WO2022077405A1

WO2022077405A1 - Singing instruction system and method for use thereof, and computer-readable storage medium

Info

Publication number: WO2022077405A1
Application number: PCT/CN2020/121330
Authority: WO
Inventors: 曹庆恒
Original assignee: 曹庆恒
Priority date: 2020-10-15
Filing date: 2020-10-15
Publication date: 2022-04-21
Also published as: CN112534425A

Abstract

Provided are a singing instruction system and method for use thereof, and a computer-readable storage medium, the singing instruction system comprising: an audio acquisition module (11), an analysis module (13), and a database module (12). The method for using the singing instruction system comprises: obtaining audio data of the singing of a user (S1); by means of the audio data of the singing of the user, assessing the multidimensional singing ability of the user (S2); according to the user's multidimensional singing ability of the user and singing-related information of the individual user, recommending a singing instruction solution suitable for the user (S3). In the method, by means of establishing a standard for assessing multidimensional singing ability, and obtaining the audio data of the singing of the user to assess the multidimensional singing ability of the user, it is possible to customize a singing solution specifically suitable for the user according to the user's individual circumstances, and to provide standardized guidance, reminders, and correction during the singing learning/practice process, making it more efficient and convenient and less costly for a user to learn/practice singing.

Description

A singing teaching system, using method thereof, and computer-readable storage medium

technical field

The present invention relates to the technical field of teaching equipment, in particular to a singing teaching system, a method for using the same, and a computer-readable storage medium.

Background technique

With the continuous improvement of people's living standards, people's demands for spiritual life are getting higher and higher, and more and more people like music and begin to learn to sing. Singing is an important way for people to express and exchange thoughts and feelings. There are many benefits to people practicing singing: taking deep breaths while singing increases lung function and refreshes the blood. Singing promotes good body posture, graceful body movements and vivid facial expressions. Singing can promote active thinking. Singing can enhance self-confidence and help to form an optimistic and calm character. Singing can exercise concentration and enhance memory. Singing improves speech and builds correct pronunciation and rich intonation. Singing can be familiar with more poems and deepen the ability to understand the language. Singing develops an appreciation for vocal arts such as solo, ensemble, chorus, musical, opera, etc. Singing promotes interest in other arts. Through singing, the pursuit of beautiful things is deepened, and the exploration of ideals is reflected. Singing helps express emotions and is a bridge between individuals and the outside world. Singing is a great way to entertain yourself.

Learning to sing requires the guidance of professional teachers, usually taking remedial classes or asking teachers for one-on-one tutoring. The tutors in the remedial class give one-to-many lectures. Because each student’s learning situation is different, it is difficult for the teacher to take into account the progress of all students and control the teaching speed. In addition, when the students are practicing independently, there is no teacher to provide one-on-one tutoring. Supervision, in the process of practice, it is easy to have individual syllable errors that cannot be found. This will lead to low learning efficiency and quality in the long run, which is not conducive to students' efficient learning and singing. Asking teachers for one-on-one tutoring is highly dependent on the ability of teachers, and the teaching costs of professional teachers are expensive, resulting in high learning costs for singing; in addition, the learning of singing mainly depends on the teacher's supervisor's feelings, which cannot be objectively evaluated. .

Therefore, there is an urgent need for a singing teaching system, a method for using the same, and a computer-readable storage medium, which enable users to learn singing efficiently, conveniently and at low cost.

SUMMARY OF THE INVENTION

The main purpose of the present invention is: to provide a singing teaching system, a method for using the same, and a computer-readable storage medium, which can analyze and evaluate the multi-dimensional ability of the user's singing by establishing the evaluation standard of the multi-dimensional ability of singing, and obtaining the audio data and video data of the user's singing. , can tailor a suitable singing teaching plan for the user according to the user's personal situation, and provide standardized guidance reminders and corrections during the practice process, so that the user can learn to sing more efficiently, more conveniently, and at a lower cost.

In order to achieve the above purpose, the present invention provides a singing teaching system, the singing teaching system includes: an audio acquisition module, an analysis module and a database module,

The audio acquisition module is used to acquire audio data sung by the user;

The database module is used to store the multi-dimensional singing ability database and the user's personal singing database, the singing multi-dimensional ability database includes the evaluation criteria of the singing multi-dimensional ability, and the user's personal singing database stores the personal singing related information of the user;

The analysis module is used to analyze and evaluate the multi-dimensional ability of the user's singing by analyzing the audio data of the user's singing and/or recommend a singing teaching scheme suitable for the user according to the multi-dimensional ability of the user's singing and the user's personal singing-related information.

In the singing teaching system as described above, the singing teaching system further includes a video acquisition module, which is used to acquire video data sung by the user, and the analysis module can also analyze and evaluate the performance of the user singing through the video data sung by the user. Multidimensional capabilities.

The singing teaching system as described above, the multi-dimensional ability of singing includes at least one of rhythm mastery, melody mastery, singing volume, singing method, singing skills, singing action, singing posture, emotional expression, musical score and lyrics familiarity/understanding/memory. an ability.

The singing teaching system as described above, the singing teaching plan includes a learning plan and/or an exercise plan, the learning plan includes a review and a summary after the study of specific teaching content and practice, and the exercise plan includes exercise goals, exercises Song/paragraph, practice points, method/technique, movement/posture, practice time, practice standard, familiar song/paragraph.

