<![CDATA[The campursari music singer Alm. Didi Kempot left a work in the form of 80 albums containing about 700 songs of which 98% of the songs were composed by himself. Therefore, after his death, it was necessary to create a new campursari song so that the existence of the music was maintained. Based on this background, this research tries to build a generative model to produce new songs that have almost the same lyrics as the previous songs. The first stage was taken various song lyrics of campursari as many as 56 song lyrics as data testing then data cleansing was carried out and stored in excel format as the dataset. Then go to the Kaggle platform and use the Pandas library to read the dataset and perform clustering to see the top of terms. The next step using the Keras library is to build a sequential model with the Neural Network architecture on LongShort-TermMemory (LSTM). In order for the system to produce song lyrics as desired, they are generated per line of song lyrics by processing the number of epochs 100 times. The results obtained from this study are in the form of prototypes because in the experimental stage the final results can have many variants of new songs. Therefore, the performance measure used is the level of success in producing new campursari music that has different song lyrics but has the same theme.]]>
Copyrights © 2022
