CN110060702B - Data processing method and device for singing pitch accuracy detection - Google Patents
Data processing method and device for singing pitch accuracy detection Download PDFInfo
- Publication number
- CN110060702B CN110060702B CN201910357278.7A CN201910357278A CN110060702B CN 110060702 B CN110060702 B CN 110060702B CN 201910357278 A CN201910357278 A CN 201910357278A CN 110060702 B CN110060702 B CN 110060702B
- Authority
- CN
- China
- Prior art keywords
- pitch
- singing
- note
- duration
- deviation tolerance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000033764 rhythmic process Effects 0.000 claims description 25
- 230000001755 vocal effect Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 239000011295 pitch Substances 0.000 description 254
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 206010052806 Drug tolerance increased Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 108700041286 delta Proteins 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/36—Accompaniment arrangements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
- G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
- G10H2210/091—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for performance evaluation, i.e. judging, grading or scoring the musical qualities or faithfulness of a performance, e.g. with respect to pitch, tempo or other timings of a reference performance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Auxiliary Devices For Music (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
Abstract
The application discloses a data processing method and a data processing device for singing pitch accuracy detection, wherein the method comprises the following steps: acquiring note attributes of the singing notes; determining pitch deviation tolerance of the singing notes according to the note attributes; and the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the note is. The purpose of obtaining different pitch deviation tolerances under different conditions is achieved, and therefore the technical effect that the note attribute is reasonably utilized by the pitch deviation tolerance calculation method, the variable pitch deviation tolerance is generated, and the evaluation standard of the singing pitch accuracy becomes flexible is achieved.
Description
Technical Field
The application relates to the technical field of digital music processing, in particular to a data processing method and device for singing pitch accuracy detection.
Background
Today, the interest of people in singing is gradually increased due to the rapid development of the spiritual civilization, and a Karaoke system and an application program for evaluating the pitch accuracy of singers in the infinite singing process follow.
The existing data processing technology for singing pitch accuracy detection is as follows: and according to the pitch template, evaluating whether the singing pitch is within the range of the tolerance of the pitch deviation of the template with fixed tolerance of the pitch deviation, if so, determining that the singing is correct, otherwise, determining that the singing is wrong. The disadvantages are that: the fixed tolerance of pitch deviation is not flexible enough in evaluation, and many notes which are difficult to sing accurately are often difficult to be judged as singing accurately, even though singing is performed completely according to a pitch template, the listening feeling is not satisfactory.
Aiming at the technical problems in the related art, no effective solution is provided at present.
Disclosure of Invention
The present application mainly aims to provide a data processing method and apparatus for singing pitch accuracy detection, so as to solve at least one problem in the related art.
To achieve the above object, according to one aspect of the present application, there is provided a data processing method for vocal pitch accuracy detection.
The data processing method for singing pitch accuracy detection according to the application comprises the following steps:
acquiring note attributes of the singing notes;
determining pitch deviation tolerance of the singing notes according to the note attributes; and the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the note is.
Further, as the aforementioned data processing method for detecting accuracy of singing pitch, the note attribute of the singing note is obtained; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
obtaining rhythm characteristics of the singing notes;
determining an initial pitch deviation tolerance accept0 of the singing note according to the rhythm characteristics, as shown in the following formula:
accept0＝f(R)
wherein R is a rhythm characteristic, and f is a functional expression.
Further, as the aforementioned data processing method for detecting accuracy of singing pitch, the note attribute of the singing note is obtained; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a standard duration interval of the notes;
acquiring the duration of the singing notes;
determining a first duration relationship between the duration of the singing note and the standard duration interval;
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta1, wherein delta1 is a positive number;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 which is 0;
when the duration of the singing note is greater than the maximum value of the standard duration interval, a first pitch deviation tolerance accept1 ═ delta2 is obtained, wherein delta2 is a positive number.
