CN111223471A - Ringtone generation method, device, storage medium and processor - Google Patents
Ringtone generation method, device, storage medium and processor Download PDFInfo
- Publication number
- CN111223471A CN111223471A CN201811419507.5A CN201811419507A CN111223471A CN 111223471 A CN111223471 A CN 111223471A CN 201811419507 A CN201811419507 A CN 201811419507A CN 111223471 A CN111223471 A CN 111223471A
- Authority
- CN
- China
- Prior art keywords
- melody
- initial
- predicted
- determining
- ring
- 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.)
- Pending
Links
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
- G10H7/00—Instruments in which the tones are synthesised from a data store, e.g. computer organs
-
- 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
- G10H2210/056—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 extraction or identification of individual instrumental parts, e.g. melody, chords, bass; Identification or separation of instrumental parts by their characteristic voices or timbres
-
- 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
- G10H2210/101—Music Composition or musical creation; Tools or processes therefor
-
- 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
- G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
- G10H2250/311—Neural networks for electrophonic musical instruments or musical processing, e.g. for musical recognition or control, automatic composition or improvisation
Abstract
The invention discloses a ringtone generation method, a ringtone generation device, a storage medium and a processor. Wherein, the method comprises the following steps: receiving an initial melody; inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody in a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: an initial melody and a predicted melody of the initial melody after a predetermined length of time; and determining the ring tone according to the initial melody and the predicted melody. The invention solves the technical problems that only the inherent ring tone can be selected and the use experience is poor in the related technology.
Description
Technical Field
The invention relates to the field of smart phones, in particular to a ringtone generation method, a ringtone generation device, a ringtone generation storage medium and a ringtone generation processor.
Background
The mobile phone has gradually become an essential important tool in the life of people, and the related application in the mobile phone has been deeply involved in the aspects of the life field of people except the basic social function. Therefore, under the condition that only one hand is used, how to enable the mobile phone to meet the personalized requirements of the user becomes an important trend of future development of the mobile phone. The mobile phone ring has various applications in daily life of a user, such as incoming call prompt, alarm clock prompt and the like, but most of the mobile phone ring is preset by a manufacturer before the mobile phone leaves a factory, or the mobile phone ring is public music on a network selected by the user, so that the mobile phone ring is probably similar to other people, and is inconvenient for the user to show the mobile phone ring in a personalized manner.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a ringtone generation method, a ringtone generation device, a storage medium and a processor, which at least solve the technical problems that only inherent ringtones can be selected and the use experience is poor in the related technology.
According to an aspect of an embodiment of the present invention, there is provided a ring tone generating method, including: receiving an initial melody; inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: an initial melody and a predicted melody of the initial melody after a predetermined length of time; and determining the ring tone according to the initial melody and the predicted melody.
Optionally, the receiving the initial melody includes: receiving initial sound information; determining the melody of the initial sound to be the initial melody.
Optionally, determining the melody of the initial sound to be the initial melody: pre-processing the initial sound, wherein the pre-processing comprises at least one of: denoising and filtering; extracting melody features of the processed initial sound, and determining the melody of the initial sound according to the extracted melody features; and taking the melody of the initial sound as the initial melody.
Optionally, the determining the ringtone according to the initial melody and the predicted melody includes: merging the initial melody and the predicted melody into a combined melody; post-processing the synthesized melody to determine a ring melody, wherein the post-processing comprises at least one of adjusting the tone and increasing or decreasing the tail tone; and determining the ring according to the ring melody.
Optionally, the post-processing the combined melody, and the determining the ring melody includes: receiving an adjusting instruction, wherein the adjusting instruction is an instruction for adjusting the synthesized melody; determining the post-processing mode according to the adjusting instruction; post-processing the synthesized melody according to the post-processing mode; and determining the post-processed combined melody as the ring melody.
Optionally, determining the ringtone according to the ringtone melody includes: receiving ring tone parameters, wherein the ring tone parameters comprise tone colors; and determining the ring according to the tone and the ring melody.
Optionally, the melody prediction model includes a duration neural network and a note neural network, the inputting the initial melody into the melody prediction model, and the predicting the predicted melody of the initial melody within the predetermined duration by the melody prediction model includes: acquiring a note sequence, initial characteristics and preset time length in an initial melody; determining the melody characteristics of each time section in the preset time length through the time length neural network according to the preset time length and the initial characteristics; determining predicted notes through the note neural network according to the melody characteristics of each time length in the preset time length and the note sequence in the initial melody; determining a predicted melody according to the predicted note.
