Lilac Atassi

Lilac Atassi

Denoising Diffusion Probabilistic models have emerged as simple yet very powerful generative models. Unlike other generative models, diffusion models do not suffer from mode collapse or require a discriminator to generate high-quality samples. In this paper, a diffusion model that uses a binomial prior distribution to generate piano rolls is proposed. The paper also proposes an efficient method to train the model and generate samples. The generated music has coherence at time scales up to the length of the training piano roll segments. The paper demonstrates how this model is conditioned on the input and can be used to harmonize a given melody, complete an incomplete piano roll, or generate a variation of a given piece. The code is publicly shared to encourage the use and development of the method by the community.

Lilac Atassi

While recent generative models can produce engaging music, their utility is limited. The variation in the music is often left to chance, resulting in compositions that lack structure. Pieces extending beyond a minute can become incoherent or repetitive. This paper introduces an approach for generating structured, arbitrarily long musical pieces. Central to this approach is the creation of musical segments using a conditional generative model, with transitions between these segments. The generation of prompts that determine the high-level composition is distinct from the creation of finer, lower-level details. A large language model is then used to suggest the musical form.

Lilac Atassi

In the process of developing a new digital music interface, the author faced three questions that have attracted little to no attention in the literature. By tracking body joints, a performer can use body parts to directly control a digital music instrument. An immediate question that follows asks which limb(s) is more effective for the instrument. The next question asks that movement should be measured relative to a particular reference point. And the last question asks about the mathematical form of the mapping function from the movement feature to the sound parameters. This paper attempts to discuss why finding an answer to these questions is worthwhile and to provide possible solutions that require further investigation.