Remote teaching method and system for music education

Abstract

The invention relates to the technical field of music education, in particular to a remote teaching method and system for music education, and the method comprises the following steps: separating the frequency, amplitude and duration information of an audio signal based on an audio data stream played by a student, and recognizing the duration of each note and the deviation standard of pitch; the audio signals deviating from the normal range are screened, and then the duration time and the intensity characteristic of the signals are calculated to obtain an audio characteristic deviation value; according to the invention, through deep analysis of the audio data, accurate capture of playing skill details of students is realized, individuation and accuracy of teaching are improved, deviation analysis and dynamic monitoring of notes are emphasized, teachers are allowed to carry out instant teaching adjustment according to data analyzed in real time, interactivity and adaptability of music education are enhanced, and teaching experience is improved. Therefore, the education process better meets individual demands of students, and specific weaknesses of the students in music execution can be identified through comprehensive utilization of audio signal processing and time sequence analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of music education, and in particular to a remote teaching method and system for music education. Background Art

[0002] Music education technology involves the use of technological tools and resources to enhance the effectiveness and accessibility of music learning, including the use of various software, applications, digital music tools and online platforms to teach music theory, vocal music, instrumental performance and music creation. With the development of technology, virtual instruments, music production software and online collaboration platforms enable students to create and perform music in remote environments, whether for individual learning or group collaboration.

[0003] Among them, the distance teaching method used for music education focuses on how to effectively impart music education through distance teaching technology. The purpose is to make music education more popular through the Internet and digital technology, break the limitations of traditional classrooms, and allow teachers and students to interact and learn anywhere in the world. Using this method, teachers can use video conferencing, online course platforms, virtual musical instruments, and interactive software tools for teaching, so that students can receive professional music education even if they are in different geographical locations.

[0004] Existing technologies ignore the in-depth attention to students' individual learning differences and the dynamic changes in their performance skills. Most of them focus on providing general virtual instruments and online courses. They lack the function of continuously monitoring students' performance quality, which limits the personalized adjustment and instant feedback of teaching. The lack of the function of detailed analysis of music performance makes it difficult for teachers to respond quickly to students' specific needs and to accurately measure the effectiveness of teaching strategies. In addition, existing technologies fail to effectively use students' performance data to optimize teaching plans, resulting in insufficient response time and personalization of teaching activities, and unable to give full play to the potential of distance learning technology. These defects slow down students' learning progress and the improvement of teaching quality. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a remote teaching method and system for music education.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a remote teaching method for music education, comprising the following steps:

[0007] S1: Based on the audio data stream of the student's performance, separate the frequency, amplitude and duration information of the audio signal, identify the deviation of the duration and pitch of each note, and filter out the audio signals that deviate from the normal range, and then calculate the duration and intensity characteristics of the signal to obtain the audio feature offset value;

[0008] S2: Based on the audio feature offset value, select parameters for comparison with standard music performance, analyze the pitch, rhythm and dynamic deviation of the notes, classify and identify the deviation features, determine the error types of pitch error, inaccurate rhythm or dynamic loss of control, and obtain a music execution error classification table;

[0009] S3: Based on the music execution error classification table, a two-way audio and video synchronization channel is established using WebRTC technology to transmit student performance data and teacher guidance information in real time, and the frequency and intensity of errors in the student performance data are analyzed to obtain teaching feedback synchronization data;

[0010] S4: Based on the teaching feedback synchronization data, analyze the time series data related to the students' performance skills, identify the skill items that differ from the standard teaching skill performance, and calculate the improvement space of the skill items. Then, adjust the teaching content and direction in combination with the teaching objectives to obtain an overview of the music teaching adjustment.

[0011] The present invention is improved in that the step of identifying the deviation of the duration and pitch of the note from the standard is specifically as follows:

[0012] S111: extracting a single note signal based on the audio data stream played by the student, segmenting the audio stream using a window function, isolating the individual notes, and obtaining segmented note signals;

[0013] S112: Performing Fourier transform on the segmented note signal to calculate the basic frequency and amplitude of each note to obtain the frequency-amplitude characteristics of the note;

[0014] S113: Based on the frequency amplitude characteristics of the note, the deviation of each note frequency from the standard frequency is calculated using the formula:

[0015]

[0016] and

[0017] T=t end -t start ;

[0018] The duration and pitch deviation of the note are obtained, where Δf represents the frequency deviation ratio, T represents the duration of the note, f represents the currently measured note frequency, and f std Represents the standard frequency of the note, t start is the start time of the note, t end is the end time of the note.

