Automatic song creation method via computer

Abstract

The invention discloses an automatic song creation method via a computer. The method comprises the steps of computer composing, computer arranging and computer singing concretely, and is realized via computer composing software by that a user inputs random rows of lyrics, the rows of lyrics are separated by separators respectively, and an algorithm operation composing module generates a melody MIDI music score file; the operation composing module adds an accompaniment audio track to the corresponding MIDI music score file, and renders an accompaniment file into a high-quality WAVE audio accompaniment file via a sound source library; the MIDI music score file is combined with a specific human sound source file via a music synthesis algorithm to generate a theme; and the theme is combined with the accompaniment file to form a final song. The method is a great innovation in the field of computer music, and through the method, an ordinary person can convert words of himself/herself into the song which includes melody and customized accompaniment and can be sung.

Description

technical field [0001] The invention belongs to the technical field of song creation methods, and in particular relates to a method for automatically creating songs by using a computer. Background technique [0002] Automatic song creation is divided into three technologies in terms of process, namely computer composition, computer arrangement and computer singing. Computer composition (automated composition) or algorithm composition (algorithmic composition) is an attempt to use a formalized process to minimize the involvement of ordinary users or composers when using computers to create music. The main technologies adopted in the traditional automatic composition algorithm in the prior art include: Markov chain, random process, layered technology, knowledge base system, music grammar, artificial neural network technology and genetic algorithm, all of which use machine learning algorithms to analyze music. The melody is simulated. Since music is a work of art that is diff...

AI Technical Summary

Problems solved by technology

Since music is a work of art that is difficult to quantify, it is very inconvenient to use machine learning algorithms to simulate, that is, it is impossible to accurately evaluate the training results of the model, because the music is very difficult to quantify, and it is a unique human Perceptual knowledge, different people's evaluations also have deviations

Therefore, the music produced by traditional machine learning methods is difficult to meet people's aesthetics, thus losing the ar

Images