Music generation with variational recurrent autoencoder supported by history
Ivan P. Yamshchikov, Alexey Tikhonov
Abstract
Abstract A new artificial neural network architecture that helps generating longer melodic patterns is introduced alongside with methods for post-generation filtering. The proposed approach, called variational autoencoder supported by history, is based on a recurrent highway gated network combined with a variational autoencoder. The combination of this architecture with filtering heuristics allows the generation of pseudo-live, acoustically pleasing, melodically diverse music.
Topics & Concepts
AutoencoderArtificial intelligenceComputer scienceHeuristicsRecurrent neural networkArtificial neural networkMelodySpeech recognitionDeep learningPattern recognition (psychology)Machine learningNetwork architectureAlgorithmArchitectureMusic Technology and Sound StudiesMusic and Audio ProcessingGenerative Adversarial Networks and Image Synthesis