With the continuous development of deep learning and artificial neural networks(ANNs), algorithmic composition has gradually become a hot research field. In order to solve the music-style problem in generating chord m...With the continuous development of deep learning and artificial neural networks(ANNs), algorithmic composition has gradually become a hot research field. In order to solve the music-style problem in generating chord music, a multi-style chord music generation(MSCMG) network is proposed based on the previous ANN for creation. A music-style extraction module and a style extractor are added by the network on the original basis;the music-style extraction module divides the entire music content into two parts, namely the music-style information Mstyleand the music content information Mcontent. The style extractor removes the music-style information entangled in the music content information. The similarity of music generated by different models is compared in this paper. It is also evaluated whether the model can learn music composition rules from the database. Through experiments, it is found that the model proposed in this paper can generate music works in the expected style. Compared with the long short term memory(LSTM) network, the MSCMG network has a certain improvement in the performance of music styles.展开更多
The first part of this article addresses the main premise of the Theory of Musical Equilibration. It states that in contrast to previous hypotheses, music does not directly describe emotions: instead;it evokes process...The first part of this article addresses the main premise of the Theory of Musical Equilibration. It states that in contrast to previous hypotheses, music does not directly describe emotions: instead;it evokes processes of the will which the listener identifies with. It is not until these processes are experienced that music appears to take on an emotional character. The second part of the article focuses on demonstrating the emotional nature of musical harmonies. The Basic Test and the Rocky Test are presented. These tests were designed to find correlations between chords and scenes from fairy tales as well as emotional terms. 86% of the participants correlated the musical selection to the emotion outlined by the Theory of Musical Equilibration the authors developed in this context.展开更多
基金National Natural Science Foundation of China (No.61801106)。
文摘With the continuous development of deep learning and artificial neural networks(ANNs), algorithmic composition has gradually become a hot research field. In order to solve the music-style problem in generating chord music, a multi-style chord music generation(MSCMG) network is proposed based on the previous ANN for creation. A music-style extraction module and a style extractor are added by the network on the original basis;the music-style extraction module divides the entire music content into two parts, namely the music-style information Mstyleand the music content information Mcontent. The style extractor removes the music-style information entangled in the music content information. The similarity of music generated by different models is compared in this paper. It is also evaluated whether the model can learn music composition rules from the database. Through experiments, it is found that the model proposed in this paper can generate music works in the expected style. Compared with the long short term memory(LSTM) network, the MSCMG network has a certain improvement in the performance of music styles.
文摘The first part of this article addresses the main premise of the Theory of Musical Equilibration. It states that in contrast to previous hypotheses, music does not directly describe emotions: instead;it evokes processes of the will which the listener identifies with. It is not until these processes are experienced that music appears to take on an emotional character. The second part of the article focuses on demonstrating the emotional nature of musical harmonies. The Basic Test and the Rocky Test are presented. These tests were designed to find correlations between chords and scenes from fairy tales as well as emotional terms. 86% of the participants correlated the musical selection to the emotion outlined by the Theory of Musical Equilibration the authors developed in this context.