Further, as the aforementioned data processing method for detecting accuracy of singing pitch, the note attribute of the singing note is obtained; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a first pitch of a previous note and a second pitch of a next note of the singing notes;
determining a pitch relationship between the pitch of the singing note and the first pitch and the second pitch, respectively;
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 0-delta3, wherein delta3 is a positive number and is smaller than accept 0;
a second pitch deviation tolerance accept2 ═ accept0 when the pitch of the singing note is between the first pitch and the second pitch;
when the pitch of the singing note is the highest or lowest of the first pitch and the second pitch, a second pitch deviation tolerance accept 2-accept 0+ delta4 is obtained, wherein delta4 is a positive number.
Further, as the aforementioned data processing method for detecting accuracy of singing pitch, the note attribute of the singing note is obtained; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a first duration of a previous note and a second duration of a next note of the singing notes;
determining a second duration relationship between the duration of the singing note and the first and second durations, respectively;
when the duration of the singing note is smaller than the first duration and the second duration at the same time, obtaining a third pitch deviation tolerance accept 3-delta 5, wherein delta5 is a positive number; otherwise, the third pitch deviation tolerance accept3 is 0.
In order to achieve the above object, according to another aspect of the present application, there is provided a data processing apparatus for vocal pitch accuracy detection.
The data processing device for singing pitch accuracy detection according to the application comprises:
a note attribute acquiring unit for acquiring note attributes of the singing notes;
a pitch deviation tolerance unit, configured to determine a pitch deviation tolerance of the singing note according to the note attribute; and the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the note is.
Further, the data processing apparatus for singing pitch accuracy detection as described above,
the note attribute acquisition unit includes:
the rhythm characteristic module is used for acquiring the rhythm characteristic of the singing note;
the pitch deviation tolerance unit includes:
an initial pitch deviation tolerance module, configured to determine an initial pitch deviation tolerance accept0 of the singing note according to the rhythm feature, as shown in the following equation:
accept0＝f(R)；
wherein R is a rhythm characteristic, and f is a functional expression.
Further, the data processing apparatus for singing pitch accuracy detection as described above,
the note attribute acquisition unit includes:
the standard duration interval module is used for acquiring a standard duration interval of the notes;
the duration module is used for acquiring the duration of the singing notes;
the pitch deviation tolerance unit includes:
the first duration relation module is used for determining a first duration relation between the duration of the singing note and the standard duration interval;
a first pitch deviation tolerance module to:
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta1, wherein delta1 is a positive number;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 which is 0;
when the duration of the singing note is greater than the maximum value of the standard duration interval, a first pitch deviation tolerance accept1 ═ delta2 is obtained, wherein delta2 is a positive number.
Further, the data processing apparatus for singing pitch accuracy detection as described above,
the note attribute acquisition unit includes:
acquiring a first pitch of a previous note and a second pitch of a next note of the singing notes;
the pitch deviation tolerance unit includes:
determining a pitch relationship between the pitch of the singing note and the first pitch and the second pitch, respectively;
a second pitch deviation tolerance module to:
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 0-delta3, wherein delta3 is a positive number and is smaller than accept 0;
obtaining a second pitch deviation tolerance accept 2-accept 0 when the pitch of the singing note is between the first pitch and the second pitch;
when the pitch of the singing note is the highest or lowest of the first pitch and the second pitch, a second pitch deviation tolerance accept 2-accept 0+ delta4 is obtained, wherein delta4 is a positive number.