[0019] The present invention is improved in that the step of obtaining the audio feature offset value is specifically as follows:

[0020] S121: based on the deviation standards of the duration and pitch of the notes, filter the audio signals that deviate from the normal frequency range or intensity threshold to obtain a list of abnormal audio signals;

[0021] S122: Based on the abnormal audio signal list, calculate the duration and intensity of each signal using the formula:

[0022]

[0023] Evaluate the degree of deviation of the audio signal and obtain the audio feature deviation value ERD, where T i represents the duration of the i-th abnormal audio signal, I i represents the strength of the i-th abnormal audio signal, w T and w I is the weight coefficient of duration and intensity, and N is the total number of abnormal signals.

[0024] The present invention is improved in that the steps of analyzing the pitch, rhythm and dynamic deviation of the note are specifically as follows:

[0025] S211: Based on the audio feature offset value, the pitch, rhythm and dynamic data of each note are collected, compared with the standard music performance parameters, the note deviation data are determined, and a preliminary deviation data list is obtained;

[0026] S212: Based on the preliminary deviation data list, the pitch, rhythm and dynamic data of the note are analyzed using the formula:

[0027]

[0028] Get the deviation analysis results, where a h 、a r and a d Represents the weight coefficient of pitch, rhythm and dynamic deviation, Δh i is the pitch deviation of the ith note, Δr i is the rhythmic deviation of the ith note, Δd i is the dynamic deviation of the ith note, N G Total number of notes.

[0029] The present invention is improved in that the steps of obtaining the music execution error classification table are specifically as follows:

[0030] S221: Classifying and identifying the deviation features of each note, determining whether the note has a pitch error, an inaccurate rhythm, or a dynamic out-of-control problem, and obtaining an identified error type;

[0031] S222: Based on the identified error types, the occurrence frequency of each error type is counted to obtain a music execution error classification table.

[0032] The present invention is improved in that the steps of transmitting the student's performance data and the teacher's guidance information are specifically as follows:

[0033] S311: Based on the music execution error classification table, configure the WebRTC technology, establish a two-way audio and video synchronization channel, and verify whether the real-time transmission function of the audio and video data is activated to obtain a real-time audio and video synchronization channel;

[0034] S312: Based on the real-time audio and video synchronization channel, the student performance data and the teacher's guidance information are transmitted in real time, and the transmission process is optimized to obtain an optimized data transmission stream.

[0035] The present invention is improved in that the step of acquiring the teaching feedback synchronization data is specifically as follows:

[0036] S321: Analyze the frequency and intensity of errors in the student's performance data, using the formula:

[0037]

[0038] Calculate the influence of each error type and obtain the preliminary performance error analysis result EA, where fC i represents the frequency of occurrence of the i-th error, IC i represents the strength of the i-th error, wu i Represents the weight coefficient of the i-th error type, N U is the total number of error events;

[0039] S322: Based on the preliminary performance error analysis results, the teacher's real-time feedback data is integrated to obtain teaching feedback synchronization data.

[0040] The present invention is improved in that the steps of obtaining the music teaching adjustment overview are specifically as follows:

[0041] S411: Analyze the time series data associated with the student's performance skills based on the teaching feedback synchronization data, identify the skill items that differ from the standard teaching skill performance, determine the deviation of the skill performance, and obtain a skill deviation log;

[0042] S412: Based on the skill deviation log, the formula is used:

[0043]

[0044] Quantify the improvement space of each skill, calculate the average improvement potential IOP of each skill item, and obtain the improvement space analysis data, where se ti Indicates the target performance of the skill item, se si Indicates the student's performance on the corresponding skill item, Nl Indicates the total number of skill items;

[0045] S413: Based on the improvement space analysis data, the teaching content and direction are adjusted according to the teaching objectives to obtain an overview of the music teaching adjustments.

[0046] A remote teaching system for music education, the system comprising:

[0047] The audio feature module separates the frequency, amplitude and duration information of the audio signal based on the audio data stream of the student's performance, identifies the deviation of the duration and pitch of each note from the standard, calculates the duration and intensity characteristics of the signal, and obtains the audio feature offset value;

[0048] The error analysis module selects parameters for comparison with standard music performance based on the audio feature offset value, analyzes the pitch, rhythm and dynamic deviation of the notes, determines the error types of pitch error, inaccurate rhythm or dynamic loss of control, and obtains a music execution error classification table;

[0049] The synchronous transmission module uses WebRTC technology to establish a two-way audio and video synchronization channel based on the music execution error classification table, transmits student performance data and teacher guidance information in real time, analyzes the frequency and intensity of errors in student performance data, and obtains teaching feedback synchronization data;