The singing teaching system as described above, the singing multidimensional ability database includes various songs/paragraphs/units/sections/multi-notes/single notes according to difficulty, characteristics, ability and required level, practice points, style, author, singer mark.

The above-mentioned singing teaching system, the singing teaching system can also intelligently analyze the situation that needs attention in the process of the user's singing according to the songs/paragraphs sung and the multi-dimensional ability of the user's singing, and remind in advance or along with the singing process. User attention.

In the singing teaching system as described above, the singing teaching system further includes adjusting or re-recommending a singing teaching scheme suitable for the user according to the actual situation of the user learning/practicing singing.

The singing teaching system as described above, the singing teaching system also includes: for different singing teaching schemes, respectively setting corresponding levels/points according to the evaluation results of each analysis item, and setting according to the actual situation of the user It includes the comprehensive analysis model of each analysis item, so that the comprehensive level/score of the singing teaching program can be obtained, which can be used for the evaluation and comparison of different programs.

In the singing teaching system as described above, the singing teaching system can also perform intelligent analysis and feedback according to the actual situation of the user's singing learning/practice, and the feedback includes: feeding back the analysis result to the user so that the user can improve in a targeted manner; The analysis results are fed back to teachers/parents in real time, and the teachers/parents conduct manual intervention; at least one of the evaluation reports is issued according to the analysis results.

The singing teaching system as described above, the singing teaching system further comprises: by obtaining audio data of double/multiple/chorus singing; analyzing and evaluating the double/multiple/chorus from the audio data of double/multiple/chorus singing According to the multi-dimensional ability of duo/multi-person/chorus singing and the personal singing information of duo/multi-person/choir users, a singing teaching plan suitable for duo/multi-person/choir users is recommended.

The present invention also provides a method for using the above-mentioned singing teaching system, the method comprising:

Obtain the audio data sung by the user;

Evaluate the multi-dimensional ability of the user's singing by analyzing the audio data of the user's singing;

According to the multi-dimensional ability of the user's singing and the user's personal singing-related information, a singing teaching plan suitable for the user is recommended.

The present invention also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the steps of the above-mentioned method for using the singing teaching system.

A singing teaching system, a method for using the same, and a computer-readable storage medium of the present invention include: an audio acquisition module, an analysis module and a database module. The method of using the singing teaching system includes: acquiring the audio data sung by the user; analyzing and evaluating the multi-dimensional ability of the user's singing through the audio data of the user's singing; The present invention provides a singing teaching system, a method for using the same, and a computer-readable storage medium. By establishing an evaluation standard for the multi-dimensional ability of singing, and obtaining the audio data of the user's singing to analyze and evaluate the multi-dimensional ability of the user's singing, the multi-dimensional ability of singing can be analyzed and evaluated according to the user's personal situation. The user tailors a suitable singing teaching plan, and provides standardized guidance reminders and corrections during the user's singing learning/practice process, making the user's learning/practice singing more efficient, more convenient, and lower in cost.

Description of drawings

FIG. 1 is a schematic diagram of a singing teaching system according to the first embodiment of the present invention.

FIG. 2 is a method flowchart of a method for using a singing teaching system according to the second embodiment of the present invention.

Detailed ways

In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings and embodiments.

Refer to FIG. 1 for the first embodiment of the present invention. FIG. 1 is a schematic diagram of a singing teaching system according to the first embodiment of the present invention. As shown in the figure, the singing teaching system of the present invention includes: an audio acquisition module 11 , a database module 12 and an analysis module 13 .

The audio acquisition module 11 is used to acquire audio data of the user's singing process. In the present invention, the singing teaching system may further include a video acquisition module for acquiring video data of the user's singing process. The singing teaching system of the present invention can analyze the multi-dimensional singing ability of the user only through the audio data of the user's singing process, and can also more comprehensively analyze the multi-dimensional singing ability of the user from more angles through the audio data and video data of the user's singing process. The video acquisition module needs to acquire the video of the user's singing process, such as the video of the user's mouth and facial expressions, body posture and body movements during singing. Therefore, the video acquisition module can include multiple cameras, and use different shooting angles to acquire related videos. video.

The database module 12 is used for storing the singing multi-dimensional capability database and the user's personal singing database. The singing multidimensional ability database includes evaluation criteria for singing multidimensional ability. The multi-dimensional singing ability includes at least one ability of rhythm mastery, melody mastery, singing volume, singing method, singing skills, singing movements, singing posture, emotional expression, familiarity/understanding/remembering of scores and lyrics, and may also include two and The combined ability of the above single abilities can also include the completion ability of a single track/paragraph/section or its combination, as well as the relationship between the completion ability, combination ability, and single ability. Completion ability refers to the ability of the user to complete the singing of a specific track. The user can sing a specific song well, indicating that the user's multi-dimensional singing ability meets the requirements of the song, that is, the user's rhythm mastery, melody mastery, singing volume, singing method, singing skills, singing action, singing posture, emotional expression, score and lyrics. Familiarity/understanding/memory and other abilities meet the requirements of the song, so the user has the ability to sing the song. Completion ability can be the completion ability of the track, or the completion ability of the paragraph/unit/bar/multi-note/single note. Each singing single-dimensional ability includes: the user's mastery of each singing single-dimensional ability in single-note/multi-note/measure/unit/paragraph/repertoire, etc. The mastery degree of the single-note/multi-note/bar/unit/paragraph/song, set different levels to measure the user's ability to sing in each dimension. The multi-dimensional singing ability of the user is a combination of various singing single-dimensional abilities. Singing methods can include: pronunciation method, breathing method, different usage methods of treble/alto/bass/vibrato/true voice/falsetto, etc. Singing skills can include: coordination of singing method with breathing/rhythm/melody/mood, etc.