Further, the data processing apparatus for singing pitch accuracy detection as described above,
the note attribute acquisition unit includes:
acquiring a first duration of a previous note and a second duration of a next note of the singing notes;
the pitch deviation tolerance unit includes:
a second duration relation module, configured to determine a second duration relation between the duration of the singing note and the first duration and the second duration, respectively;
a third pitch deviation tolerance module to: when the duration of the singing note is smaller than the first duration and the second duration at the same time, obtaining a third pitch deviation tolerance accept 3-delta 5, wherein delta5 is a positive number; otherwise, the third pitch deviation tolerance accept3 is 0
In the embodiment of the present application, a method for providing a data processing method and apparatus for detecting accuracy of singing pitch is adopted, wherein the method includes: acquiring note attributes of the singing notes; determining pitch deviation tolerance of the singing notes according to the note attributes; and the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the note is. The purpose of obtaining different pitch deviation tolerances under different conditions is achieved, and therefore the technical effect that the note attribute is reasonably utilized by the pitch deviation tolerance calculation method, the variable pitch deviation tolerance is generated, and the evaluation standard of the pitch accuracy of the singer in singing becomes flexible is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic flow diagram of a data processing method for singing pitch accuracy detection according to one embodiment of the present application;
FIG. 2 is a block diagram of functional blocks of a data processing apparatus for pitch accuracy detection in singing according to an embodiment of the present application; and
FIG. 3 is a Musical Instrument Digital Interface (MIDI) template for a lyric in accordance with one embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to one embodiment of the present application, a data processing method for vocal pitch accuracy detection is provided. As shown in fig. 1, the method includes steps S1 to S2 as follows:
s1, acquiring note attributes of singing notes;
specifically, the note attribute includes: song rhythm, note length, high-low relationship of adjacent notes, length relationship of adjacent notes, and the like, and the selection of the note attribute can be selected according to a specific application scenario, which is not specifically limited in this embodiment;
s2, determining the pitch deviation tolerance of the singing notes according to the note attributes; the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the singing note is; and the deviation of the lowest pitch and the highest pitch in the pitch interval and the standard pitch is consistent with the tolerance of the pitch deviation; the singing of the user can be judged through the high-pitch deviation tolerance;
that is, when the attributes of the notes are different, the tolerance of the pitch deviation of the singing notes is different; preferably, the speed of the song rhythm determines the definition of the length of the note, and the length of the note is a condition for determining the tolerance of pitch deviation; the relation of the heights of the adjacent notes refers to the relative relation between the current singing note and the previous note and the next note on the pitch, and the relative relation is also a condition for determining the tolerance of pitch deviation; the length of the adjacent notes refers to the proportional relation of a plurality of note lengths adjacent to the current singing notes, and the relation reflects the difficulty of the accuracy of the current notes and the perception sensitivity of the listening sense to the singing deviation of the current notes, so the relation is also a condition for determining the tolerance of the pitch deviation;
for example, for a song with a faster song tempo, the pitch tolerance of the notes may be greater than for a song with a slower song tempo; the absolute duration of the current singing note is very short, so that the current singing note can be singed into a transitional sound, and the pitch tolerance of the current note is amplified; the relative relation between the absolute pitch of the current singing note and the absolute pitches of the adjacent notes is the same, the pitch tolerance of the current note is reduced, otherwise, the relative relation between the absolute pitch of the current singing note and the adjacent notes is in a falling and fluctuating shape, and the pitch tolerance of the current note is increased; the absolute duration of the current singing note is slightly different from the absolute durations of the preceding note and the following note, so that the pitch tolerance of the current note is reduced, otherwise, the absolute duration of the current singing note is greatly different from the absolute durations of the preceding note and the following note, and the pitch tolerance of the note with shorter duration is larger than that of the note with longer duration;
on the basis of the steps, a pitch tolerance interval of the singing note can be obtained through the standard pitch and the pitch deviation tolerance of the singing note;
when the intonation is judged by the method, the singing pitch of the user singing the singing note is obtained;
and judging the accuracy of the singing pitch of the user according to the singing pitch and the pitch tolerance interval.
In some embodiments, as the aforementioned data processing method for pitch accuracy detection of singing, the obtaining of note attributes of the singing notes; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
obtaining rhythm characteristics of the singing notes;
determining an initial pitch deviation tolerance accept0 of the singing note according to the rhythm characteristics, as shown in the following formula:
accept0＝f(R)
wherein R is a rhythm characteristic, and f is a functional expression.
Generally, the rhythm feature is the BPM of the song corresponding to the singing note;
specifically, the BPM is the number of beats per minute;
determining an initial pitch deviation tolerance accept0 of the singing note according to the standard BPM and the BPM of the corresponding song, as shown in the following formula, wherein f is a functional expression:
accept0＝f(BPM)。
preferably, accept0 ═ 0.0083 ═ BPM + 1.5.