[0050] The teaching adjustment module identifies skill items that differ from standard teaching skill performance based on the teaching feedback synchronization data, calculates the improvement space of the skill items, adjusts the teaching content and direction, and obtains an overview of the music teaching adjustment.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are:

[0052] In the present invention, through in-depth analysis of audio data, accurate capture of students' performance skills details is achieved, the personalization and accuracy of teaching are improved, emphasis is placed on deviation analysis and dynamic monitoring of notes, and teachers are allowed to make instant teaching adjustments based on real-time analysis data, thereby enhancing the interactivity and adaptability of music education and making the education process more in line with students' individual needs. By comprehensively utilizing audio signal processing and time series analysis, specific weaknesses of students in music execution can be identified, and teaching content can be tailored for each student. Through real-time data feedback, students' progress and problems can be monitored, thereby more effectively guiding the learning process and optimizing the allocation of educational resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flow chart of a remote teaching method for music education is proposed for the present invention;

[0054] Figure 2A flow chart for identifying deviations from the standard of duration and pitch of a note in the present invention;

[0055] Figure 3 This is a flow chart for obtaining the audio feature offset value in the present invention;

[0056] Figure 4 A flowchart for analyzing the pitch, rhythm and dynamic deviation of a note in the present invention;

[0057] Figure 5 A flowchart for obtaining a music execution error classification table in the present invention;

[0058] Figure 6 The present invention is a flow chart of the transmission of student performance data and teacher's guidance information;

[0059] Figure 7 This is a flow chart for obtaining teaching feedback synchronization data in the present invention;

[0060] Figure 8 It is a flow chart for obtaining an overview of the music teaching adjustment in the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0062] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0063] Example

[0064] See also Figure 1 The present invention provides a technical solution: a remote teaching method for music education, comprising the following steps:

[0065] S1: Based on the audio data stream of the student's performance, separate the frequency, amplitude and duration information of the audio signal, identify the deviation of the duration and pitch of each note, and filter out the audio signals that deviate from the normal range, and then calculate the duration and intensity characteristics of the signal to obtain the audio feature offset value;

[0066] S2: Based on the audio feature offset value, select parameters for comparison with standard music performance, analyze the pitch, rhythm and dynamic deviation of the notes, classify and identify the deviation features, determine the error types of pitch error, inaccurate rhythm or dynamic loss of control, and obtain a music execution error classification table;

[0067] S3: Based on the music execution error classification table, WebRTC technology is used to establish a two-way audio and video synchronization channel to transmit student performance data and teacher guidance information in real time, and analyze the frequency and intensity of errors in student performance data to obtain teaching feedback synchronization data;

[0068] S4: Based on the teaching feedback synchronization data, analyze the time series data related to students' performance skills, identify the skill items that differ from the standard teaching skill performance, and calculate the improvement space of the skill items. Then, adjust the teaching content and direction in combination with the teaching objectives to obtain an overview of the music teaching adjustment.

[0069] The audio feature offset values ​​include frequency variation, amplitude deviation, and time offset. The music execution error classification table specifically includes pitch deviation, beat error, and dynamic range anomaly information. The teaching feedback synchronization data includes error detection data, real-time response indicators, and feedback effectiveness information. The music teaching adjustment overview includes skill improvement indicators, adjusted teaching content, and teaching objective update results.

[0070] See also Figure 2 The specific steps for identifying deviations of note duration and pitch from the standard are:

[0071] S111: extracting a single note signal based on the audio data stream played by the student, segmenting the audio stream using a window function, isolating the individual notes, and obtaining segmented note signals;

[0072] The audio data is stored in the form of a continuous waveform through an audio data acquisition device. The audio waveform file is read using a signal segmentation tool, and the different notes in the overall waveform are preliminarily segmented. The start and end points of the notes are identified based on the amplitude changes of the signal and the energy peak in the time domain, and the note segment range is extracted. The note signal is then segmented using a window function. The window function uses an adjustment formula based on the Hanning window to reduce the signal error caused by frequency domain leakage. Through local sampling of the note signal, the window function sliding processing is gradually completed, the signal of a single note is isolated and the amplitude is normalized, the interference of environmental noise and background signals on the note segment is removed, and the segmented note signal is obtained.

[0073] S112: Perform Fourier transform on the segmented note signals, calculate the basic frequency and amplitude of each note, and obtain the frequency-amplitude characteristics of the note;

[0074] Perform fast Fourier transform to decompose the frequency components and amplitude information in the signal in the form of a spectrum, use the spectrum main frequency positioning method to identify the main frequency of the signal, filter the high-frequency noise that appears in the frequency spectrum, and call the weighted average method to calculate the peak frequency of the signal as the basic frequency of the note. At the same time, according to the amplitude distribution of different frequencies on the frequency spectrum, calculate the amplitude characteristics of the note signal. The amplitude characteristics are solved based on the summation formula of the absolute value of the amplitude, and then the frequency and amplitude calculation results are stored separately to generate the frequency amplitude characteristics of each note.