The singing teaching system of the present invention can be used for singing teaching of different singing methods, including: popular singing method, bel canto method, national singing method, etc., and can also include different forms such as songs, operas, and operas. For different singing methods, the evaluation criteria of singing multidimensional ability can also be different. Such as: the characteristics of popular singing is to sing completely with real voice, close to the language of life, soft and natural, emphasizing passion and appeal. Bel Canto is characterized by the mixed-voice singing method. The true and false voices are mixed according to the pitch ratio, and all the resonance cavities that can be used for singing are mobilized. Folk singing is characterized by a very sweet voice, clear articulation, exquisite breath, and high pitch.

The singing multi-dimensional ability database may also include: the mastery range and list of individual tracks/paragraphs/sections or their combinations corresponding to different singing levels/levels, and the single-dimensional abilities and combined abilities corresponding to each track/paragraph/section or their combinations , Completion standards and requirements, standard audio, video, and action demonstrations corresponding to this level/level; scores of various tracks/paragraphs, teaching standard singing audio/video, tracks/paragraphs under the singing multi-dimensional ability single-dimensional/multi-dimensional/ The grading standard of the combination, the characteristics/difficulties of the pieces/paragraphs, the marks of the pieces/paragraphs according to the type/difficulty/characteristics/ability and required level/practice points/style/author/singer, etc. It is possible to find a track/section suitable for the user as the content of the teaching plan by tagging. Through the singing multi-dimensional ability database, the audio data and video data of the user's singing can be compared and analyzed with the evaluation criteria of the singing multi-dimensional ability, and the multi-dimensional ability of the user's singing can be evaluated. In the present invention, the analysis, evaluation, and marking of a piece/section can be further refined to unit/bar/multi-note/single-note, which can be adopted according to actual needs.

The user's personal singing database stores the user's personal singing-related information, which is used for analyzing and evaluating the multi-dimensional ability of the user's singing, recommending a singing teaching plan suitable for the user, analyzing the situation that needs attention in the process of the user's singing, and pointing out the deficiencies in the user's singing process. Provide the user's personal singing-related information at the time of writing. The personal singing-related information of the user may include: basic information of the user, personal ability of the user to sing, personal characteristics of the user's singing, singing learning goals, singing learning time, various abilities related to singing learning, mastered repertoires/skills/skills, Information such as repertoires/skills/skills, practice time, practice experience, and progress in the exercise, as well as the evaluation information of the user's multi-dimensional singing ability and the corresponding audio and video data. Among them, the basic information of the user includes: age, gender, height, weight, singing foundation and so on. The personal ability of the user to sing may include: the level/level of the single-dimensional ability and the combined ability of the user's multi-dimensional singing ability, the completion ability of a single track/paragraph/section or a combination thereof that the user has mastered, and the corresponding level and proficiency. The personal characteristics of the user's singing may include: the style, technique, rhythm, melody, track, author, etc. that the user likes/dislikes; the style, skill, rhythm, melody, track, author, etc. that the user is good at/not good at. Various abilities related to singing learning include: vital capacity, range, pitch, timbre, knowledge of music theory, memory ability, comprehension ability, coordination ability, coordination ability, physical strength, endurance, attention and so on.

In the present invention, the source of the singing multi-dimensional ability database can be based on various teaching materials, musical scores and related books, audio materials, video materials, related digital features of singing multi-dimensional ability and song completion ability, industry norms, expert consensus, and relevant meeting minutes , papers, monographs, inventions, scientific inferences, experimental reports, test reports, analysis reports, test reports, test reports, other literature materials, and other professional/authoritative research results. The method of establishing a singing multi-dimensional ability database can be to select suitable repertoires and performers to obtain standard audio and video data to establish, or to analyze existing data through artificial intelligence and establish it according to the standard synthesis, or to obtain data through data mining/data reorganization/statistical analysis. It is established by generating new data, or it can be established by a combination of the above methods. The data acquisition method of the user's personal singing database may include user/tutor/parent input, acquisition from other information systems, equipment or databases, or new data that is continuously acquired and analyzed during the use of database-related information. Can be a combination of the above methods.

The analysis module 13 is used to analyze and evaluate the multi-dimensional ability of the user's singing by analyzing the audio data and/or video data of the user's singing, and/or recommend a singing teaching plan suitable for the user according to the multi-dimensional ability of the user's singing and the user's personal singing-related information. The track/paragraph/unit/bar/multi-note/single note sung by the user should be included in the singing multi-dimensional capability database, including the standard singing audio/video of the track/paragraph/unit/bar/multi-note/single note and Evaluation Criteria.