By way of example: since the speed of the song will determine an initial pitch deviation tolerance, the relationship between the initial pitch deviation tolerance (accept) and the BPM is: -0.0083 BPM +1.5 acept 0;
for example, BPM (beats per minute) 60, the initial pitch deviation tolerance will be set to plus or minus 1 semitone.
In some embodiments, as the aforementioned data processing method for pitch accuracy detection of singing, the obtaining of note attributes of the singing notes; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a standard duration interval of the notes;
acquiring the duration of the singing notes;
determining a first duration relationship between the duration of the singing note and the standard duration interval;
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta1, wherein delta1 is a positive number; that is, when this condition is met, the pitch deviation tolerance is increased by plus or minus delta 1;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 which is 0; that is, when this condition is satisfied, the pitch deviation tolerance is not adjusted
When the duration of the singing note is greater than the maximum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta2, wherein delta2 is a positive number; that is, when this condition is met, the pitch deviation tolerance is increased by plus or minus delta 2;
specifically, when the standard duration interval U is (200ms to 500ms), the obtained duration t of the singing note can be compared with U to determine whether t is within the interval U, lower than U or higher than U;
and when calculating on the basis of the initial pitch-deviation tolerance:
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ accept0+ delta1, wherein delta1 is a positive number; preferably, if delta1 is 0.5, then the first pitch deviation tolerance accept1 is acept 0+ 0.5;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ accept 0;
when the duration of the singing note is greater than the maximum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ accept0+ delta2, wherein delta2 is a positive number; preferably, if delta2 is 0.25, then the first pitch deviation tolerance accept1 is acept 0+ 0.25;
for example, in the MIDI template corresponding to a lyric shown in fig. 3:
the absolute duration of note number 2 is shorter than the absolute duration of note number 9, so the pitch deviation tolerance corresponding to note number 2 is greater than that of note number 9. If the absolute duration of a note is shorter than 200ms, then his pitch deviation tolerance will be plus or minus 0.5 semitones added to the pitch deviation tolerance calculated by Condition0 (accept1 ═ accept0+ 0.5). If the note absolute duration is longer than 500ms, then his pitch deviation tolerance will be that calculated by Condition0 (accept 1-accept 0). If the absolute duration of a note is longer than 200ms, notes shorter than 500ms will have their corresponding pitch deviation tolerance increased by 0.25 semitones based on the pitch deviation tolerance calculated by Condition0 (accept1 ═ accept0+ 0.25).
In addition, the pitch deviation tolerance can also be calculated by the method.
In some embodiments, as the aforementioned data processing method for pitch accuracy detection of singing, the obtaining of note attributes of the singing notes; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a first pitch of a previous note and a second pitch of a next note of the singing notes;
determining a pitch relationship between the pitch of the singing note and the first pitch and the second pitch, respectively;
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 0-delta3, wherein delta3 is a positive number and is smaller than accept 0; that is, when this condition is satisfied, the pitch deviation tolerance upper and lower edges are reduced by positive and negative deltas 1, respectively; preferably, delta3 is 0.25, then the second pitch deviation tolerance accept2 is acept 0-0.25;
a second pitch deviation tolerance accept2 ═ accept0 when the pitch of the singing note is between the first pitch and the second pitch; that is, when this condition is satisfied, no modification is made to the pitch deviation tolerance;
obtaining a second pitch deviation tolerance accept 2-accept 0+ delta4 when the pitch of the singing note is the highest or lowest of the first pitch and the second pitch, wherein delta4 is a positive number; preferably, the delta4 is 0.25, and the second pitch deviation tolerance accept2 is accept0+ 0.25.
Furthermore, the calculation may also be performed on the basis of the first pitch deviation tolerance, as follows:
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 1-delta 3;
a second pitch deviation tolerance accept2 ═ accept1 when the pitch of the singing note is between the first pitch and the second pitch;
when the pitch of the singing note is the highest or the lowest of the first pitch and the second pitch, a second pitch deviation tolerance accept 2-accept 1+ delta4 is obtained.
