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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