The analysis module 13 analyzes and evaluates the multi-dimensional ability of the user's singing by analyzing the audio data and/or video data sung by the user, and may extract the data required for the evaluation from the audio data and/or video data sung by the user, and then compare the extracted data with the multi-dimensional singing performance. Comparing the standards in the ability database, assessing each aspect of the user's multi-dimensional singing ability from rhythm mastery, melody mastery, singing volume, singing method, singing skills, singing movements, singing posture, emotional expression, familiarity/understanding/memory of scores and lyrics, etc. It can also directly compare the audio data and video data sung by the user with the standard audio/video in the singing multi-dimensional ability database, and evaluate the ability of each aspect of the user's singing multi-dimensional ability. The data required for the analysis may be the user's original sound data with background and accompaniment sounds removed from the audio data and/or video data sung by the user, or the extraction of digital features related to multi-dimensional singing ability and track completion ability. The analysis and evaluation may also be to evaluate the combined ability of two or more of the user's individual abilities of singing multi-dimensional abilities, and to evaluate the completion ability of a single track/paragraph/section or a combination thereof.

Assessing rhythm grasping ability can be comparing the start time, end time, duration, etc. of single note/polynote/single syllable/polysyllable in the audio data sung by the user with musical score or standard singing, and can be based on different abilities For the evaluation results, set the corresponding grades or scores, for example, the rhythm ability corresponding to the difference of less than 3% corresponding to the score is grade 1, the rhythm ability corresponding to the corresponding difference between 3% and 10% of the score is grade 2, and the difference corresponding to the score is 10%. The above corresponding rhythm ability is level 3.

Assessing the melody mastery ability may be to compare the pitch of the single note/multiple notes in the audio data sung by the user with the musical score or standard singing, and corresponding grades or scores may be set according to different ability evaluation results.

Assessing the singing volume capability may be to compare the volume of the single note/multi-note in the audio data sung by the user with the musical score or standard singing, and may set corresponding grades or scores according to different capability evaluation results.

The ability to evaluate the singing method can be to compare the pronunciation method, breathing method, different usage methods of treble/alto/bass/vibrato/true voice/falsetto, etc. in the audio data and/or video data sung by the user with musical scores or standard singing. Comparisons are made, and corresponding grades or scores can be set according to different ability assessment results.

The ability to evaluate singing skills is to analyze the audio data and/or video data sung by the user, and evaluate the singer’s timbre/high-bass/long-short tone conversion, articulation/articulation/breathing skills, and rhythm/melody/mood, etc. Whether the cooperation meets the standards, and can set corresponding grades or scores according to different ability evaluation results.

The ability to evaluate singing movements can be analyzed and evaluated by analyzing and evaluating the video data of the user's singing, analyzing whether the user's head/upper body/trunk/lower body movements during the singing process are coordinated and suitable for singing, and can be set according to different ability evaluation results. corresponding grades or scores.

The ability to evaluate the singing posture can be analyzed and evaluated by the video data of the user's singing, and whether the user's posture during the singing process is consistent with the singing, whether it can increase the expressiveness, and can be set according to different ability evaluation results. score.

Emotional expression ability can be evaluated by analyzing and evaluating the rhythm, melody, volume, facial expressions and body movements of the user during singing, including head movement/upper body movement/trunk movement/lower body movement, and can be set according to different ability assessment results. corresponding grades or scores.

Familiarity/understanding/remembering of scores and lyrics can be used to analyze and evaluate the user’s familiarity and memory of scores and lyrics sung, as well as the rationality and proficiency of the corresponding singing methods, singing skills, singing movements, and singing postures. , and corresponding grades or scores can be set according to different ability assessment results.

The singing teaching system of the present invention can also set corresponding grades/points according to the evaluation results of various abilities of the multi-dimensional ability of the user to sing, and can set various ability analysis results according to the actual situation of the user. The comprehensive analysis model of multi-dimensional ability based on the user's singing situation can be based on the level/score corresponding to each ability analysis and the comprehensive analysis model including the relationship between the comprehensive analysis result and each analysis item, and the comprehensive ability of the user's singing ability can be evaluated. Level/point value, used to recommend suitable singing teaching programs to users. The rating/rating may also consider the user's age and development prospect, and a higher rating/rating may be given to a user with a young age or a promising development prospect. The comprehensive analysis model is a model used to analyze and evaluate the multi-dimensional ability of the user's singing. It can be manually set by experts/senior teachers, or obtained through data statistics/analysis, or obtained through information reorganization/big data analysis. Or obtained through artificial intelligence deep learning/optimization, and can be continuously accumulated and optimized during use.

F is the grade/score of the comprehensive ability, fi is the grade/score corresponding to the evaluation result of the _i -th ability, and S(fi) is the analytical model formula related to the _i -th ability. The specific calculation formula is as follows:

In the present invention, through the evaluation and analysis of the completion ability of different songs of the user, on the one hand, the gap between the specified songs/paragraphs/bars/notes/lyrics can be found; The common problem of users' gaps in various aspects reflected in these completion capabilities enables users to improve in a targeted manner. On the other hand, according to the status and changes of the user's ability to complete different songs, and the completion of the learning and practice content in the singing teaching plan, it can more accurately reflect the current situation and change curve of the user's singing ability, and continuously dynamically adjust the user. The model of singing multi-dimensional ability makes the model more suitable for the actual situation of the user, so as to adjust the progress or goal of learning and practice in the singing teaching plan according to the latest model data, so that the singing teaching plan is more suitable for users, and users can use the singing teaching plan. Better to learn and practice.