[0075] S113: Based on the frequency amplitude characteristics of the note, the deviation of each note frequency from the standard frequency is calculated using the formula:

[0076]

[0077] and

[0078] T=t end -t start ;

[0079] The duration and pitch deviation of the note are obtained, where Δf represents the frequency deviation ratio, T represents the duration of the note, and f represents the currently measured note frequency. The Fourier transform is used to obtain f std Represents the standard frequency of a note, which is the frequency that each note should have according to music theory or the tuning standard of an instrument. start is the start time of the note, t end is the end time of the note;

[0080] The measured note frequency f = 440.5Hz, the standard frequency f std =440.0Hz, substitute into the formula get:

[0081]

[0082] Known note start time t start =0.002s, end time t end = 0.620s, substitute into the formula T = t end -t start ,get:

[0083] T = 0.620-0.002 = 0.618;

[0084] The result shows that the calculated frequency deviation ratio is 0.00114 (about 0.114%), which means that the actual frequency of the note is basically consistent with the standard frequency, and the note duration is 0.618s, which can be further compared with the performance rhythm standard to determine the rhythm deviation.

[0085] See also Figure 3 , the specific steps for obtaining the audio feature offset value are:

[0086] S121: based on the deviation standards of the duration and pitch of the notes, filter the audio signals that deviate from the normal frequency range or intensity threshold to obtain a list of abnormal audio signals;

[0087] The frequency and amplitude data of the notes are obtained, and the audio signal is converted into frequency domain data through fast Fourier transform. The main frequency peak is extracted to identify the frequency of the note, and the amplitude information is combined to determine the amplitude characteristics. The data is range-filtered and the frequency range is set to 40Hz to 2000Hz to filter low-frequency and ultra-high-frequency noise signals. At the same time, the signal with an amplitude lower than 20% of the set minimum value is detected and marked as a low-intensity signal. Then each note is compared one by one to filter out the note signals that deviate from the normal range mentioned above and classify them as abnormal signals. All abnormal signals are sorted into a list for subsequent analysis and processing.

[0088] S122: Based on the abnormal audio signal list, calculate the duration and strength of each signal using the formula:

[0089]

[0090] Evaluate the degree of deviation of the audio signal and obtain the audio feature deviation value ERD, where T i represents the duration of the i-th abnormal audio signal, which is directly obtained from the audio signal analysis. i represents the strength of the i-th abnormal audio signal, obtained by analyzing the amplitude or energy of the audio signal, w T and w I is the weight coefficient of duration and intensity, N is the total number of abnormal signals;

[0091] The following data was collected: the total number of abnormal audio signals N = 5, the duration of each abnormal audio signal is T1, T2, T3, T4, T5 = 0.8, 1.2, 0.6, 1.0, 0.9 seconds, and the intensity of each abnormal audio signal is I1, I2, I3, I4, I5 =

[0092] 0.7, 0.6, 0.8, 0.5, 0.9, the weight coefficient of duration and intensity is w T =0.6, w I =0.4;

[0093] The weight w T and w I Substitute into the formula to calculate the offset contribution of each signal:

[0094] ERD1=0.6·0.8+0.4·0.7=0.48+0.28=0.76;

[0095] ERD2 = 0.6 1.2 + 0.4 0.6 = 0.72 + 0.24 = 0.96;

[0096] ERD3 = 0.6 0.6 + 0.4 0.8 = 0.36 + 0.32 = 0.68;

[0097] ERD4=0.6·1.0+0.4·0.5=0.60+0.20=0.80;

[0098] ERD5=0.6·0.9+0.4·0.9=0.54+0.36=0.90;

[0099] Calculate the weighted average deviation of all anomalies:

[0100]

[0101] The result shows that the final audio feature deviation value ERD=0.82 comprehensively reflects the deviation degree of the abnormal audio signal in duration and intensity, and provides a quantitative basis for the subsequent audio signal quality evaluation.

[0102] See also Figure 4 , the analysis steps of the pitch, rhythm and dynamic deviation of the notes are as follows:

[0103] S211: Based on the audio feature offset value, the pitch, rhythm and dynamic data of each note are collected, compared with the standard music performance parameters, the note deviation data is determined, and a preliminary deviation data list is obtained;

[0104] To extract the pitch, rhythm and dynamic data of the notes, firstly, the frequency characteristics of the notes are analyzed to obtain the pitch deviation value, which is calculated as the difference between the actual note frequency and the standard note frequency. At the same time, the time information of the note (start time and end time) is used to analyze the degree of deviation from the standard beat time, so as to obtain the rhythm deviation value, and the dynamic deviation value is calculated by analyzing the amplitude change of the note signal. The above calculation results are organized into the deviation data of the note, including the pitch deviation value, rhythm deviation value and dynamic deviation value, forming a preliminary deviation data list.

