Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Buddhist music generation method and device, equipment and storage medium

A kind of Buddhist music and Buddhist technology, applied in neural learning methods, biological neural network models, speech analysis, etc., to achieve the effects of strong applicability, improved efficiency, and enhanced fun

Pending Publication Date: 2021-06-25
PING AN TECH (SHENZHEN) CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the technical problem that the music generation system trained by the traditional model is prone to overfitting and the output is approximately equal to the training sample

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
  • Buddhist music generation method and device, equipment and storage medium
  • Buddhist music generation method and device, equipment and storage medium
  • Buddhist music generation method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] Aiming at the above problems, this application proposes a double hidden layer network model improved by using a product cyclic neural network and a long-short memory cyclic neural network to generate Buddhist music, and also uses one-hot encoding to convert the digital files of Buddhist music Encode the features in the feature to increase the connection of the front and back features for a longer period of time, so that the model can better learn the relationship between non-adjacent data points, and get a generated file that is more in line with its musical characteristics, thus solving the problem of the traditional model. The trained music generation system is prone to problems such as many repetitions, single structure, and the output after overfitting is approximately equal to the training samples.

[0091] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distingui...

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 relates to the technical field of artificial intelligence, and discloses a Buddhist music generation method and device, equipment and a storage medium. According to the method, after discretization and one-hot coding are carried out on a digital file of Buddhist music, the digital file is input into a 3-gram mLSTM model for vector calculation, then gradient descent back propagation operation is carried out on the calculated vector, and Buddhist music corresponding to the digital file is generated. and after one-hot encoding is carried out on discrete features, the features of each dimension of the encoded features can be regarded as continuous features, so that the continuity after digital file processing is ensured, the over-fitting processing is avoided, the synthesis accuracy is improved, the music synthesis efficiency is effectively improved, the interestingness of the synthesized music is enhanced, and the applicability is higher.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a method, device, equipment and storage medium for generating Buddhist music. Background technique [0002] As a high-level product of human intelligence activities, music has a rather complex structure. Musicians who have undergone certain musical training can easily create musical works with long-term structures, including passages such as beginning, succession, transition, and so on. However, for the artificial intelligence system, although it can generate works with some small structures, it is difficult to guarantee its long-term structures such as echoes, developments, and transitions on the minute scale. [0003] Traditional time series models such as hidden Markov models and recurrent neural networks often only have connection and control functions in adjacent units, but do not connect across more time units. The cyclic neural network has the c...

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 Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06F40/289G06F40/157G06K9/62G10L25/30
CPCG06N3/08G06F40/289G06F40/157G10L25/30G06N3/044G06N3/045G06F18/214
Inventor 刘奡智郭锦岳韩宝强肖京
Owner PING AN TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products