After evaluating the multi-dimensional ability of the user's singing, the analysis module 13 recommends a suitable singing teaching plan for the user according to the multi-dimensional ability of the user's singing and the user's personal singing-related information. A singing instructional program may include a study program and/or a practice program. The study plan includes review and summary after the study of specific teaching content and practice. The learning of specific teaching content can be in the form of text, audio, video, interactive programs, manual distance, etc., and can also include prompts in the learning process.

The practice program includes practice goals, practice repertoires/paragraphs, practice points, methods/skills, movements/postures, practice time, practice standards, familiarity with scores/lyrics, and the like. The practice goal can be the test requirements such as specific repertoires and method skills required to master, or master more repertoires/paragraphs, or master more methods/skills/actions/postures, such as pronunciation method/breathing method/vibrato method/posture /Rhythm/melody/emotion control, etc., it can also improve various abilities related to singing, including lung capacity, range, pitch, timbre, music theory knowledge, memory ability, comprehension ability, coordination ability, cooperation ability, physical strength, endurance , attention, etc., or a combination of the above goals. The goal of practice can be to learn new repertoires, to consolidate repertoires that have been learned but not mastered well, or to review repertoires already mastered. The singing teaching system of the present invention can provide different targeted schemes in the singing teaching scheme according to the user's memory and the length of time required for mastering the newly learned repertoire and consolidating the repertoire, such as: for users with high memory, the review interval is long ; For users with strong ability to learn new songs, the time to learn new songs is short.

The singing teaching system of the present invention can recommend a suitable singing teaching scheme for the user according to the actual situation of the user, including the multi-dimensional ability of the user's singing, the user's personal singing-related information, and the characteristics of the user's practice intensity and practice time. The teaching plan can be a single teaching plan, a comprehensive teaching plan for a period of time, or a teaching plan for a specific track. For example, it can recommend an exercise program consisting of songs that meet the user's level and are conducive to improving the user's ability, and while recommending the songs, give the practice points and methods that users need to pay attention to when practicing the songs, and also include the recommended exercises. Time, standards for completing exercises, etc., make users learn to sing more efficiently, more conveniently, and at a lower cost. The practice program can also be accompanied by audio/video/point/difficulty analysis of practice tracks and techniques, etc. The recommended learning content and practice repertoire may be contained in the singing multi-dimensional ability database.

Recommended singing teaching programs for users include:

Identify user goals. The user goal may be to achieve a certain level of multi-dimensional singing ability or to achieve a certain repertoire completion ability or a combination thereof.

According to the user's goal and the current status of the user's current multi-dimensional singing ability and track completion ability, calculate the tasks that need to be completed to improve the ability to achieve the goal.

Then, according to the task and combined with the actual situation of the user, a personalized singing teaching plan is formulated.

Teaching programmes may contain study programmes and/or practice programmes. The learning plan may be to select the appropriate learning content as the learning plan. Selecting the appropriate learning content is based on the user's existing problems, analyzes and finds out the essential reasons for the user's problems, and recommends suitable content for the essential reasons. For example, the user's ability to master rhythm is insufficient. After analysis, it is found that the user does not master the fast rhythm well, and the mastery of the slow rhythm and the ordinary rhythm can meet the requirements. Therefore, it is necessary to focus on recommending fast-paced related content. Another example: the user did not complete several paragraphs in a track well. After analysis, it was found that the user did not master a certain melody well, resulting in these paragraphs not being completed well. Therefore, it is necessary to focus on recommending relevant content for this melody to the user. . The exercise program can be based on the difficulty/characteristics/practice points/style, etc., select the correspondingly marked tracks/paragraphs from the singing multi-dimensional ability database, and generate the tracks/paragraphs or their combinations that cover the task requirements and suit the actual situation of the user as the exercise program. Generate an exercise program. For example: according to the user's current multi-dimensional singing ability and the gap between the ability to complete the repertoire and the target, the calculated task is to improve each of the three abilities from level 1 to level 2, and then select the learning content and practice repertoire that match the current task from the database. / paragraph, combined with the user's practice time/practice difficulty, etc., to generate a teaching plan.

In the present invention, if the gap between the target and the existing capability is large, the target can also be decomposed into a plurality of sub-targets, and the task can also be decomposed into a plurality of corresponding sub-tasks. For example: each ability of singing multi-dimensional ability is divided into ten levels, the user's goal is to reach the eighth level in singing method, melody and rhythm, and at the same time can sing 2 classic songs proficiently. The user's current singing method ability is level 6, the melody and rhythm are both level 7, and two songs cannot be sung completely, then the user's task is to improve the singing method from level 6 to level 8, and the melody and rhythm from level 7. By level 8, 2 classic pieces have the ability to complete. Due to the large gap between this goal and the existing ability, the goal can be decomposed into multiple sub-goals: singing method reaches level 7, melody reaches level 8, rhythm reaches level 8, singing method reaches level 8, and sings the first piece proficiently. , Skillfully sing the second song. Correspondingly, the task can also be divided into multiple sub-tasks: singing method from level 6 to level 7, melody from level 7 to level 8, rhythm from level 7 to level 8, singing method from level 7 to level 8, with the first song Completion ability of the track and the ability to complete the second track. Sub-goals and corresponding sub-tasks may also be single-dimensional ability, combined ability of singing multi-dimensional ability, and completion ability of a single track/paragraph/section, or a combination thereof, which is not limited.

