Frank Heyen

Abstract

We propose a visual approach for interactive, AI-assisted composition that serves as a compromise between fully automatic and fully manual composition. Instead of generating a whole piece, the AI takes on the role of an assistant that generates short melodies for the composer to choose from and adapt. In an iterative process, the composer queries the AI for continuations or alternative fill-ins, chooses a suggestion, and adds it to the piece. As listening to many suggestions would take time, we explore different ways to visualize them, to allow the composer to focus on the most interesting-looking melodies. We also present the results of a qualitative evaluation with five composers.

Abstract

We contribute two design studies for augmented reality visualizations that support learning musical instruments. First, we designed simple, glanceable encodings for drum kits, which we display through a projector. As second instrument, we chose guitar and designed visualizations to be displayed either on a screen as an augmented mirror or an an optical see-through AR headset. These modalities allow us to also show information around the instrument and in 3D. We evaluated our prototypes through case studies and our results demonstrate the general effectivity and revealed design-related and technical limitations.

Abstract

We propose a data-driven approach to music instrument practice that allows studying patterns and long-term trends through visualization. Inspired by life logging and fitness tracking, we imagine musicians to record their practice sessions over the span of months or years. The resulting data in the form of MIDI or audio recordings can then be analyzed sporadically to track progress and guide decisions. Toward this vision, we started exploring various visualization designs together with a group of nine guitarists, who provided us with data and feedback over the course of three months.

Abstract

We contribute an interactive visual frontend to live coding environments, which allows live coders and performers to influence the behavior of their code more quickly and efficiently. Users can trigger actions and change parameters via instruments, buttons, and sliders, instead of only inside the code. For instance, toggling a loop or controlling a fading effect through mouse or touch interaction on a screen is faster than editing code. While this kind of control has already been possible with hardware MIDI devices, we provide a more accessible, easy-to-use, and customizable alternative that only requires a web browser. With examples, we show how users perform live-coded music faster and more easily with our design compared to using pure code.

Abstract

Immersive analytics often takes place in virtual environments which promise the users immersion. To fulfill this promise, sensory feedback, such as haptics, is an important component, which is however not well supported yet. Existing haptic devices are often expensive, stationary, or occupy the user’s hand, preventing them from grasping objects or using a controller. We propose PropellerHand, an ungrounded hand-mounted haptic device with two rotatable propellers, that allows exerting forces on the hand without obstructing hand use. PropellerHand is able to simulate feedback such as weight and torque by generating thrust up to 11 N in 2-DOF and a torque of 1.87 Nm in 2-DOF. Its design builds on our experience from quantitative and qualitative experiments with different form factors and parts. We evaluated our prototype through a qualitative user study in various VR scenarios that required participants to manipulate virtual objects in different ways, while changing between torques and directional forces. Results show that PropellerHand improves users’ immersion in virtual reality. Additionally, we conducted a second user study in the field of immersive visualization to investigate the potential benefits of PropellerHand there.

Abstract

The logos of metal bands can be by turns gaudy, uncouth, or nearly illegible. Yet, these logos work: they communicate sophisticated notions of genre and emotional affect. In this paper we use the design considerations of metal logos to explore the space of "illegible semantics": the ways that text can communicate information at the cost of readability, which is not always the most important objective. In this work, drawing on formative visualization theory, professional design expertise, and empirical assessments of a corpus of metal band logos, we describe a design space of metal logos and present a tool through which logo characteristics can be explored through visualization. We investigate ways in which logo designers imbue their text with meaning and consider opportunities and implications for visualization more widely.

Abstract

We propose a visual approach for AI-assisted music composition, where the user interactively generates, selects, and adapts short melodies. Based on an entered start melody, we automatically generate multiple continuation samples. Repeating this step and in turn generating continuations for these samples results in a tree or graph of melodies. We visualize this structure with two visualizations, where nodes display the piano roll of the corresponding sample. By interacting with these visualizations, the user can quickly listen to, choose, and adapt melodies, to iteratively create a composition. A third visualization provides an overview over larger numbers of samples, allowing for insights into the AI's predictions and the sample space.

Abstract

Dimensionality Reduction (DR) is a popular technique that is often used in Machine Learning and Visualization communities to analyze high-dimensional data. The approach is empirically proven to be powerful for uncovering previously unseen structures in the data. While observing the results of the intermediate optimization steps of DR algorithms, we coincidently discovered the artistic beauty of the DR process. With enthusiasm for the beauty, we decided to look at DR from a generative art lens rather than their technical application aspects and use DR techniques to create artwork. Particularly, we use the optimization process to generate images, by drawing each intermediate step of the optimization process with some opacity over the previous intermediate result. As another alternative input, we used a neural-network model for face-landmark detection, to apply DR to portraits, while maintaining some facial properties, resulting in abstracted facial avatars. In this work, we provide such a collection of such artwork.

Abstract

Immersive analytics is a fast growing field that is often applied in virtual reality (VR). VR environments often lack immersion due to missing sensory feedback when interacting with data. Existing haptic devices are often expensive, stationary, or occupy the user’s hand, preventing them from grasping objects or using a controller. We propose PropellerHand, an ungrounded hand-mounted haptic device with two rotatable propellers, that allows exerting forces on the hand without obstructing hand use. PropellerHand is able to simulate feedback such as weight and torque by generating thrust up to 11 N in 2-DOF and a torque of 1.87 Nm in 2-DOF. Its design builds on our experience from quantitative and qualitative experiments with different form factors and parts. We evaluated our final version through a qualitative user study in various VR scenarios that required participants to manipulate virtual objects in different ways, while changing between torques and directional forces. Results show that PropellerHand improves users’ immersion in virtual reality.

Abstract

We propose ClaVis, a visual analytics system for comparative analysis of classification models. ClaVis allows users to visually compare the performance and behavior of tens to hundreds of classifiers trained with different hyperparameter configurations. Our approach is plugin-based and classifier-agnostic and allows users to add their own datasets and classifier implementations. It provides multiple visualizations, including a multivariate ranking, a similarity map, a scatterplot that reveals correlations between parameters and scores, and a training history chart. We demonstrate the effectivity of our approach in multiple case studies for training classification models in the domain of natural language processing.