相关论文: Losses, Dissonances, and Distortions

Data driven models of dynamical systems help planners and controllers to provide more precise and accurate motions. Most model learning algorithms will try to minimize a loss function between the observed data and the model's predictions.…

In many applications, one needs to learn a dynamical system from its solutions sampled at a finite number of time points. The learning problem is often formulated as an optimization problem over a chosen function class. However, in the…

Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…

Applications of machine learning tools to problems of physical interest are often criticized for producing sensitivity at the expense of transparency. To address this concern, we explore a data planing procedure for identifying combinations…

This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the…

Generative models of expressive piano performance are usually assessed by comparing their predictions to a reference human performance. A generative algorithm is taken to be better than competing ones if it produces performances that are…

Perceptual sound matching (PSM) aims to find the input parameters to a synthesizer so as to best imitate an audio target. Deep learning for PSM optimizes a neural network to analyze and reconstruct prerecorded samples. In this context, our…

Music composition using digital audio sequence editors is increasingly performed in a visual workspace where sound complexes are built from discrete sound objects, called gestures that are arranged in time and space to generate a continuous…

In this paper, we focus on approximating a natural class of functions that are compositions of smooth functions. Unlike the low-dimensional support assumption on the covariate, we demonstrate that composition functions have an intrinsic…

In this paper we present mathematical and physical models to be used in the analysis of the problem of intonation of musical instruments such as guitars, mandolins and the like, i.e., we study how to improve the tuning on these instruments.…

Small random perturbations may have a dramatic impact on the long time evolution of dynamical systems, and large deviation theory is often the right theoretical framework to understand these effects. At the core of the theory lies the…

In piano playing, different ways of touch lead to different tones. The effects of changing forces on keys are presented by changing interaction between hammer and string. The thesis focuses on several important variables in hammer-string…

Independently trained machine learning models tend to learn similar features. Given an ensemble of independently trained models, this results in correlated predictions and common failure modes. Previous attempts focusing on decorrelation of…

Diffusion models have been widely used in the generative domain due to their convincing performance in modeling complex data distributions. Moreover, they have shown competitive results on discriminative tasks, such as image segmentation.…

Recent AI-driven step-function advances in several longstanding problems in music technology are opening up new avenues to create the next generation of music education tools. Creating personalized, engaging, and effective learning…

Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales. Fortunately, most music is also highly structured and can be represented as…

The development of autonomous robotic systems that can learn from human demonstrations to imitate a desired behavior - rather than being manually programmed - has huge technological potential. One major challenge in imitation learning is…

Physics-based and first-principles models pervade the engineering and physical sciences, allowing for the ability to model the dynamics of complex systems with a prescribed accuracy. The approximations used in deriving governing equations…

Advances in neural network design and the availability of large-scale labeled datasets have driven major improvements in piano transcription. Existing approaches target either offline applications, with no restrictions on computational…

Manual sound design with a synthesizer is inherently iterative: an artist compares the synthesized output to a mental target, adjusts parameters, and repeats until satisfied. Iterative sound-matching automates this workflow by continually…