For example, in the MIDI template corresponding to a lyric shown in fig. 3:
when note 7 is lifted to be parallel to note 6 and note 8, and note 7 is assumed to be the current singing note, the relative relationship between the current note 7 and the adjacent pitches is called 'flat', and the corresponding pitch deviation tolerance is reduced by plus or minus 0.25 semitones (accept2 is accept1-0.25) on the basis of the tolerance calculated by Condition1, but is not less than plus or minus 1 semitone (if accept2<1 then accept2 is 1).
Assuming that note No. 2 or note No. 4 is the current singing note, the relative relationship between the current note No. 2 or note No. 4 and the adjacent pitches is called 'monotonous', and the corresponding tolerance of pitch deviation is the tolerance calculated by Condition1 (accept2 ═ accept 1).
Assuming that the note No. 3 or 7 is the currently singing note, the relative relationship between the currently playing note No. 3 or 7 and the adjacent pitches is called 'fall', and the corresponding pitch deviation tolerance is plus or minus 0.25 semitones (accept2 is accept1+0.25) on the basis of the tolerance calculated by Condition 1.
In some embodiments, as the aforementioned data processing method for pitch accuracy detection of singing, the obtaining of note attributes of the singing notes; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a first duration of a previous note and a second duration of a next note of the singing notes;
determining a second duration relationship between the duration of the singing note and the first and second durations, respectively;
when the duration of the singing note is smaller than the first duration and the second duration at the same time, obtaining a third pitch deviation tolerance accept 3-delta 5, wherein delta5 is a positive number; otherwise, the third pitch deviation tolerance accept3 is 0.
Furthermore, a calculation may be performed on the basis of the second pitch deviation tolerance, as follows:
and when the duration of the singing note is less than the first duration and the second duration simultaneously, obtaining a third pitch deviation tolerance accept 3-accept 2+ delta5, wherein delta5 is a positive number. Preferably, the third pitch deviation tolerance accept3 is equal to accept2+ 0.1.
For example, in the MIDI template corresponding to a lyric shown in fig. 3:
assuming that note 2 is currently singing and the duration of the two notes adjacent to it is longer than itself, the pitch deviation tolerance of note 2 will be increased by plus or minus 0.1 semitones based on the tolerance calculated by Condition2 (accept3 is accept2+ 0.1).
Therefore, the method in the embodiment can reasonably utilize the song rhythm, the note length, the height relationship of the adjacent notes and the influence of the length relationship of the adjacent notes on the accuracy of the singing pitch, and generate the variable pitch deviation tolerance so that the evaluation standard of the accuracy of the singing pitch becomes flexible.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided a data processing apparatus for vocal pitch accuracy detection for implementing the above data processing method for vocal pitch accuracy detection, as shown in fig. 2, the apparatus including:
a note attribute acquiring unit 1 configured to acquire a note attribute of a singing note;
a pitch deviation tolerance unit 2, configured to determine a pitch deviation tolerance of the singing note according to the note attribute; and the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the note is.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
In some embodiments, a data processing apparatus for vocal pitch accuracy detection as described above,
the note attribute acquisition unit includes:
the rhythm characteristic module is used for acquiring the rhythm characteristic of the singing note;
the pitch deviation tolerance unit includes:
an initial pitch deviation tolerance module, configured to determine an initial pitch deviation tolerance accept0 of the singing note according to the rhythm feature, as shown in the following equation:
accept0＝f(R)；
wherein R is a rhythm characteristic, and f is a functional expression.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
In some embodiments, a data processing apparatus for vocal pitch accuracy detection as described above,
the note attribute acquisition unit includes:
the standard duration interval module is used for acquiring a standard duration interval of the notes;
the duration module is used for acquiring the duration of the singing notes;
the pitch deviation tolerance unit includes:
the first duration relation module is used for determining a first duration relation between the duration of the singing note and the standard duration interval;
a first pitch deviation tolerance module to:
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta1, wherein delta1 is a positive number;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 which is 0;
when the duration of the singing note is greater than the maximum value of the standard duration interval, a first pitch deviation tolerance accept1 ═ delta2 is obtained, wherein delta2 is a positive number.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
In some embodiments, a data processing apparatus for vocal pitch accuracy detection as described above,
the note attribute acquisition unit includes:
acquiring a first pitch of a previous note and a second pitch of a next note of the singing notes;
the pitch deviation tolerance unit includes:
determining a pitch relationship between the pitch of the singing note and the first pitch and the second pitch, respectively;