Afterwards, a corresponding sub-scheme needs to be formulated according to each sub-task, each sub-scheme can cover the corresponding sub-task, and then the sub-schemes are integrated to form a complete teaching scheme, which can completely cover the entire task and achieve the requirements of the complete goal. Each sub-program can also be optimized, so that the integrated teaching program achieves the best efficiency and effect. Through the completion of different sub-schemes, the overall scheme is dynamically adjusted to enable users to achieve their goals. For example: if the user completes the sub-program of familiarity with scores/lyrics, and his familiarity with scores/lyrics meets the requirements of the sub-goal, he can enter the sub-task of practicing rhythm/melody. If the familiarity fails to meet the requirements, he cannot enter the practice. In the subtask of rhythm/melody, you need to continue to be familiar with the score/lyric.

The formulation of the sub-scheme needs to fully cover the learning/practice tasks of all the task units of this goal, so as to be precise and not omitted. Afterwards, optimization can be made for the scheme. The optimization can be based on the related digital features of the user’s multi-dimensional ability to sing, repertoire and repertoire completion ability. The optimization can include the following items:

1. Optimized for new content. According to the multi-dimensional ability of the user's singing and the ability to complete the track, try not to include new unmastered/unskilled content in the plan. If new unmastered/unskilled content must be included, try to include new unmastered/unskilled content as much as possible. Programs with less skilled content and less difficulty.

2. Optimized for learning/practice range. Since different tracks are composed of different rhythms, melodies, and other musical characteristics, but subdivided into paragraphs/units/bars, there are a lot of repetitions or similar parts in different tracks. Through a detailed analysis of the user's own situation, select the program that enables the user to achieve the minimum learning/practice range required for the task goal.

3. Optimize for time. Choose the one that requires the least amount of study/practice time for different scenarios.

4. Optimize for strength. According to the content complexity of different programs, choose the program that requires the least amount of learning/practice.

5. Optimized for user preferences. According to the user's preferred style, rhythm, melody, repertoire, author, etc., select a solution that includes more content/tracks that the user likes and less content/tracks that the user does not like.

6. Optimize for environment/conditions. According to the environment/condition of the user's learning/practice, including the place environment, time conditions, auxiliary conditions, etc., select the most suitable solution for the environment/condition. For example: during lunch breaks and evenings, try to schedule listening to audio/video learning instead of practice repertoire.

7. Optimized for user status. According to the user's personal state, including mood, physical strength, fatigue, etc., select the most suitable solution for the user's state.

The singing teaching scheme generated by the singing teaching system of the present invention can be one or more, and the singing teaching system can also set corresponding levels/points according to the evaluation results of each analysis item for different singing teaching schemes. , and a comprehensive analysis model including each analysis item can be set according to the actual situation of the user, so that the comprehensive level/point value of the singing teaching program can be obtained, which can be used for evaluation and comparison of different programs. The singing teaching system can recommend the teaching plan with the highest comprehensive level/score to the user, or it can set a recommendation threshold manually or automatically by the system. The teaching plan with the comprehensive level/score higher than the threshold will be recommended. The teacher or parent makes the choice.

F is the comprehensive level/point of the singing teaching plan, f _i is the level/point corresponding to the evaluation result of the i-th analysis item, and S(f _i ) is the analysis model related to the evaluation result of the i-th analysis item formula. The specific calculation formula is as follows:

The singing teaching system of the present invention stores a plurality of singing teaching schemes suitable for different model groups, such as multi-dimensional capabilities suitable for different users' singing/sing-related information of different users, and these singing teaching schemes can be manually set by experts/senior teachers. , or obtained through data statistics/data analysis, or through information reorganization/big data analysis, or through artificial intelligence deep learning/optimization, and can be continuously accumulated and optimized during use. According to the actual situation of the user, recommending a singing teaching plan suitable for the user is to select the most suitable existing singing teaching plan for the user by analyzing and comparing the multi-dimensional ability of the user's singing and the degree of fit between the user's personal singing-related information and the existing model. Considering the difference between the user's actual situation and the existing model, make appropriate adjustments to the scheme to make the scheme more suitable for the user's own actual situation. The adjustment can be done manually by professionals, or automatically by the system relying on pre-set rules, or by artificial intelligence through self-learning.

The singing teaching system of the present invention can also be aimed at the user's existing teaching and practice plan, by analyzing the audio data and/or video data of the user's practice, the user's progress can be obtained, and the existing teaching and practice plan can be promoted according to the actual progress. The implementation of the teaching and practice plan has greatly improved the implementation effect.

The singing teaching system of the present invention can also intelligently analyze the situation that needs attention during the singing process of the user according to the sung songs/paragraphs combined with the multi-dimensional ability of the user's singing, and remind the user to pay attention in advance or along the singing process. The singing teaching system may also include a display module for displaying music scores and information for reminding users to pay attention. The information that reminds users to pay attention can be displayed on the display module in the form of text, pictures or videos, or it can be displayed in a prominent manner in combination with scores/lyrics, such as changing the color of the score or displaying it in bold in the section that reminds attention , or alert the user by voice or other means.

The singing teaching system of the present invention may also include an accompaniment module for playing accompaniment suitable for the user's learning/practice repertoire, so that the user can practice singing without other auxiliary equipment and without finding a suitable accompaniment. The accompaniment can be recommended along with the user's teaching plan, or can be selected by the user.

