Method and device for generating rhythm by words based on neural network and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a method for generating rhythm by words based on a neural network, and the method comprises the steps: convertinglyrics of given music into a vector set according to a preset lyric coding rule; inputting the vector set of the lyrics of given music into a pre-constructed neural network model to obtain time sequence distribution of the lyrics; and performing connection time sequence classification on the lyrics by using the time sequence distribution to obtain a target rhythm. The invention further provides adevice for generating rhythm by words based on a neural network and a computer readable storage medium. According to the invention, the deep learning network is applied to the generation of the musicrhythm, and a reliable result can be obtained, so that the generated music better conforms to an original music standard.

Description

technical field [0001] The present invention relates to artificial intelligence technical field, relate in particular to a kind of method, device and computer-readable storage medium based on neural network to generate rhythm with words. Background technique [0002] Music rhythm is an important part of the automatic music generation algorithm. Music rhythm can regulate the distribution of lyrics, and at the same time, it can restrict pitch, melody, etc., and is a bridge connecting lyrics and music. The construction of traditional speech recognition and music models all use state modeling, a phoneme or a word is artificially divided into multiple states without physical meaning, and then a discrete or continuous Gaussian model is used to describe the output distribution of each state. This modeling method needs to segment the boundary of the modeling unit in the middle of the continuous sequence in advance, and the input and output distribution edges are aligned, and the cal...

AI Technical Summary

Problems solved by technology

[0003] People have made a lot of efforts to combine deep neural networks with various fields. In terms of music generation, probability generation algorithms and Markov chains can more accurately generate the original music rhythm, but the melody of the generated music rhythm is too simple. ; The structure model of the Long Short-Term Memory (LSTM) is too complex, and the training time of the model is long; while the Recurrent Neural Network (RNN) is likely to lose There is a problem of vanishing gradient

Images