According to another aspect of the embodiments of the present invention, there is also provided a ringtone generation apparatus, including: a receiving module for receiving the initial melody; the prediction module is used for inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: an initial melody and a predicted melody of the initial melody after a predetermined length of time; and the determining module is used for determining the ring according to the initial melody and the predicted melody.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium, where the storage medium stores program instructions, and when the program instructions are executed, the storage medium is controlled by an apparatus to execute any one of the above methods.
According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a program, where the program executes to perform the method described in any one of the above.
In the embodiment of the invention, the method comprises the steps of receiving an initial melody; inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: an initial melody and a predicted melody of the initial melody after a predetermined length of time; the method for determining the ring according to the initial melody and the predicted melody generates the new ring according to the inherent initial melody, and achieves the purpose of generating various ring according to the requirement, thereby realizing the technical effects of improving the user experience, using flexibility and using interest, and further solving the technical problems that in the related technology, only the inherent ring can be selected and the using experience is poor.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a ring tone generating method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a ringtone generation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention 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 is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. 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 accordance with an embodiment of the present invention, there is provided a method embodiment of a ring tone generation method, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of a ring tone generating method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, receiving an initial melody;
step S104, inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: the initial melody and the predicted melody of the initial melody after the preset time length;
step S106, determining the ring according to the initial melody and the predicted melody.
According to the steps, receiving the initial melody; inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody in a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: the initial melody and the predicted melody of the initial melody after the preset time length; the method for determining the ring according to the initial melody and the predicted melody generates the new ring according to the inherent initial melody, and achieves the purpose of generating various ring tones according to requirements, thereby improving the user experience, using flexibility and using interest technical effects, and further solving the technical problems that in the related technology, only the inherent ring can be selected and the using experience is poor.
The above-mentioned receiving the initial melody may be directly receiving the melody sent by the user, for example, the image recognition device may recognize the melody map to determine the initial melody; the initial melody may also be determined by recognizing the sound by means of a speech recognition device. The sound may be various sounds, such as a user humming a melody, received music, a melody, and the like. The receiving the initial frequency may include receiving a sound, extracting a melody of the sound from the sound, and setting the melody as an initial melody.
The melody prediction model is a recognition model which can be subjected to machine learning, such as a convolutional neural network recognition model, and the like, and is obtained by using multiple groups of data through machine learning training, for example, the recognition model is trained through multiple groups of data until the model converges, and the recognition capability between input data and output data is possessed. Each set of data in the plurality of sets of data includes: the initial melody and the predicted melody after the initial melody is a predetermined length of time may belong to a front melody and a back melody of the same musical melody. For example, the first half and the second half of the same music piece may be connected, that is, the first half and the second half may be seamlessly connected to form a same melody, which may be the music piece or a part of the music piece. It should be noted that the longer the inputted music melody in the first half and the second half, the better the training effect. The same music melody may be the same month, the same category of music, the same style of music, the same music of the same chapter, etc. The more consistent the front-stage melody and the back-stage melody, the better the training effect.
The music melody to which the initial melody and the predicted melody belong may be a music melody preferred by the user. In the process of training the melody prediction model, the front-stage melody and the rear-stage melody of the same music melody are adopted, the music melody can be a music tune selected by a user or the melody of a music song, the front-stage melody and the rear-stage melody belong to the same music melody, and the two sections of melodies of the melody prediction model can be closely associated, so that the melody prediction model can be better trained. The types of the music tunes are many, and there are different types of tunes, which may be different from each other, for example, the melody of the rock type and the melody of the lyric type are different from each other, so that, in the case that the initial melody is the lyric type music, the melody of the rock type is used to train the melody prediction model, which may interfere with the melody prediction model to predict the melody of the lyric type music, and therefore, the music tune for training the melody prediction model may be the same as the music type of the initial melody. The initial melody is a reference for generating the bell sound by the user, so that the initial melody may be a music melody selected by the user and preferred by the user, and the music melody of the trained melody prediction model may be a music melody preferred by the user.
The determining of the ring tone according to the initial melody and the predicted melody may be performed in various ways, for example, the predicted melody may be modified first to determine the melody of the ring tone, the initial melody may be modified in combination with the predicted melody, or the coherence between the initial melody and the predicted melody may be modified to determine the melody of the ring tone. The ring tone may be determined according to the determined ring tone melody, such as adding background music to the ring tone melody, or attaching different sound characteristics to the ring tone melody, for example, the sound characteristics of a star may be combined with the ring tone melody, and a ring tone sung the ring tone melody by the star may be generated.
