Related papers: Exploring how a Generative AI interprets music
Learning and inferring features that generate sensory input is a task continuously performed by cortex. In recent years, novel algorithms and learning rules have been proposed that allow neural network models to learn such features from…
Mapping music to dance is a challenging problem that requires spatial and temporal coherence along with a continual synchronization with the music's progression. Taking inspiration from large language models, we introduce a 2-step approach…
Automatic generation of sequences has been a highly explored field in the last years. In particular, natural language processing and automatic music composition have gained importance due to the recent advances in machine learning and…
Automatic choreography generation is a challenging task because it often requires an understanding of two abstract concepts - music and dance - which are realized in the two different modalities, namely audio and video, respectively. In…
Structure perception is a fundamental aspect of music cognition in humans. Historically, the hierarchical organization of music into structures served as a narrative device for conveying meaning, creating expectancy, and evoking emotions in…
In the domain of algorithmic music composition, machine learning-driven systems eliminate the need for carefully hand-crafting rules for composition. In particular, the capability of recurrent neural networks to learn complex temporal…
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…
Our goal is to be able to build a generative model from a deep neural network architecture to try to create music that has both harmony and melody and is passable as music composed by humans. Previous work in music generation has mainly…
Generative models and vision encoders have largely advanced on separate tracks, optimized for different goals and grounded in different mathematical principles. Yet, they share a fundamental property: latent space Gaussianity. Generative…
We present in this paper PerformacnceNet, a neural network model we proposed recently to achieve score-to-audio music generation. The model learns to convert a music piece from the symbolic domain to the audio domain, assigning…
Music is one of the Gardner's intelligences in his theory of multiple intelligences. How humans perceive and understand music is still being studied and is crucial to develop artificial intelligence models that imitate such processes. Music…
Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…
Traditionally, music was treated as an analogue signal and was generated manually. In recent years, music is conspicuous to technology which can generate a suite of music automatically without any human intervention. To accomplish this…
Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to…
This paper focuses on the modeling of musical melodies as networks. Notes of a melody can be treated as nodes of a network. Connections are created whenever notes are played in sequence. We analyze some main tracks coming from different…
In this work we study Variational Autoencoders (VAEs) from the perspective of harmonic analysis. By viewing a VAE's latent space as a Gaussian Space, a variety of measure space, we derive a series of results that show that the encoder…
Variational Autoencoders (VAEs) constitute a crucial component of neural symbolic music generation, among which some works have yielded outstanding results and attracted considerable attention. Nevertheless, previous VAEs still encounter…
To many people, music is a mystery. It is uniquely human, because no other species produces elaborate, well organized sound for no particular reason. It has been part of every known civilization on earth. It has become a very part of man's…
The advent of ML music models such as Google Magenta's MusicVAE now allow us to extract and replicate compositional features from otherwise complex datasets. These models allow computational composers to parameterize abstract variables such…
Music segmentation refers to the dual problem of identifying boundaries between, and labeling, distinct music segments, e.g., the chorus, verse, bridge etc. in popular music. The performance of a range of music segmentation algorithms has…