and system for suspected cyprocoytenoid dislocation | |
| Rodriguez et al. | A fuzzy information space approach to speech signal non‐linear analysis | |
| Salas | Acoustic coupling in phonation and its effect on inverse filtering of oral airflow and neck surface acceleration | |
| Sharifzadeh | Reconstruction of natural sounding speech from whispers | |
| CN106782616A (en) | A kind of method that respiratory tract is detected by voice analysis | |
| CN113129923A (en) | Multi-dimensional singing playing analysis evaluation method and system in art evaluation | |
| Gonzalez et al. | Direct Speech Generation for a Silent Speech Interface based on Permanent Magnet Articulography. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Qian Yongjun Inventor after: Jiang Wen Inventor after: Li Ning Inventor after: Wang Zhengjie Inventor after: Tong Qi Inventor after: Sun Yiren Inventor after: Yang Ziqi Inventor after: Xu Qiyue Inventor before: Qian Yongjun Inventor before: Jiang Wen Inventor before: Li Ning Inventor before: Wang Zhengjie Inventor before: Tong Qi Inventor before: Sun Yiren Inventor before: Yang Ziqi Inventor before: Xu Qiyue |