Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Representation of music data and its conversion.

More »

Fig 1 Expand

Fig 2.

Example of melody in midi file.

(Use FL Studio DAW for presentation).

More »

Fig 2 Expand

Fig 3.

System flow chart.

More »

Fig 3 Expand

Fig 4.

Flow chart of data preprocessing.

More »

Fig 4 Expand

Fig 5.

Example of textual conversion, the graph of the upper part is the musical melody, and the bottom is the corresponding textual melody text.

More »

Fig 5 Expand

Fig 6.

GPT-2 model flow chart.

More »

Fig 6 Expand

Fig 7.

GPT-2 model fine-tuning.

More »

Fig 7 Expand

Fig 8.

Block diagram of music evaluation model.

More »

Fig 8 Expand

Fig 9.

Sample music melody text after preprocessing, and each line represents the melody of a song.

More »

Fig 9 Expand

Fig 10.

The change of loss value during training, the abscissa is rounds and the ordinate is loss.

More »

Fig 10 Expand

Fig 11.

Examples of using the MT-GPT-2 model to generate music, the note in red box is the starting note of the input, the notes framed in blue in (a) (b) are rhythmic pitches similar to the starting notes, while the notes framed in green in (c) (d) are rhythmic and pitch pitches unrelated to the starting notes.

More »

Fig 11 Expand

Fig 12.

MIDI files, (a) and (b) generated using the LSTM model were compared with MIDI files (c) and (d) generated using the MT-GPT-2 model.

(Use FL Studio DAW for presentation).

More »

Fig 12 Expand

Table 1.

Mathematical evaluation table.

More »

Table 1 Expand

Fig 13.

Smooth-saltatory progression comparison analysis.

More »

Fig 13 Expand

Fig 14.

Wave test analysis.

More »

Fig 14 Expand

Table 2.

Music theory evaluation table.

More »

Table 2 Expand