The singing teaching system of the present invention can also perform intelligent analysis and feedback according to the actual situation of the user's singing learning/practice. The feedback includes: feeding back the analysis result to the user so that the user can improve in a targeted manner; feeding back the analysis result to the teacher in real time /Parents, manual intervention by teachers/parents; at least one of the evaluation reports is issued based on the analysis results.

The singing teaching system of the present invention can also intelligently analyze the actual situation of the user's singing learning/practice and feed back the analysis results to the user, so that the user can stick to the correct part in a targeted manner, correct the wrong part, and continuously improve the singing level. After the user finishes singing, the singing teaching system can analyze and evaluate the audio data and/or video data sung by the user, and feed back the results of the analysis and evaluation to the user. The audio or video of the correct singing can be fed back to the user, so that the user can make targeted corrections. As a singing teaching tool, the singing teaching system of the present invention can help users analyze whether their singing is correct, and continuously improve their singing level.

The singing teaching system of the present invention may further include providing feedback in real time during the user's singing learning/practice process, and manual intervention by the teacher/parent. Through manual intervention, when the user does not use the system correctly for learning/practice, it can be corrected in time. Or when the user obtains the results of learning/practice, it can timely feedback to teachers and parents, give praise to the user, etc., so as to improve the user's interest in learning to sing.

The singing teaching system of the present invention can also issue an evaluation report according to the user's singing learning/practice situation. The evaluation report may include: the multi-dimensional ability of the user's singing, including rhythm mastery, melody mastery, singing volume, singing method, singing skills, singing action, singing posture, emotional expression, and familiarity/understanding/remembering of musical scores and lyrics. , it can also include the combined ability of two or more individual abilities, or the comprehensive ability of the user's multi-dimensional singing ability, the ability to complete a single track/paragraph/section or its combination, etc., and the user's personal singing related ability. Information, such as: user's basic information, user's personal ability to sing, user's personal characteristics of singing, singing learning goals, singing learning time, various abilities related to singing learning, mastered songs/skills/skills, songs in practice/ Information on techniques/skills, practice time, practice experience and progress. The evaluation report can also be a phase-by-phase comparison report, or a progress report over a period of time, or a report on the achievement of a certain goal. Reports can be oriented to users, teachers, parents, schools, extracurricular organizations, social organizations, performance venues, and work units, as the basis for the learning process/personnel professional level evaluation/professional normative evaluation, etc.

The singing teaching system of the present invention can also visually display at least one of the multi-dimensional ability of the user's singing, the user's personal singing-related information, the singing teaching scheme suitable for the user, and the progress obtained after adopting the singing teaching scheme, etc., so that the user// Teachers/parents, etc. can more directly observe and compare the multi-dimensional ability of the user's singing, the singing teaching plan, and the progress made after adopting the singing teaching plan.

In the present invention, the analysis module 13 and the database module 12 can be installed on the server, and the evaluation results and recommended solutions can be directly fed back to the user's display module or smartphone or computer remotely through the network.

By adopting the singing teaching system of the present invention, the user can make a personalized learning/practice plan according to the actual situation of the user through the ability evaluation and problem analysis of singing the specified repertoire, complete the corresponding exercises according to the learning/practice plan, and achieve the learning/practice goal— - Improve the multi-dimensional ability of users to sing and the ability to sing more songs proficiently.

The singing teaching system of the present invention can also evaluate the multi-dimensional ability of the user's singing and the effect of the user's use of the singing teaching scheme at any time during the user's use, and adjust or re-recommend the singing teaching scheme suitable for the user according to the actual situation of the user's learning/practice. When using the singing teaching system of the present invention, users can always obtain a suitable singing teaching scheme, and continuously and effectively improve their singing level.

The singing teaching system of the present invention can also be used for singing teaching and practice of double/multi-person/chorus. The audio data of the duo/multi-person/chorus singing process can be obtained; the multi-dimensional ability of duo/multi-person/choir singing can be evaluated through the audio data analysis of duo/multi-person/choir singing. The multi-dimensional ability of singing and the singing-related information of duo/multi-person/chorus users recommends a singing teaching plan suitable for duo/multi-person/choir users.

The singing teaching system of the present invention can identify and extract the voice data of different singers from the audio data according to the voice characteristics of different singers, analyze and evaluate the corresponding standard audio data, and then analyze the multi-dimensional singing ability of different singers, and According to the multi-dimensional singing ability of different singers and the personal singing-related information of different singers, the singing teaching plan suitable for different singers is recommended. The standard audio data corresponding to the content sung by different singers may be existing in the database, or may be standard audio of different voices/roles extracted from the chorus standard audio.

In the practice process of duo/multi-person/choir, all members can practice together or individually. When practiced by a single or part of the members, the singing teaching system of the present invention can generate standard audio including other absent members, including chorus/chorus/accompaniment sound data, so that a single or part of the members can also conduct a complete practice.

Refer to FIG. 2 for the second embodiment of the present invention. FIG. 2 is a method flowchart of a method for using a singing teaching system according to the second embodiment of the present invention. As shown in the figure, the using method of the singing teaching system of the present invention comprises:

S1: Obtain the audio data sung by the user;

S2: Evaluate the multi-dimensional ability of the user's singing through the audio data analysis of the user's singing;

S3: According to the multi-dimensional ability of the user's singing and the user's personal singing-related information, a singing teaching plan suitable for the user is recommended.