a second pitch deviation tolerance module to:
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 0-delta3, wherein delta3 is a positive number and is smaller than accept 0;
obtaining a second pitch deviation tolerance accept 2-accept 0 when the pitch of the singing note is between the first pitch and the second pitch;
when the pitch of the singing note is the highest or lowest of the first pitch and the second pitch, a second pitch deviation tolerance accept 2-accept 0+ delta4 is obtained, wherein delta4 is a positive number.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
In some embodiments, a data processing apparatus for vocal pitch accuracy detection as described above,
the note attribute acquisition unit includes:
acquiring a first duration of a previous note and a second duration of a next note of the singing notes;
the pitch deviation tolerance unit includes:
a second duration relation module, configured to determine a second duration relation between the duration of the singing note and the first duration and the second duration, respectively;
a third pitch deviation tolerance module to: when the duration of the singing note is smaller than the first duration and the second duration at the same time, obtaining a third pitch deviation tolerance accept 3-delta 5, wherein delta5 is a positive number; otherwise, the third pitch deviation tolerance accept3 is 0.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A data processing method for singing pitch accuracy detection, comprising:
acquiring note attributes of the singing notes;
determining pitch deviation tolerance of the singing notes according to the note attributes; the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the singing note is;
obtaining the note attribute of the singing note; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a standard duration interval of the notes;
acquiring the duration of the singing notes;
and determining a first duration relation between the duration of the singing notes and the standard duration interval.
2. The data processing method for pitch accuracy detection of singing of claim 1, wherein said obtaining note attributes of a musical note of singing; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
obtaining rhythm characteristics of the singing notes;
determining an initial pitch deviation tolerance accept0 of the singing note according to the rhythm characteristics, as shown in the following formula:
accept0＝f(R)
wherein R is a rhythm characteristic, and f is a functional expression.
3. The data processing method for vocal pitch accuracy detection according to claim 1, wherein said determining a pitch deviation tolerance of said vocal notes according to said note attributes; the method comprises the following steps:
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta1, wherein delta1 is a positive number;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 which is 0;
when the duration of the singing note is greater than the maximum value of the standard duration interval, a first pitch deviation tolerance accept1 ═ delta2 is obtained, wherein delta2 is a positive number.
4. The data processing method for pitch accuracy detection of singing of claim 2, wherein said obtaining note attributes of a musical note of singing; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a first pitch of a previous note and a second pitch of a next note of the singing notes;
determining a pitch relationship between the pitch of the singing note and the first pitch and the second pitch, respectively;
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 0-delta3, wherein delta3 is a positive number and is smaller than accept 0;
a second pitch deviation tolerance accept2 ═ accept0 when the pitch of the singing note is between the first pitch and the second pitch;
when the pitch of the singing note is the highest or lowest of the first pitch and the second pitch, a second pitch deviation tolerance accept 2-accept 0+ delta4 is obtained, wherein delta4 is a positive number.
5. The data processing method for pitch accuracy detection of singing of claim 1, wherein said obtaining note attributes of a musical note of singing; determining pitch deviation tolerance of the singing notes according to the note attributes; the method comprises the following steps:
acquiring a first duration of a previous note and a second duration of a next note of the singing notes;
determining a second duration relationship between the duration of the singing note and the first and second durations, respectively;
when the duration of the singing note is smaller than the first duration and the second duration at the same time, obtaining a third pitch deviation tolerance accept 3-delta 5, wherein delta5 is a positive number; otherwise, the third pitch deviation tolerance accept3 is 0.
6. A data processing apparatus for singing pitch accuracy detection, comprising:
a note attribute acquiring unit for acquiring note attributes of the singing notes;
a pitch deviation tolerance unit, configured to determine a pitch deviation tolerance of the singing note according to the note attribute; the larger the tolerance of the pitch deviation is, the larger the range of the pitch interval representing the accuracy of singing the singing note is;
the note attribute acquisition unit includes:
the standard duration interval module is used for acquiring a standard duration interval of the notes;
the duration module is used for acquiring the duration of the singing notes;
the pitch deviation tolerance unit includes:
and the first duration relation module is used for determining a first duration relation between the duration of the singing note and the standard duration interval.