Optionally, the receiving the initial melody includes: receiving initial sound information; the melody of the initial sound is determined to be the initial melody.
The receiving of the initial melody may be directly receiving initial sound information, such as a music piece being played, or a song, a tone hummed by a user, or a song sung, a sound of a musical instrument, or the like. Through directly receiving initial sound information, convenient and fast, easy to handle only needs to adopt sound collection system just can accomplish the collection to initial sound usually. The sound collecting device may be a microphone, a sound catcher, or the like.
Optionally, determining the melody of the initial sound to be the initial melody: pre-processing the initial sound, wherein the pre-processing comprises at least one of: denoising and filtering; extracting melody features of the processed initial sound, and determining the melody of the initial sound according to the extracted melody features; the melody of the initial sound is used as the initial melody.
After the initial sound information is collected by the sound collection device, the initial melody is extracted from the initial sound information. Since the initial sound information usually includes the environmental sound, the target initial sound, the noise, and the like, before the initial melody is extracted from the initial sound information, it is necessary to extract the target initial sound from the initial sound information and to filter out other useless interference sounds such as the environmental sound and the noise, and the preprocessing may be performed on the initial sound information, and the preprocessing includes at least one of the following: and (4) denoising and filtering. Only the target initial sound is provided for the processed initial sound information, and then the initial melody is extracted from the initial sound information.
Optionally, the determining the ringtone according to the initial melody and the predicted melody includes: merging the initial melody and the predicted melody into a combined melody; post-processing the synthesized melody to determine a ring melody, wherein the post-processing comprises at least one of adjusting the tone and increasing or decreasing the tail tone; and determining the ring according to the ring melody.
After the melody prediction model determines the predicted melody according to the initial melody, the ringtone melody may be determined according to the predicted melody, and the ringtone melody may be determined according to the initial melody and the predicted melody. Since the predicted melody determined by the melody prediction model is not completely accurate and meets the user's needs, the melody of the ring tone is usually determined by combining the initial melody and the predicted melody.
In this embodiment, in the process of determining the ring tone melody by combining the initial melody and the predicted melody, the initial melody and the predicted melody are combined into a combined melody, which may be a combination of various ways, for example, the beginning of the predicted melody is connected to the end of the initial melody, or the initial melody and the predicted melody are divided into multiple sections, and the multiple sections are connected according to a predetermined rule, where the predetermined rule may be that a predetermined matching degree is exceeded. The combined melody is post-processed, and the post-processing may be melody adjustment, and the post-processing is performed according to a predetermined processing manner, for example, the smoothness of the combined melody must not exceed/fall below a predetermined threshold value, so as to make the combined melody gentle/exciting. The pitch of the synthesized melody may be adjusted, the length of the tail sound may be adjusted, and the like. And determining the combined melody after the post-processing as the ring melody, and determining the ring according to the ring melody.
Optionally, post-processing the synthesized melody, and determining the ring melody includes: receiving an adjusting instruction, wherein the adjusting instruction is an instruction for adjusting the closed melody; determining a post-processing mode according to the adjusting instruction; post-processing the synthesized melody according to a post-processing mode; and determining the post-processed combined melody as the ring melody.
In the post-processing of the combined melody, the adjustment of the pitch, the increase and decrease of the tail sound, and the like may be performed according to a predetermined adjustment rule, or may be performed in response to an adjustment instruction from the user. After the user receives the synthesized melody, the user adjusts the synthesized melody according to the self-intention, the tone can be adjusted through the adjusting instruction, the tail tone can be adjusted through the adjusting instruction, and the like. The adjusting instruction may include an instruction to adjust the pitch and/or an instruction to adjust the length of the tail tone. And after post-processing the combined melody, determining the combined melody as the ring melody.
Optionally, the determining the ring tone according to the ring tone melody includes: receiving a ring tone parameter, wherein the ring tone parameter comprises a tone; and determining the ring according to the tone and the ring melody.
After the ring tone melody is determined, the ring tone may be determined according to the ring tone melody, and the ring tone may be automatically generated according to a predetermined ring tone parameter, and the ring tone parameter may include a tone color, for example, if the predetermined ring tone parameter is a violin tone, a ring tone in which the violin plays the melody may be generated according to the ring tone melody. It is also possible that a ring tone is generated according to selected ring tone parameters, after the ring tone melody is determined, the user may be provided with a selection of ring tone parameters, or the ring tone may be determined by the user inputting ring tone parameters, according to the received ring tone parameters selected or inputted by the user, in combination with the above ring tone melody.
Optionally, the melody prediction model includes a duration neural network and a note neural network, the inputting the initial melody into the melody prediction model, and the predicting the predicted melody of the initial melody within the predetermined duration by the melody prediction model includes: acquiring a note sequence, initial characteristics and preset time length in an initial melody; determining the melody characteristics of each time length in the preset time length through a time length neural network according to the preset time length and the initial characteristics; determining predicted notes through a note neural network according to the melody characteristics of each time period in the preset time period and the note sequence in the initial melody; the predicted melody is determined based on the predicted note.
The predetermined time period may be a default time period or a time period set by a user. The initial characteristic may be a melody characteristic in the initial melody. The note sequence may be a sequence followed by note changes of the initial melody, for example, note changes in the lyric's tune cannot be skipped in high-pitch order, and the sequence may be set manually or automatically generated according to the initial melody.
It should be noted that this embodiment also provides an alternative implementation, which is described in detail below.
The mobile phone ring has various applications in daily life of a user, such as incoming call prompt, alarm clock prompt and the like, and in order to meet the personalized highlighting requirement of the user, the embodiment provides a mobile phone ring design method based on a neural network. The mobile phone is provided with a melody generating module, and in the module, a large amount of music preferred by a user is used for training a time-lapse neural network and a note neural network. When the user hums a favorite melody at random, the melody generation module can automatically recognize the melody characteristics of the user humming, then the duration characteristics of each preset duration are calculated according to the duration network state of the duration neural network model in the module, and each note is calculated according to the note network state in the note neural network model, so that the melody born by the user generates a whole melody of the preset duration, wherein the generated melody is more in line with the preference of the user to music due to the combination of the notes and the duration of the composite melody. The method specifically comprises the following steps:
firstly, a melody generating module is arranged in a mobile phone, and in the module, a time-lapse neural network and a note neural network are trained by using a large amount of music preferred by a user;
secondly, acquiring an initial melody sent by the user when a melody generating function is executed, and identifying the melody characteristics of the user humming through a melody generating module;
thirdly, acquiring a note sequence, initial characteristics and preset time set by a user in the initial melody, and calculating time characteristics of each section in the preset time according to the preset time, the initial characteristics and the time neural network model; and calculating notes according to the characteristics of each time period in the calculated preset time period, the note sequence in the initial melody and the note neural network model, and acquiring the melody according to the calculated notes.
According to the design method of the mobile phone ring based on the neural network, when a melody generation module arranged in the mobile phone executes a melody generation function, an initial melody sent by a user can be obtained, and the melody characteristics of humming of the user are identified; and then, according to a time length neural network and a note neural network which are trained by a large amount of user-preferred music, the melody hummed by the client is accepted, the subsequent melody rhythm time period distribution and the notes in each time period are calculated, and the finally generated composite melody is more in line with the music preference of the user, and the personality is revealed, so that the user experience is improved.
In order to meet the personalized highlighting requirements of users, the embodiment provides a design method of mobile phone ring based on a neural network, so that the mobile phone ring can automatically generate personalized melody according with the preference of the users when the users prompt daily incoming calls and alarm clocks. Firstly, a melody generating module is arranged in the mobile phone, and in the module, a large amount of music preferred by a user is needed to train a time-lapse neural network and a note neural network.
The duration characteristics of each preset duration calculated by the trained duration neural network model are different when the input samples of the duration neural network model are different in the training process, if the melody input in the training process is jazz music, the duration characteristics given by the trained duration neural network model subsequently are the duration characteristics of the jazz music, and if the melody input in the training process is Beijing opera, the duration characteristics given by the trained duration neural network model are the duration characteristics of the Beijing opera. For example, a measure is taken as a predetermined duration, a same note sequence is given, the duration characteristic of each measure is calculated as the duration characteristic of jazz after the duration neural network model trained by the jazz samples is input, and the duration characteristic of each measure is calculated as the duration characteristic of kyphosis after the duration neural network model trained by the kyphosis samples is input. The same is true for the effect of training samples on the note neural network model. Therefore, the favorite songs frequently listened by the user as the training sample directly influence the result of the melody generation, and further can generate the songs which accord with the favorite songs of the user.
Furthermore, when the user hums a favorite melody randomly, the melody generation module can automatically recognize the melody characteristics of the user humming, and then generate a whole melody of a preset duration and bearing the melody hummed by the client according to the duration neural network model and the character neural network model.
Fig. 2 is a schematic diagram of a ring signal generating apparatus according to an embodiment of the present invention, as shown in fig. 2, the ring signal generating apparatus includes: a receiving module 22, a prediction module 24 and a determination module 26, which are described in detail below.
A receiving module 22, configured to receive an initial melody; a prediction module 24, connected to the receiving module 22, for inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a predetermined time period by using the melody prediction model, wherein the melody prediction model is obtained by machine learning training using multiple sets of data, and each set of data in the multiple sets of data includes: the initial melody and the predicted melody of the initial melody after the preset time length; and a determining module 26 connected to the predicting module 24 for determining the ring tone according to the initial melody and the predicted melody.
By the above device, the receiving module 22 is adopted to receive the initial melody; the prediction module 24 inputs the initial melody into a melody prediction model, and predicts the predicted melody of the initial melody within a predetermined time period by using the melody prediction model, wherein the melody prediction model is obtained by using multiple sets of data through machine learning training, and each set of data in the multiple sets of data comprises: the initial melody and the predicted melody of the initial melody after the preset time length; the determining module 26 determines the ring according to the initial melody and the predicted melody, and generates a new ring according to the inherent initial melody, so as to achieve the purpose of generating various ring tones according to the requirement, thereby achieving the technical effects of improving the user experience, using flexibility and using interest, and further solving the technical problems that in the related art, only the inherent ring can be selected and the using experience is poor.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium storing program instructions, wherein when the program instructions are executed, the apparatus on which the storage medium is located is controlled to execute the method of any one of the above.
According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a program, where the program executes to perform the method of any one of the above.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A ring tone generating method, comprising:
receiving an initial melody;
inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: an initial melody and a predicted melody of the initial melody after a predetermined length of time;
and determining the ring tone according to the initial melody and the predicted melody.
2. The method of claim 1, wherein receiving the initial melody comprises:
receiving initial sound information;
determining the melody of the initial sound to be the initial melody.
3. The method of claim 2, wherein the melody of the initial sound is determined to be the initial melody:
pre-processing the initial sound, wherein the pre-processing comprises at least one of: denoising and filtering;
extracting melody features of the processed initial sound, and determining the melody of the initial sound according to the extracted melody features;
and taking the melody of the initial sound as the initial melody.
4. The method of claim 1, wherein determining a ringtone from the initial melody and the predicted melody comprises:
merging the initial melody and the predicted melody into a combined melody;
post-processing the synthesized melody to determine a ring melody, wherein the post-processing comprises at least one of adjusting the tone and increasing or decreasing the tail tone;
and determining the ring according to the ring melody.
5. The method of claim 4, wherein post-processing the synthesized melody and determining the ring melody comprises:
receiving an adjusting instruction, wherein the adjusting instruction is an instruction for adjusting the synthesized melody;
determining the post-processing mode according to the adjusting instruction;
post-processing the synthesized melody according to the post-processing mode;
and determining the post-processed combined melody as the ring melody.
6. The method of claim 5, wherein determining the ringtone according to the ringtone melody comprises:
receiving ring tone parameters, wherein the ring tone parameters comprise tone colors;
and determining the ring according to the tone and the ring melody.
7. The method of any one of claims 1 to 6, wherein the melody prediction model comprises a duration neural network and a note neural network, wherein inputting the initial melody into the melody prediction model, wherein predicting the predicted melody of the initial melody within the predetermined duration by the melody prediction model comprises:
acquiring a note sequence, initial characteristics and preset time length in an initial melody;
determining the melody characteristics of each time section in the preset time length through the time length neural network according to the preset time length and the initial characteristics;
determining predicted notes through the note neural network according to the melody characteristics of each time length in the preset time length and the note sequence in the initial melody;
determining a predicted melody according to the predicted note.
8. A ringtone generation apparatus, comprising:
a receiving module for receiving the initial melody;
the prediction module is used for inputting the initial melody into a melody prediction model, and predicting the predicted melody of the initial melody within a preset time length by the melody prediction model, wherein the melody prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: an initial melody and a predicted melody of the initial melody after a predetermined length of time;
and the determining module is used for determining the ring according to the initial melody and the predicted melody.
9. A storage medium storing program instructions, wherein the program instructions, when executed, control an apparatus in which the storage medium is located to perform the method of any one of claims 1 to 7.
10. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811419507.5A CN111223471A (en) | 2018-11-26 | 2018-11-26 | Ringtone generation method, device, storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811419507.5A CN111223471A (en) | 2018-11-26 | 2018-11-26 | Ringtone generation method, device, storage medium and processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111223471A true CN111223471A (en) | 2020-06-02 |
Family
ID=70827099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811419507.5A Pending CN111223471A (en) | 2018-11-26 | 2018-11-26 | Ringtone generation method, device, storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111223471A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6124543A (en) * | 1997-12-17 | 2000-09-26 | Yamaha Corporation | Apparatus and method for automatically composing music according to a user-inputted theme melody |
| US20050090292A1 (en) * | 2003-10-27 | 2005-04-28 | Nec Corporation | Mobile phone system with incoming melody designating function and mobile phone |
| CN101231844A (en) * | 2008-02-28 | 2008-07-30 | 北京中星微电子有限公司 | System and method of mobile phone ring mixing |
| CN104464702A (en) * | 2014-10-27 | 2015-03-25 | 叶煦舟 | Chord accompany generation method based on genetic algorithm |
| CN107644630A (en) * | 2017-09-28 | 2018-01-30 | 清华大学 | Melody generation method and device based on neutral net |
| US20180322854A1 (en) * | 2017-05-08 | 2018-11-08 | WaveAI Inc. | Automated Melody Generation for Songwriting |
-
2018
- 2018-11-26 CN CN201811419507.5A patent/CN111223471A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6124543A (en) * | 1997-12-17 | 2000-09-26 | Yamaha Corporation | Apparatus and method for automatically composing music according to a user-inputted theme melody |
| US20050090292A1 (en) * | 2003-10-27 | 2005-04-28 | Nec Corporation | Mobile phone system with incoming melody designating function and mobile phone |
| CN101231844A (en) * | 2008-02-28 | 2008-07-30 | 北京中星微电子有限公司 | System and method of mobile phone ring mixing |
| CN104464702A (en) * | 2014-10-27 | 2015-03-25 | 叶煦舟 | Chord accompany generation method based on genetic algorithm |
| US20180322854A1 (en) * | 2017-05-08 | 2018-11-08 | WaveAI Inc. | Automated Melody Generation for Songwriting |
| CN107644630A (en) * | 2017-09-28 | 2018-01-30 | 清华大学 | Melody generation method and device based on neutral net |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110019931B (en) | Audio classification method and device, intelligent equipment and storage medium | |
| CN106373580B (en) | The method and apparatus of synthesis song based on artificial intelligence | |
| CN109785859A (en) | The method, apparatus and computer equipment of management music based on speech analysis | |
| CN102881283B (en) | Method and system for processing voice | |
| CN109299318A (en) | Method, apparatus, storage medium and the terminal device that music is recommended | |
| CN106898339B (en) | Song chorusing method and terminal | |
| CN107481735A (en) | A kind of method, server and the computer-readable recording medium of transducing audio sounding | |
| CN108764114B (en) | Signal identification method and device, storage medium and terminal thereof | |
| GB2522644A (en) | Audio signal analysis | |
| CN109346045A (en) | Counterpoint generation method and device based on long neural network in short-term | |
| CN106302987A (en) | A kind of audio frequency recommends method and apparatus | |
| CN105931634A (en) | Audio screening method and device | |
| CN109147816B (en) | Method and equipment for adjusting volume of music | |
| CN112216294A (en) | Audio processing method and device, electronic equipment and storage medium | |
| CN112420015A (en) | Audio synthesis method, device, equipment and computer readable storage medium | |
| CN112037739B (en) | Data processing method and device and electronic equipment | |
| CN111462775B (en) | Audio similarity determination method, device, server and medium | |
| CN112632318A (en) | Audio recommendation method, device and system and storage medium | |
| KR101813704B1 (en) | Analyzing Device and Method for User's Voice Tone | |
| CN111859008A (en) | Music recommending method and terminal | |
| CN111223471A (en) | Ringtone generation method, device, storage medium and processor | |
| CN110853606A (en) | Sound effect configuration method and device and computer readable storage medium | |
| CN107025902B (en) | Data processing method and device | |
| CN113781989A (en) | Audio animation playing and rhythm stuck point identification method and related device | |
| CN113450811B (en) | Method and equipment for performing transparent processing on music |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200602 |
|
| RJ01 | Rejection of invention patent application after publication |