The use method of a singing teaching system of the present invention corresponds to the technical features of a singing teaching system of the present invention one by one, and the description of the above-mentioned singing teaching system can be referred to, which will not be repeated here.

The present invention also provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, implements the steps of the above-mentioned method for using the singing teaching system.

A computer-readable storage medium of the present invention corresponds to a method of using a singing teaching system and the technical features of a singing teaching system of the present invention. Reference can be made to the above-mentioned method of using a singing teaching system and a singing teaching system. The description of the teaching system will not be repeated here.

To sum up, a singing teaching system, a method of using the same, and a computer-readable storage medium of the present invention, the singing teaching system includes: an audio acquisition module, an analysis module and a database module. The method of using the singing teaching system includes: acquiring the audio data sung by the user; analyzing and evaluating the multi-dimensional ability of the user's singing through the audio data of the user's singing; The present invention provides a singing teaching system, a method for using the same, and a computer-readable storage medium. By establishing an evaluation standard for the multi-dimensional ability of singing, and obtaining the audio data of the user's singing to analyze and evaluate the multi-dimensional ability of the user's singing, the multi-dimensional ability of singing can be analyzed and evaluated according to the user's personal situation. The user tailors a suitable singing teaching plan, and provides standardized guidance reminders and corrections during the user's singing learning/practice process, making the user's learning/practice singing more efficient, more convenient, and lower in cost.

The specific embodiments described above further describe the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

A singing teaching system, characterized in that the singing teaching system comprises: an audio acquisition module, an analysis module and a database module,

The audio acquisition module is used to acquire audio data sung by the user;

The database module is used to store the multi-dimensional singing ability database and the user's personal singing database, the singing multi-dimensional ability database includes the evaluation criteria of the singing multi-dimensional ability, and the user's personal singing database stores the personal singing related information of the user;

The analysis module is used to analyze and evaluate the multi-dimensional ability of the user's singing by analyzing the audio data of the user's singing and/or recommend a singing teaching scheme suitable for the user according to the multi-dimensional ability of the user's singing and the user's personal singing-related information.
The singing teaching system according to claim 1, wherein the singing teaching system further comprises a video acquisition module, the video acquisition module is used to acquire video data of the user's singing, and the analysis module can also obtain the video data of the user's singing. Video data analysis assesses the multidimensional ability of users to sing.
The singing teaching system according to claim 1 or 2, wherein the singing multi-dimensional ability includes rhythm mastery, melody mastery, singing volume, singing method, singing skill, singing action, singing posture, emotional expression, musical score and lyrics of at least one of familiarity/comprehension/memory.
The singing teaching system according to claim 1 or 2, wherein the singing teaching scheme includes a learning scheme and/or an exercise scheme, and the learning scheme includes a review and summary after the study of specific teaching content and practice, The practice program includes practice goals, practice songs/sections, practice points, methods/techniques, movements/postures, practice time, practice standards, and familiar songs/sections.
The singing teaching system according to claim 1 or 2, characterized in that: the singing multi-dimensional ability database includes various songs/paragraphs/units/sections/multi-notes/single notes according to difficulty, characteristics, ability and required level, Practice points, style, author, singer to mark.
The singing teaching system according to any one of claims 1-5, wherein the singing teaching system can also intelligently analyze the process of singing by the user according to the song/paragraph being sung and in combination with the multi-dimensional ability of the user to sing In case of needing attention, remind the user beforehand or with the singing process.
The singing teaching system according to any one of claims 1-5, wherein the singing teaching system further comprises adjusting or re-recommending a singing teaching scheme suitable for the user according to the actual situation of the user learning/practicing singing.
The singing teaching system according to any one of claims 1-5, wherein the singing teaching system further comprises: for different singing teaching schemes, respectively setting corresponding According to the actual situation of the user, a comprehensive analysis model including each analysis item can be set, so that the comprehensive level/point value of the singing teaching scheme can be obtained, which can be used for evaluation and comparison of different schemes.
The singing teaching system according to any one of claims 1-5, wherein the singing teaching system can also perform intelligent analysis and feedback according to the actual situation of the user's singing learning/practice, and the feedback includes: The analysis result is fed back to the user so that the user can improve in a targeted manner; the analysis result is fed back to the teacher/parent in real time, and the teacher/parent will manually intervene; at least one of the evaluation reports will be issued according to the analysis result.
The singing teaching system according to any one of claims 1-9, characterized in that, the singing teaching system further comprises: by acquiring audio data of double/multiple/chorus singing; The audio data analysis of chorus singing evaluates the multi-dimensional ability of duo/multi-person/choir singing, and recommends suitable duo/multi-person/choir based on the multi-dimensional ability of duo/multi-person/choir singing and the personal singing information of duo/multi-person/choir users. A singing teaching plan for multi-person/choir users.
A method of using the singing teaching system according to any one of claims 1-10, wherein the method comprises:

Obtain the audio data sung by the user;

Evaluate the multi-dimensional ability of the user's singing by analyzing the audio data of the user's singing;

According to the multi-dimensional ability of the user's singing and the user's personal singing-related information, a singing teaching plan suitable for the user is recommended.
A computer-readable storage medium, characterized in that: the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the steps of the method for using the singing teaching system according to claim 11 .