7. The data processing apparatus for pitch accuracy detection of singing of claim 6, wherein,
the note attribute acquisition unit includes:
the rhythm characteristic module is used for acquiring the rhythm characteristic of the singing note;
the pitch deviation tolerance unit includes:
an initial pitch deviation tolerance module, configured to determine an initial pitch deviation tolerance accept0 of the singing note according to the rhythm feature, as shown in the following equation:
accept0＝f(R)；
wherein R is a rhythm characteristic, and f is a functional expression.
8. The data processing apparatus for pitch accuracy detection of singing of claim 6, wherein,
the pitch deviation tolerance unit includes:
a first pitch deviation tolerance module to:
when the duration of the singing note is smaller than the minimum value of the standard duration interval, obtaining a first pitch deviation tolerance accept1 ═ delta1, wherein delta1 is a positive number;
when the duration of the singing note is within the standard duration interval, obtaining a first pitch deviation tolerance accept1 which is 0;
when the duration of the singing note is greater than the maximum value of the standard duration interval, a first pitch deviation tolerance accept1 ═ delta2 is obtained, wherein delta2 is a positive number.
9. The data processing apparatus for pitch accuracy detection of singing of claim 7,
the note attribute acquisition unit includes:
acquiring a first pitch of a previous note and a second pitch of a next note of the singing notes;
the pitch deviation tolerance unit includes:
determining a pitch relationship between the pitch of the singing note and the first pitch and the second pitch, respectively;
a second pitch deviation tolerance module to:
when the pitch of the singing note is consistent with the first pitch and the second pitch, obtaining a second pitch deviation tolerance accept 2-accept 0-delta3, wherein delta3 is a positive number and is smaller than accept 0;
obtaining a second pitch deviation tolerance accept 2-accept 0 when the pitch of the singing note is between the first pitch and the second pitch;
obtaining a second pitch deviation tolerance accept 2-accept 0+ delta4 when the pitch of the singing note is the pitch of the singing note and is the highest or lowest of the first pitch and the second pitch, wherein delta4 is a positive number.
10. The data processing apparatus for pitch accuracy detection of singing of claim 6, wherein,
the note attribute acquisition unit includes:
acquiring a first duration of a previous note and a second duration of a next note of the singing notes;
the pitch deviation tolerance unit includes:
a second duration relation module, configured to determine a second duration relation between the duration of the singing note and the first duration and the second duration, respectively;
a third pitch deviation tolerance module to: when the duration of the singing note is smaller than the first duration and the second duration at the same time, obtaining a third pitch deviation tolerance accept 3-delta 5, wherein delta5 is a positive number; otherwise, the third pitch deviation tolerance accept3 is 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910357278.7A CN110060702B (en) | 2019-04-29 | 2019-04-29 | Data processing method and device for singing pitch accuracy detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910357278.7A CN110060702B (en) | 2019-04-29 | 2019-04-29 | Data processing method and device for singing pitch accuracy detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110060702A CN110060702A (en) | 2019-07-26 |
| CN110060702B true CN110060702B (en) | 2020-09-25 |
Family
ID=67321569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910357278.7A Active CN110060702B (en) | 2019-04-29 | 2019-04-29 | Data processing method and device for singing pitch accuracy detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110060702B (en) |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4407473B2 (en) * | 2004-11-01 | 2010-02-03 | ヤマハ株式会社 | Performance method determining device and program |
