CN-121999737-A - Music data processing

CN121999737ACN 121999737 ACN121999737 ACN 121999737ACN-121999737-A

Abstract

Embodiments of the present disclosure relate to music data processing. Methods, devices and computer program products for processing music data are provided. In the method, music data is divided into a plurality of segments according to a predetermined length. Based on control information associated with the plurality of segments, a plurality of control flags for the plurality of segments are respectively determined. A plurality of sound markers for the plurality of segments are determined based on sound information associated with the plurality of segments, respectively. Based on the plurality of control marks and the plurality of sound marks, features for music data are acquired.

Inventors

CHEN HAONAN
J. BL. Smith
Jenny Jane Halm Ren e Spickvitt
WANG RUJIANG
ZOU PEI
LI BOCHEN
KONG QIUQIANG
DU XINGJIAN

Assignees

北京字跳网络技术有限公司
脸萌有限公司

Dates

Publication Date: 20260508
Application Date: 20251104
Priority Date: 20241104

Claims (15)

1. A method for processing music data, comprising: dividing the music data into a plurality of segments according to a predetermined length; determining a plurality of control flags for the plurality of segments, respectively, based on control information associated with the plurality of segments; Determining a plurality of sound marks for the plurality of segments, respectively, based on sound information associated with the plurality of segments, and Based on the plurality of control marks and the plurality of sound marks, features for the music data are acquired.
2. The method of claim 1, wherein obtaining the feature based on the plurality of control markers and the plurality of sound markers comprises: Determining a control marker sequence based on the plurality of control markers, the control marker sequence having a control sequence terminator; Determining a sequence of sound marks based on the plurality of sound marks, the sequence of sound marks having a sound sequence ending symbol, and The feature is determined based on the control signature sequence and the sound signature sequence.
3. The method of claim 1, wherein determining the plurality of control markers based on the control information associated with the plurality of segments comprises, with respect to a segment of the plurality of segments, Extracting control items from the segments, the control items including at least any one of style, chapter, speed, chord, and track of the music data, and A control flag for the segment is determined based on the control item.
4. A method according to claim 3, wherein the music data comprises at least one track, and determining the control mark comprises: generating a track portion corresponding to a track of the at least one track within the segment, and The track portion is inserted into the control mark for the segment.
5. The method of claim 4, wherein determining the plurality of sound markers based on the sound information associated with the plurality of segments comprises determining sound markers for the segments by updating the control markers for the segments with the sound information associated with the segments.
6. The method of claim 5, wherein determining the sound marker for the segment comprises: extracting sound items from the sound information associated with the segment, the sound items including at least any one of the position, duration and pitch of notes in the segment, and The sound marker for the segment is determined by updating the track portion in the control marker for the segment with the sound item.
7. The method of claim 1, further comprising: Determining a plurality of reference features in response to receiving the plurality of reference music data; combining the plurality of reference features into a reference feature sequence; Acquiring training samples from the reference feature sequence according to a predetermined window size, and A music generation model is trained based on the training samples, the music generation model representing an association between at least one reference preceding marker and a reference following marker, the reference following marker following the at least one reference preceding marker.
8. The method of claim 7, further comprising: Determining a first probability of a subsequent marker from the music generation model based on at least one preceding marker; Determining subspaces in the label space of the post-label according to a finite state machine based on the at least one prior label, and The post-label is determined based on the first probability of the post-label and the subspace.
9. The method of claim 8, wherein determining the subsequent marker comprises: determining a second probability associated with the first probability and the subspace, and The subsequent marker is determined based on the second probability.
10. The method of claim 8, further comprising any of: Generating target music data based on the at least one preceding marker in response to determining that the subsequent marker is an ending symbol marker, or In response to determining that the subsequent marker is not an ending symbol, the subsequent marker is appended to the ending symbol of the at least one preceding marker.
11. An electronic device comprising a computer processor coupled to a computer readable memory unit, the memory unit comprising instructions that when executed by the computer processor implement a method for processing music data, the method comprising: dividing the music data into a plurality of segments according to a predetermined length; determining a plurality of control flags for the plurality of segments, respectively, based on control information associated with the plurality of segments; Determining a plurality of sound marks for the plurality of segments, respectively, based on sound information associated with the plurality of segments, and Based on the plurality of control marks and the plurality of sound marks, features for the music data are acquired.
12. The electronic device of claim 11, wherein obtaining the feature based on the plurality of control markers and the plurality of sound markers comprises: Determining a control marker sequence based on the plurality of control markers, the control marker sequence having a control sequence terminator; Determining a sequence of sound marks based on the plurality of sound marks, the sequence of sound marks having a sound sequence ending symbol, and The feature is determined based on the control signature sequence and the sound signature sequence.
13. The electronic device of claim 11, wherein determining the plurality of control markers based on the control information associated with the plurality of segments comprises, with respect to a segment of the plurality of segments, Extracting control items from the segments, the control items including at least any one of style, chapter, speed, chord, and track of the music data, and A control flag for the segment is determined based on the control item.
14. The electronic device of claim 13, wherein the music data comprises at least one track, and determining the control indicia comprises: generating a track portion corresponding to a track of the at least one track within the segment, and The track portion is inserted into the control mark for the segment.
15. A non-transitory computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by an electronic device to cause the electronic device to perform a method for processing music data, the method comprising: dividing the music data into a plurality of segments according to a predetermined length; determining a plurality of control flags for the plurality of segments, respectively, based on control information associated with the plurality of segments; Determining a plurality of sound marks for the plurality of segments, respectively, based on sound information associated with the plurality of segments, and Based on the plurality of control marks and the plurality of sound marks, features for the music data are acquired.

Description

Music data processing Technical Field The present disclosure relates generally to machine learning, and more particularly, to methods, apparatus, and computer program products for processing music data. Background In current techniques for generating multi-track score, the score is typically first converted to a sequence of labels, which can then be modeled using a model (typically based on a converter). Multitrack music has a correlation between the time dimension and the different instrument track dimensions, but the marker sequence is one-dimensional. How to design the coding method of the marker sequence so that the model learns this two-dimensional correlation is a problem. Furthermore, since the score can be edited directly by the composer, it is another problem how to enable the composer to control the generation of the score by means of some control signals. Disclosure of Invention In a first aspect of the present disclosure, a method for processing music data is provided. In the method, music data is divided into a plurality of segments according to a predetermined length. Based on control information associated with the plurality of segments, a plurality of control flags for the plurality of segments are respectively determined. A plurality of sound markers for the plurality of segments are determined based on sound information associated with the plurality of segments, respectively. Based on the plurality of control marks and the plurality of sound marks, features for music data are acquired. In a second aspect of the present disclosure, an electronic device is provided. The electronic device comprises a computer processor coupled to a computer readable memory unit comprising instructions which, when executed by the computer processor, implement a method according to the first aspect of the present disclosure. In a third aspect of the present disclosure, there is provided a computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by an electronic device to cause the electronic device to perform a method according to the first aspect of the present disclosure. This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Drawings The foregoing and other objects, features and advantages of the disclosure will be apparent from the following more particular descriptions of certain embodiments of the disclosure as illustrated in the accompanying drawings wherein like reference numbers generally refer to the same components throughout the embodiments of the disclosure. FIG. 1 shows a schematic diagram of encoding music data based on a correlation work; Fig. 2 illustrates an example diagram of processing music data according to an embodiment of the present disclosure; FIG. 3 illustrates a schematic diagram of a combined control mark and sound mark according to an embodiment of the present disclosure; FIG. 4 illustrates a schematic diagram of determining sound signatures in accordance with an embodiment of the present disclosure; FIG. 5 shows a schematic diagram of a training music generation model according to an embodiment of the present disclosure; FIG. 6 shows a schematic diagram of determining a later marker according to an embodiment of the present disclosure; FIG. 7 shows an example flowchart of a method for processing music data according to an embodiment of the present disclosure, and FIG. 8 illustrates a block diagram of a computing device in which various embodiments of the present disclosure may be implemented. Detailed Description The principles of the present disclosure will now be described with reference to some embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and practicing the present disclosure, and do not imply any limitation on the scope of the present disclosure. The disclosure described herein may be implemented in various ways other than those described below. In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. References in the present disclosure to "one embodiment," "an example embodiment," etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Furthermore, when a particular feature, structure, or c