A Transformer Based Pitch Sequence Autoencoder with MIDI Augmentation

Algorithms based on deep learning have been widely put forward for automatic music generated. However, few objective approaches have been proposed to assess whether a melody was created by automatons or Homo sapiens. Conference of Sound and Music Technology (2020) provides us a great opportunity to cope with the problem. In this paper, a masked language model based on ALBERT trained with AI-composed single-track MIDI is demonstrated for composers classification tasks. Besides, music tune transposition and MIDI sequence truncation is applied for data augments. To prevent from over-fitting, a refined loss function is proposed and the amount of parameters is reduced. This work provides a new approach to tackle the problem on obtaining features from tiny dataset which is common in music signal analysis and deserve more attention.