Learning to Traverse Latent Spaces for Musical Score Inpainting
arXiv:1907.01164
Abstract
Music Inpainting is the task of filling in missing or lost information in a piece of music. We investigate this task from an interactive music creation perspective. To this end, a novel deep learning-based approach for musical score inpainting is proposed. The designed model takes both past and future musical context into account and is capable of suggesting ways to connect them in a musically meaningful manner. To achieve this, we leverage the representational power of the latent space of a Variational Auto-Encoder and train a Recurrent Neural Network which learns to traverse this latent space conditioned on the past and future musical contexts. Consequently, the designed model is capable of generating several measures of music to connect two musical excerpts. The capabilities and performance of the model are showcased by comparison with competitive baselines using several objective and subjective evaluation methods. The results show that the model generates meaningful inpaintings and can be used in interactive music creation applications. Overall, the method demonstrates the merit of learning complex trajectories in the latent spaces of deep generative models.
20th International Society for Music Information Retrieval Conference (ISMIR), 2019, Delft, The Netherlands; 6 pages, 8 figures
References in corpus (6)
- Distributed Representations of Words and Phrases and their Compositionality
- Auto-Encoding Variational Bayes
- Music Transformer
- Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
- Learning a Latent Space of Multitrack Measures
- A Predictive Model for Music Based on Learned Interval Representations
Cited by in corpus (4)
- MMM : Exploring Conditional Multi-Track Music Generation with the Transformer
- The Ethical Implications of Generative Audio Models: A Systematic Literature Review
- Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI
- Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions