Table 5 The accuracy comparison between LSTM and LSTM + RL.

From: Automatic composition of Guzheng (Chinese Zither) music using long short-term memory network (LSTM) and reinforcement learning (RL)

Characteristic

LSTM (× 100%)

LSTM + RL (× 100%)

Arpeggio

0.1%

6%

Finger shake

0.1%

8%

Big pinch & Small pinch

0.1%

17%

Repeating notes

11%

3%

Back to article page