[0105] S212: Based on the preliminary deviation data list, the pitch, rhythm and dynamic data of the notes are analyzed using the formula:

[0106]

[0107] Get the deviation analysis results, where a h 、ar and a d Represents the weight coefficient of pitch, rhythm and dynamic deviation, which is used to adjust the influence of each type of deviation in the total deviation calculation, Δh i is the pitch deviation of the i-th note, which represents the difference between the actual pitch of the note and the standard pitch, Δr i is the rhythm deviation of the i-th note, indicating the degree of deviation between the actual rhythm of the note and the standard rhythm, Δd i is the dynamic deviation of the ith note, indicating the deviation between the sound intensity of the note and the predetermined intensity, N G The total number of notes, used to determine the number of notes considered in the deviation analysis;

[0108] The following data was collected, the total number of notes N G =3, bias weight a h =0.6, a r =0.3, a d =0.1, the deviation values ​​are:

[0109] Note 1: Δh1=4, Δr1=0.2, Δd1=0.1;

[0110] Note 2: Δh2=5, Δr2=0.1, Δd2=0.2;

[0111] Note 3: Δh3=3, Δr3=0.15, Δd3=0.12;

[0112] Deviation value for note 1:

[0113]

[0114] DG1=9.6+0.3·0.4472+0.01=9.6+0.1342+0.01=9.7442;

[0115] Deviation value for note 2:

[0116]

[0117] DG2=15+0.3·0.3162+0.02=15+0.0949+0.02=15.1149;

[0118] Deviation value for note 3:

[0119]

[0120] DG3 = 5.4 + 0.3 0.3873 + 0.012 = 5.4 + 0.1162 + 0.012 = 5.5282;

[0121] Add the deviation values ​​of all notes:

[0122] DG=9.7442+15.1149+5.5282=30.3873;

[0123] The results show that when the total number of notes is 3, the result of the comprehensive deviation analysis is DG = 30.3873. This value quantifies the overall deviation of the notes in terms of pitch, rhythm, and dynamics, providing a clear reference for subsequent improvements or classification of music performance.

[0124] See also Figure 5 , the specific steps for obtaining the music execution error classification table are:

[0125] S221: Classify and identify the deviation features of each note, determine whether the note has a pitch error, an inaccurate rhythm, or a dynamic out-of-control problem, and obtain an identified error type;

[0126] First, the pitch, rhythm and dynamic deviation features of the notes are extracted, and the pitch deviation, rhythm deviation time difference and dynamic deviation intensity are compared with the standard threshold item by item. When the pitch deviation exceeds a specific range or the rhythm deviation time exceeds the allowable error range, it is marked as a pitch error or inaccurate rhythm. When the intensity of the dynamic deviation is higher or lower than the standard range, it is marked as dynamic out of control. Finally, the three types of features of each note are combined, and the error type corresponding to each note is determined according to the identification standard to obtain the identified error type.

[0127] S222: Based on the identified error types, counting the occurrence frequency of each error type to obtain a music execution error classification table;

[0128] Count the frequency of occurrence of each error type in the notes. First, summarize the list of identified error types. By counting the number of pitch errors, inaccurate rhythm and dynamic loss of control in the total number of notes, calculate the frequency of each error type and convert it into a percentage. Use the ratio of pitch errors to the total number of notes, the ratio of rhythm errors to the total number of notes, and the ratio of dynamic errors to the total number of notes, record the corresponding percentage results item by item, organize the frequency data into a structured classification table format, and finally get the music execution error classification table.

[0129] See also Figure 6 ,The specific steps for transmitting student performance data and teacher’s guidance information are as follows:

[0130] S311: Based on the music execution error classification table, configure the WebRTC technology, establish a two-way audio and video synchronization channel, and verify whether the real-time transmission function of the audio and video data is activated to obtain a real-time audio and video synchronization channel;

[0131] By calling the relevant parameters for real-time audio and video transmission, WebRTC technology is configured to establish a two-way audio and video synchronization channel. The specific process includes initializing the WebRTC protocol stack configuration, setting the video resolution and frame rate parameters, and calling the system's audio channel transmission configuration module to match the audio sampling rate and bit rate requirements. At the same time, the frame loss rate and delay rate of the video signal are tested. By determining whether the real-time threshold is met and making corrections and optimizations, the synchronization of the audio and video transmission function is finally verified, the channel status is confirmed and the settings are completed to obtain a real-time audio and video synchronization channel.