| CN101364407B (en) * | 2008-09-17 | 2011-12-28 | 清华大学 | Karaoke singing marking method keeping subjective consistency |
| JP5891656B2 (en) * | 2011-08-31 | 2016-03-23 | ヤマハ株式会社 | Accompaniment data generation apparatus and program |
| CN103971674B (en) * | 2014-05-22 | 2017-02-15 | 天格科技（杭州）有限公司 | Sing real-time scoring method |
| JP6514874B2 (en) * | 2014-10-03 | 2019-05-15 | 株式会社第一興商 | Karaoke scoring device that compares the pitch difference of the reference with the pitch difference of the singing voice and performs scoring |
| JP6464703B2 (en) * | 2014-12-01 | 2019-02-06 | ヤマハ株式会社 | Conversation evaluation apparatus and program |
| JP6561499B2 (en) * | 2015-03-05 | 2019-08-21 | ヤマハ株式会社 | Speech synthesis apparatus and speech synthesis method |
| CN106548784B (en) * | 2015-09-16 | 2020-04-24 | 广州酷狗计算机科技有限公司 | Voice data evaluation method and system |
| CN106547797B (en) * | 2015-09-23 | 2019-07-05 | 腾讯科技（深圳）有限公司 | Audio generation method and device |
| CN107103915A (en) * | 2016-02-18 | 2017-08-29 | 广州酷狗计算机科技有限公司 | A kind of audio data processing method and device |
| CN106205634A (en) * | 2016-07-14 | 2016-12-07 | 东北电力大学 | A kind of spoken English in college level study and test system and method |
| CN108206026B (en) * | 2017-12-05 | 2021-12-03 | 北京小唱科技有限公司 | Method and device for determining pitch deviation of audio content |
| CN108810075B (en) * | 2018-04-11 | 2020-12-18 | 北京小唱科技有限公司 | Audio correction system realized based on server side |
| CN108922516B (en) * | 2018-06-29 | 2020-11-06 | 北京语言大学 | Method and device for detecting threshold value |
| CN109003623A (en) * | 2018-08-08 | 2018-12-14 | 爱驰汽车有限公司 | Vehicle-mounted singing points-scoring system, method, equipment and storage medium |
| CN109272975B (en) * | 2018-08-14 | 2023-06-27 | 无锡冰河计算机科技发展有限公司 | Automatic adjustment method and device for singing accompaniment and KTV jukebox |
| CN109903778B (en) * | 2019-01-08 | 2020-09-25 | 北京雷石天地电子技术有限公司 | Method and system for real-time singing scoring |
-
2019
- 2019-04-29 CN CN201910357278.7A patent/CN110060702B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110060702A (en) | 2019-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108257613B (en) | Method and device for correcting pitch deviation of audio content | |
| CN108206026B (en) | Method and device for determining pitch deviation of audio content | |
| CN109448754B (en) | Multidimensional singing scoring system | |
| US5563358A (en) | Music training apparatus | |
| US10354625B2 (en) | Digital sight-singing piano with a fixed-solfège keyboard, continuous keys and adjustable tones by kneading piano keys | |
| Cowell | New musical resources | |
| KR101086089B1 (en) | Apparatus and method for analyzing audio data | |
| KR102107588B1 (en) | Method for evaluating about singing and apparatus for executing the method | |
| US12198665B2 (en) | Method for detecting melody of audio signal and electronic device | |
| JP5957798B2 (en) | Back voice detection device and singing evaluation device | |
| KR20100057307A (en) | Singing score evaluation method and karaoke apparatus using the same | |
| Goodchild et al. | Analysis, performance, and tension perception of an unmeasured prelude for harpsichord | |
| US9098679B2 (en) | Raw sound data organizer | |
| CN110060702B (en) | Data processing method and device for singing pitch accuracy detection | |
| JP2017097267A (en) | Technique determination device | |
| KR101795760B1 (en) | Apparatus and method for classifying level of electronic music score | |
| Hosken | The pocket: a theory of beats as domains | |
| JP6701864B2 (en) | Sound evaluation device and sound evaluation method | |
| JP6304650B2 (en) | Singing evaluation device | |
| JP2008516288A (en) | Extraction of melody that is the basis of audio signal | |
| Ellis | Pre-instrumental scales | |
| JP2016180965A (en) | Evaluation device and program | |
| Bozkurt | Features for analysis of Makam music | |
| JP5585320B2 (en) | Singing voice evaluation device | |
| EP0367191A2 (en) | Automatic music transcription method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |