Unlock instant, AI-driven research and patent intelligence for your innovation.

A method, apparatus and computer-readable storage medium for constructing chord conversion vector

A chord and vector technology, which is applied in the field of building chord conversion vectors, can solve the problems of unfavorable chord data application, lack of chord data conversion into vector representation, low processing efficiency, etc.

Active Publication Date: 2021-05-04
MIGU CO LTD +1
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the chord data is analyzed and processed based on artificially defined rules, a wealth of music theory knowledge is required, and the processing efficiency is extremely low
Chord data lacks conversion into vector representation, and in the field of artificial intelligence, it is impossible to process the discrete chord data in the original form from the perspective of numerical analysis, and use it as resource data for machine learning
Therefore, the existing technology lacks the conversion of different chords into a vector representation, which is not conducive to the application of chord data in the field of artificial intelligence

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method, apparatus and computer-readable storage medium for constructing chord conversion vector
  • A method, apparatus and computer-readable storage medium for constructing chord conversion vector
  • A method, apparatus and computer-readable storage medium for constructing chord conversion vector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0114] 1. Experimental model: Based on the schematic diagram of the neural network model architecture of the foregoing embodiment, a three-layer neural network model is built for testing.

[0115] 2. Data set: The public MIDI data set Nottingham is used as training data, and 4000 chord track segments are extracted from the Nottingham public data set, and data cleaning and precoding are performed according to the methods in the foregoing embodiments.

[0116] 3. Key experimental environment equipment: OS: Ubuntu 16.04; Deep learning framework: tensorflow 1.2.1; Graphics card: NVIDIA1070ti (8G video memory).

[0117] 4. Training results: We hope that after sufficient training, the distance of similar chords in the vector space should be smaller than the vector distance corresponding to chords with large differences. ), the difference chord takes Bm and Am, and the training effect is shown in Table 2:

[0118] training time loss Dis_Bm_B7 Dis_Bm_Am result ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method and device for constructing a chord conversion vector, and a computer-readable storage medium. The method includes: obtaining a chord sample to be analyzed; performing preprocessing on the chord sample to be analyzed to obtain a sample code data set; According to the timing of the chord progression of the chord samples, the sample encoding data set is input into the neural network model for training, and the output of the neural network model is the predicted chord encoding at time t; determined according to the objective function of the neural network model The training quality of the sample encoding data set; when the preset training quality is satisfied, the weight of the hidden layer of the neural network model is obtained as a chord conversion vector.

Description

technical field [0001] The present invention relates to the technical field of machine learning, and in particular, to a method, an apparatus and a computer-readable storage medium for constructing a chord conversion vector. Background technique [0002] In the prior art, the existing chord analysis is carried out based on the expression in symbolic form, which is an abstract summary of human experience at a high level. If a machine is used to analyze the chord data, the expression form of the chord data needs to be converted into a mathematical vector form to facilitate the reading and calculation of the chord data. In the field of intelligent music research, there is no mature technical solution to encode chord data into a vector representation. To analyze and process chord data in the form of manually defined rules requires extensive knowledge of music theory, and the processing efficiency is extremely low. The chord data is not converted into a vector representation. I...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10H1/38G06N3/08G06N3/04
Inventor 马丹
Owner MIGU CO LTD