[0132] S312: Based on the real-time audio and video synchronization channel, the student performance data and the teacher's guidance information are transmitted in real time, and the transmission process is optimized to obtain an optimized data transmission stream;

[0133] The audio signal collected by the student end is processed for noise reduction and frame encapsulation, and the data is converted into a data packet format suitable for transmission. The transmission channel is called to send it in real time. The teacher end receives the data in real time and decodes it. The timestamps of the audio and video signals are proofread according to the audio and video synchronization transmission protocol. The feedback content of the teacher end is packaged again and transmitted back to the student end in combination with the performance information and the teacher's feedback guidance text. Finally, the delay of the two-way transmission process is recorded and the synchronization parameters are optimized to obtain the optimized data transmission stream.

[0134] See also Figure 7 ,The specific steps for obtaining teaching feedback synchronization data are:

[0135] S321: Analyze the frequency and intensity of errors in the student's performance data using the formula:

[0136]

[0137] Calculate the influence of each error type and obtain the preliminary performance error analysis result EA, where fC i represents the frequency of the ith error, that is, the ratio of the number of times this type of error occurs during the performance to the total performance time or performance event. IC i represents the intensity of the ith error, that is, the prominence of the error in the performance or the severity mentioned in the teacher's feedback, wu i Represents the weight coefficient of the i-th error type, N U is the total number of error events;

[0138] The following data was collected, the total number of error events N U =2, error occurrence frequency fC1=0.3, fC2=0.2, error intensity IC1=6, IC2=4, weight coefficient wu1=0.5, wu2=0.5.

[0139] For the first error type:

[0140] EA1=wu1·(fC1×IC1)=0.5·(0.3×6)=0.5·1.8=0.9;

[0141] For the second error type:

[0142] EA2=wu2·(fC2×IC2)=0.5·(0.2×4)=0.5·0.8=0.4;

[0143] Calculate the total error impact EA:

[0144] EA = 0.9 + 0.4 = 1.3;

[0145] The results show that the total influence of performance errors calculated comprehensively is 1.3, which represents the quantitative impact of errors in the overall performance data, and provides a key reference for subsequent data analysis integrating teacher feedback.

[0146] S322: Based on the preliminary performance error analysis results, the teacher's real-time feedback data is integrated to obtain teaching feedback synchronization data;

[0147] The influence value of each error type in the error analysis results is integrated with the teacher's real-time feedback data, and the scoring items related to the specific error types in the teacher's feedback are extracted, including accuracy scores, rhythm scores, and dynamic scores. The teacher's scoring data is mapped to the error types in the preliminary error analysis results one by one, and the influence of each error type is weighted and adjusted based on the mapping relationship. The weighted adjusted comprehensive scoring results are used as a unified feedback reference value, and the adjusted data are organized into a hierarchical feedback table. Based on the hierarchical table, the teaching guidance information template is further summarized and synchronized to the feedback channel, and finally the teaching feedback synchronization data is generated.

[0148] See also Figure 8 , the specific steps for obtaining the overview of music teaching adjustments are:

[0149] S411: Analyze the time series data related to the student's performance skills based on the teaching feedback synchronization data, identify the skill items that differ from the standard teaching skill performance, determine the deviation of the skill performance, and obtain the skill deviation log;

[0150] The time series data associated with students' playing skills were analyzed, and the time series data were decomposed into performance records corresponding to each skill item. The differences between the skill performance values ​​and the standard teaching performance values ​​at each time point were extracted, and the deviation values ​​of each skill item at different time points were obtained by comparing them one by one. The abnormality of the skill performance was determined according to the size of the deviation value, and the differences of all skill items were annotated according to the time series. The annotated content included the deviation direction, deviation amplitude and deviation level. Finally, all the annotated data were integrated into a structured skill deviation log according to the time point, and the deviation size of the skill performance was determined and recorded.

