GCA:A chord music generation algorithm based on double-layer LSTM

With the continuous development of deep learning and artificial neural networks, many related fields have revealed their development potential to people. Among them, the automatic generation of music has attracted the interest of many teams and companies. Compared with traditional music composition, an Grouping-Combining Algorithm(GCA) is proposed for algorithmic composition, which aims to solve the chord problem in algorithmic composition. The algorithm is based on two-layer LSTM structure, where the first layer of LSTM is used to generate notes, and the second layer of LSTM combines the output of the first layer to generate music chords. Training and testing on the database. By comparing the similarity between the experimental results and analyzing the performance of the experimental results, it is found that its performance has been improved.