Explicitly Conditioned Melody Generation: A Case Study with Interdependent RNNs
arXiv:1907.05208
Abstract
Deep generative models for symbolic music are typically designed to model temporal dependencies in music so as to predict the next musical event given previous events. In many cases, such models are expected to learn abstract concepts such as harmony, meter, and rhythm from raw musical data without any additional information. In this study, we investigate the effects of explicitly conditioning deep generative models with musically relevant information. Specifically, we study the effects of four different conditioning inputs on the performance of a recurrent monophonic melody generation model. Several combinations of these conditioning inputs are used to train different model variants which are then evaluated using three objective evaluation paradigms across two genres of music. The results indicate musically relevant conditioning significantly improves learning and performance, and reveal how this information affects learning of musical features related to pitch and rhythm. An informal subjective evaluation suggests a corresponding improvement in the aesthetic quality of generations.
In Proceedings of the 7th International Workshop on Musical Meta-creation (MUME). Charlotte, North Carolina 2019
References in corpus (7)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distributed Representations of Words and Phrases and their Compositionality
- On the Convergence of Adam and Beyond
- C-RNN-GAN: Continuous recurrent neural networks with adversarial training
- A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
- MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
- Song From PI: A Musically Plausible Network for Pop Music Generation
Cited by in corpus (5)
- A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
- Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
- The Ethical Implications of Generative Audio Models: A Systematic Literature Review
- Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
- Automatic Melody Harmonization with Triad Chords: A Comparative Study