[0151] S412: Based on the skill deviation log, use the formula:

[0152]

[0153] Quantify the improvement space of each skill, calculate the average improvement potential IOP of each skill item, and obtain the improvement space analysis data, where se ti It indicates the target performance of a skill item, that is, the ideal performance level set according to the teaching standard or goal. si Represents the student's performance on the corresponding skill item, real-time performance data obtained from the teaching feedback synchronization data, N l Indicates the total number of skill items;

[0154] Total number of skill items N l =3, performance se of skill items t1 =8.5, se t2 =7.0, se t3 =9.0, student skill performance se s1 =7.5, se s2 =6.0, se s3 =8.0, calculate the square of the difference for each skill:

[0155] For skill item 1:

[0156] (se t1 -se s1 ) 2 =(8.5-7.5) 2 =1.0;

[0157] For skill item 2:

[0158] (se t2 -se s2 ) 2 =(7.0-6.0) 2 =1.0;

[0159] For skill item 3:

[0160] (se t3-se s3 ) 2 =(9.0-8.0) 2 =1.0;

[0161] Compute the total sum of squares of the differences and find the average:

[0162]

[0163] The results show that the average improvement potential of skill items obtained through comprehensive calculation is 1.0, indicating that there is a certain difference between students’ actual skill performance and target performance, which provides a key reference for the adjustment of subsequent teaching content and direction.

[0164] S413: Based on the improvement space analysis data, adjust the teaching content and direction according to the teaching objectives, and obtain an overview of the music teaching adjustment;

[0165] Determine the priority of teaching adjustment according to the degree of match between the deviation of each skill item and the teaching objective, correspond the improvement potential of the skill item with the various contents in the teaching objective, set a higher priority and more resource allocation ratio for skill items with greater potential, set dynamic teaching content adjustment rules according to the type and difference characteristics of specific skill items, record the specific direction of each adjustment in the teaching adjustment template, and form a systematic teaching content and direction plan by integrating the adjustment contents of all skill items, finally obtaining an overview of music teaching adjustments.

[0166] A remote teaching system for music education, the system comprising:

[0167] The audio feature module separates the frequency, amplitude and duration information of the audio signal based on the audio data stream of the student's performance, identifies the deviation of the duration and pitch of each note from the standard, calculates the duration and intensity characteristics of the signal, and obtains the audio feature offset value;

[0168] The error analysis module selects parameters for comparison with standard music performance based on the audio feature offset value, analyzes the pitch, rhythm and dynamic deviation of the notes, determines the error types of pitch error, inaccurate rhythm or dynamic loss of control, and obtains a music execution error classification table;

[0169] The synchronous transmission module uses WebRTC technology to establish a two-way audio and video synchronization channel based on the music execution error classification table, transmits student performance data and teacher guidance information in real time, analyzes the frequency and intensity of errors in student performance data, and obtains teaching feedback synchronization data;

[0170] The teaching adjustment module is based on teaching feedback synchronization data, identifies skill items that differ from standard teaching skill performance, calculates the room for improvement of skill items, adjusts teaching content and direction, and obtains an overview of music teaching adjustments.

[0171] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A remote teaching method for music education, characterized in that: The following steps are involved: S1: Based on the audio data stream of the student's performance, separate the frequency, amplitude and duration information of the audio signal, identify the deviation of the duration and pitch of each note, and filter out the audio signals that deviate from the normal range, and then calculate the duration and intensity characteristics of the signal to obtain the audio feature offset value; S2: Based on the audio feature offset value, select parameters for comparison with standard music performance, analyze the pitch, rhythm and dynamic deviation of the notes, classify and identify the deviation features, determine the error types of pitch error, inaccurate rhythm or dynamic loss of control, and obtain a music execution error classification table; S3: Based on the music execution error classification table, a two-way audio and video synchronization channel is established using WebRTC technology to transmit student performance data and teacher guidance information in real time, and the frequency and intensity of errors in the student performance data are analyzed to obtain teaching feedback synchronization data; S4: Based on the teaching feedback synchronization data, analyze the time series data related to the students' performance skills, identify the skill items that differ from the standard teaching skill performance, and calculate the improvement space of the skill items. Then, adjust the teaching content and direction in combination with the teaching objectives to obtain an overview of the music teaching adjustment.

2. The remote teaching method for music education according to claim 1, characterized in that: The steps for identifying deviations of the duration and pitch of the note from the standard are specifically as follows: S111: extracting a single note signal based on the audio data stream played by the student, segmenting the audio stream using a window function, isolating the individual notes, and obtaining segmented note signals; S112: Performing Fourier transform on the segmented note signal to calculate the basic frequency and amplitude of each note to obtain the frequency-amplitude characteristics of the note; S113: Based on the frequency amplitude characteristics of the note, the deviation of each note frequency from the standard frequency is calculated using the formula: and T=t end -t start ; The duration and pitch deviation of the note are obtained, where Δf represents the frequency deviation ratio, T represents the duration of the note, f represents the currently measured note frequency, and f std Represents the standard frequency of the note, t start is the start time of the note, t end is the end time of the note.

