This paper proposes that the ability to generate diverse outputs in response to a single prompt is necessary for text-to-image models to become more effective creativity support tools. It formalises the problem of measuring the diversity of generated text and images, with an emphasis on interactive, exploratory use in open-ended and creative tasks. It suggests, motivated by research in the psychology of creativity, that diversity should sit alongside image quality and fit-to-prompt as critical measures in this setting. The paper adapts several diversity measures from the literature to this task, then explores how they compare to human diversity ratings. These evaluations show that algorithmic measures of diversity can be a useful proxy for human ratings, with both declining in accuracy as the difficulty of the task increases. The paper concludes with an exploratory qualitative analysis of the factors involved in human diversity judgments to guide future research in this emerging area.

In creativity support and computational co-creativity contexts, the task of discovering appropriate prompts for use with text-to-image generative models remains difficult. In many cases the creator wishes to evoke a certain impression with the image, but the task of conferring that succinctly in a text prompt poses a challenge: affective language is nuanced, complex, and very much influenced by the training trajectory of each specific AI model. In this work we introduce a method for generating images conditioned on desired affect, quantified using a psychometrically validated three-component approach, that can be combined with conditioning on text descriptions. We first train a neural network for estimating the affect content of text and images from semantic embeddings, and then demonstrate how this can be used to exert control over a variety of generative models. We show examples of how affect modifies the outputs, provide quantitative and qualitative analysis of its capabilities, and discuss possible extensions and use cases. We also show the capacity of our affect-guided generation to output images which re-frame or extend ideas in original ways that may not have been immediately apparent to the human prompt-writer.

Recent advances in text-conditioned generative models have provided us with neural networks capable of creating images of astonishing quality, be they realistic, abstract, or even creative. These models have in common that (more or less explicitly) they all aim to produce a high-quality one-off output given certain conditions, and in that they are not well suited for a creative collaboration framework. Drawing on theories from cognitive science that model how professional designers and artists think, we argue how this setting differs from the former and introduce CICADA: a Collaborative, Interactive Context-Aware Drawing Agent. CICADA uses a vector-based synthesis-by-optimisation method to take a partial sketch (such as might be provided by a user) and develop it towards a goal by adding and/or sensibly modifying traces. Given that this topic has been scarcely explored, we also introduce a way to evaluate desired characteristics of a model in this context by means of proposing a diversity measure. CICADA is shown to produce sketches of quality comparable to a human user's, enhanced diversity and most importantly to be able to cope with change by continuing the sketch minding the user's contributions in a flexible manner.

This paper presents an analysis of the user experience of Reframer, a novel human-AI drawing interface designed with the iterative and reflective nature of creativity in mind. Collaboration with Reframer occurs in real time, with the user and the system drawing together concurrently. This approach is inspired by theories of creativity as being more problem-framing than problem-solving, and contrasts with the automated one-shot end-to-end workflows of most generative AI models. A 12-participant qualitative exploratory study of the capabilities of our prototype is detailed, as well as a thematic analysis of user attitudes towards drawing with it. The paper then describes two modified prototypes and a second 32-participant comparative study revealing how interface variations evoke differences in user attitudes and experiences. It concludes by proposing a model that characterises the conditions under which users experience co-creative AI as a collaborator, rather than a non-agentive tool.

Over the past few years, rapid developments in AI have resulted in new models capable of generating high-quality images and creative artefacts, most of which seek to fully automate the process of creation. In stark contrast, creative professionals rely on iteration—to change their mind, to modify their sketches, and to re-imagine. For that reason, end-to-end generative approaches limit application to real-world design workflows. We present a novel human-AI drawing interface called Reframer, along with a new survey instrument for evaluating co-creative systems. Based on a co-creative drawing model called the Collaborative, Interactive Context-Aware Design Agent (CICADA), Reframer uses CLIP-guided synthesis-by-optimisation to support real-time synchronous drawing with AI. We present two versions of Reframer’s interface, one that prioritises emergence and system agency and the other control and user agency. To begin exploring how these different interaction models might influence the user experience, we also propose the Mixed-Initiative Creativity Support Index (MICSI). MICSI rates co-creative systems along experiential axes relevant to AI co-creation. We administer MICSI and a short qualitative interview to users who engaged with the Reframer variants on two distinct creative tasks. The results show overall broad efficacy of Reframer as a creativity support tool, but MICSI also allows us to begin unpacking the complex interactions between learning effects, task type, visibility, control, and emergent behaviour. We conclude with a discussion of how these findings highlight challenges for future co-creative systems design.

When recorded in an enclosed room, a sound signal will most certainly get affected by reverberation. This not only undermines audio quality, but also poses a problem for many humanmachine interaction technologies that use speech as their input. In this paper, a new blind, two-stage dereverberation approach based in a generalized β-divergence as a fidelity term over a non-negative representation is proposed. The first stage consists of learning the spectral structure of the signal solely from the observed spectrogram, while the second stage is devoted to model reverberation. Both steps are taken by minimizing a cost function in which the aim is put either in constructing a dictionary or a good representation by changing the divergence involved. In addition, an approach for finding an optimal fidelity parameter for dictionary learning is proposed. An algorithm for implementing the proposed method is described and tested against state-of-the-art methods. Results show improvements for both artificial reverberation and real recordings.

When a signal is recorded in an enclosed room, it typically gets affected by reverberation. This degradation represents a problem when dealing with audio signals, particularly for applications involving automatic speech and/or speaker recognition. There are some approaches to deal with this issue that are quite satisfactory when multi-channel recordings or learning data are available, but this is not the general case in most human-computer interaction applications, and constructing a method that works well in a general context still poses a significant challenge. In this article, we propose a method based on convolutive nonnegative matrix factorization that mixes two penalizers in order to impose certain characteristics over the time-frequency components of the restored signal and the reverberant components. An algorithm for finding such a solution is described and tested. Comparisons of the results against state of the art methods are presented, showing significant improvement.