3. The remote teaching method for music education according to claim 1, characterized in that: The steps for obtaining the audio feature offset value are specifically as follows: S121: based on the deviation standard of the duration and pitch of the note, filter the audio signals that deviate from the normal frequency range or intensity threshold to obtain a list of abnormal audio signals; S122: Based on the abnormal audio signal list, calculate the duration and intensity of each signal using the formula: Evaluate the deviation of the audio signal and obtain the audio feature deviation value ERD, where T i represents the duration of the i-th abnormal audio signal, I i represents the strength of the i-th abnormal audio signal, w T and w I is the weight coefficient of duration and intensity, and N is the total number of abnormal signals.

4. The remote teaching method for music education according to claim 1, characterized in that: The steps of analyzing the pitch, rhythm and dynamic deviation of the notes are specifically as follows: S211: Based on the audio feature offset value, the pitch, rhythm and dynamic data of each note are collected, compared with the standard music performance parameters, the note deviation data are determined, and a preliminary deviation data list is obtained; S212: Based on the preliminary deviation data list, the pitch, rhythm and dynamic data of the note are analyzed using the formula: Get the deviation analysis results, where a h 、a r and a d Represents the weight coefficient of pitch, rhythm and dynamic deviation, Δh i is the pitch deviation of the ith note, Δr i is the rhythmic deviation of the ith note, Δd i is the dynamic deviation of the ith note, N G Total number of notes.

5. The remote teaching method for music education according to claim 1, characterized in that: The steps for obtaining the music execution error classification table are specifically as follows: S221: Classifying and identifying the deviation features of each note, determining whether the note has a pitch error, an inaccurate rhythm, or a dynamic out-of-control problem, and obtaining an identified error type; S222: Based on the identified error types, the occurrence frequency of each error type is counted to obtain a music execution error classification table.

6. The remote teaching method for music education according to claim 1, characterized in that: The steps of transmitting the student's performance data and the teacher's guidance information are specifically as follows: S311: Based on the music execution error classification table, configure the WebRTC technology, establish a two-way audio and video synchronization channel, and verify whether the real-time transmission function of the audio and video data is activated to obtain a real-time audio and video synchronization channel; S312: Based on the real-time audio and video synchronization channel, the student performance data and the teacher's guidance information are transmitted in real time, and the transmission process is optimized to obtain an optimized data transmission stream.

7. The remote teaching method for music education according to claim 1, characterized in that: The steps for obtaining the teaching feedback synchronization data are specifically as follows: S321: Analyze the frequency and intensity of errors in the student's performance data, using the formula: Calculate the influence of each error type and obtain the preliminary performance error analysis result EA, where fC i represents the frequency of occurrence of the i-th error, IC i represents the strength of the i-th error, wu i Represents the weight coefficient of the i-th error type, N U is the total number of error events; S322: Based on the preliminary performance error analysis results, the teacher's real-time feedback data is integrated to obtain teaching feedback synchronization data.

8. The remote teaching method for music education according to claim 1, characterized in that: The steps for obtaining the music teaching adjustment overview are specifically as follows: S411: Analyze the time series data associated with the student's performance skills based on the teaching feedback synchronization data, identify the skill items that differ from the standard teaching skill performance, determine the deviation of the skill performance, and obtain a skill deviation log; S412: Based on the skill deviation log, the formula is used: Quantify the improvement space of each skill, calculate the average improvement potential IOP of each skill item, and obtain the improvement space analysis data, where se ti Indicates the target performance of the skill item, se si Indicates the student's performance on the corresponding skill item, N l Indicates the total number of skill items; S413: Based on the improvement space analysis data, the teaching content and direction are adjusted according to the teaching objectives to obtain an overview of the music teaching adjustments.

9. A remote teaching system for music education, characterized in that: According to any one of claims 1 to 8, the remote teaching method for music education is implemented, and the system comprises: The audio feature module separates the frequency, amplitude and duration information of the audio signal based on the audio data stream of the student's performance, identifies the deviation of the duration and pitch of each note from the standard, calculates the duration and intensity characteristics of the signal, and obtains the audio feature offset value; The error analysis module selects parameters for comparison with standard music performance based on the audio feature offset value, analyzes the pitch, rhythm and dynamic deviation of the notes, determines the error types of pitch error, inaccurate rhythm or dynamic loss of control, and obtains a music execution error classification table; The synchronous transmission module uses WebRTC technology to establish a two-way audio and video synchronization channel based on the music execution error classification table, transmits student performance data and teacher guidance information in real time, analyzes the frequency and intensity of errors in student performance data, and obtains teaching feedback synchronization data; The teaching adjustment module identifies skill items that differ from standard teaching skill performance based on the teaching feedback synchronization data, calculates the improvement space of the skill items, adjusts the teaching content and direction, and obtains an overview of the music teaching adjustment.

Images