Portugal

Generative models for singing voice have been mostly concerned with the task of “singing voice synthesis,” i.e., to produce singing voice waveforms given musical scores and text lyrics. In this work, we explore a novel yet challenging alternative: singing voice generation without pre-assigned scores and lyrics, in both training and inference time. In particular, we outline three such generation schemes, and propose a pipeline to tackle these new tasks. Moreover, we implement such models using generative adversarial networks and evaluate them both objectively and subjectively.

ICCC&#39;20

Score and Lyrics-Free Singing Voice Generation

singing voice generation

generative models

deep learning

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020

technical paper

Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviours that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalising what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.


ICCC'20

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.
Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviors that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalizing what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.



We consider the challenge of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. Collaborative dialogue is distinct from chit-chat in that it is knowledge building, each utterance provides just enough information to add specificity and reduce ambiguity without limiting the conversation. We use concepts from information theory to define a narrative arc function which models dialogue progression. We demonstrate that this function can be used to modulate a generative conversation model and make it produce more interesting dialogues, compared to baseline outputs. We focus on two modes of modulation: reveal and conceal. Empirically, we show how the narrative arc function can model existing dialogues and shape conversation models towards either mode. We conclude with quantitative evidence suggesting that these modulated models provide interesting and engaging dialogue partners for improvisational theatre performers.

Shaping the Narrative Arc: Information-Theoretic Collaborative Dialogue

The Creative Systems Framework (CSF) formalises creativity as search through a space of concepts.  As a formal account of Margaret Boden’s descriptive hierarchy of creativity, it is at the basis of multiple studies dealing with diverse aspects ofComputational Creativity (CC) systems. However, the CSF at present neither formalises action nor action selection during search, limiting its use in analysing creative processes.  We extend the CSF by explicitly modelling these missing components in the search space traversal function.  We furthermore integrate the distinction between a concept and an artefact, and provide stopping criteria for creative search.  Our extension,  the  Creative  Action  Selection  Framework  (CASF),  is informed by previous studies in CC and draws on concepts from Markov Decision Processes (MDPs). It allows us to de-scribe a creative system as an agent selecting actions based on the value, validity and novelty of concepts and artefacts. TheCASF brings more analytical depth for creative systems that can be modelled as utilising an action selection procedure.

Action Selection in the Creative Systems Framework

"This paper presents a domain independent framework for discussing human–computer co-creativity. It expands on Rhodes’ (1961) four perspectives on creativity
and their later adaptations to socio-cultural views of creativity and computational creativity. The new framework allows the attribution of creativity not only to individual creators but to a collective of creators, recognising the importance of meta-level communication to the creative collaboration, and the variety of creative
contributions that emerge during a co-creative process. It also elaborates on the different communities and contexts surrounding co-creative collaboration and thus facilitates the analysis, evaluation and study of human–computer co-creativity by allowing researchers to describe and situate their work in the field."

Five C’s for Human–Computer Co-Creativity — An Update on Classical Creativity Perspectives

Rosetta Code provides improv theatre performers with artificial intelligence (AI)-based technology to perform shows understandable across many different languages. We combine speech recognition, improv chatbots and language translation tools to enable improvisers to communicate with each other while being understood—or comically misunderstood—by multilingual audiences. We describe the technology underlying Rosetta Code, detailing the speech recognition, machine translation, text generation and text-to-speech subsystems. We then describe scene structures that feature the system in performances in multilingual shows (9 languages). We provide evaluative feedback from performers, audiences, and critics. From this feedback, we draw analogies between surrealism, absurdism, and multilingual AI improv. Rosetta Code creates a new form of language-based absurdist improv. The performance re- mains ephemeral and performers of different languages can express themselves and their culture while accommodating the linguistic diversity of audiences.

Rosetta Code: Improv in any language

"This paper introduces the notion ‘post-creativity’ as a reference point for discussing the ways in which the computational simulation of creativity perpetually seems to hinge upon conceptions of creativity that are both much-too-human and non-contingent. Taking issue with the often implicit idea within the artificial creativity-
agenda that creativity somehow exists before the fact, this paper, drawing upon Michel Foucault’s notion of the ‘dispositif’, insists that we must keep a steady eye on the historicity of the ideas and practices of ‘creativity’ in order to fully comprehend the ways in which computational/artificial creativity is part and parcel of the perpetual re-creation of creativity and hence, at best, contributing to a conceptual reverse-engineering of‘creativity’."

Post-creativity and AI: Reverse-engineering our Conceptual Landscapes of Creativity

In this presentation, we give an overview of the system that changes country flags based on trendy topics retrieved from news titles. 

Ever-changing Flags: Modifying National Symbols

The computational generation of visual representation of concepts is a topic that has deserved attention in Computational Creativity. One technique that is often used is visual blending – using two images to produce a third. However, visual blending on its own does not necessarily have a strong conceptual grounding. In this paper, we propose that visual conceptual blending be used for concept representation – a visual blend complemented by conceptual layer developed through elaboration. We outline a model for visual conceptual blending that can be instantiated in a computational system.

Let's Figure This Out: A Roadmap for Visual Conceptual Blending

Co-creative systems are useful in fostering creativity, often leading to unexpected results. Despite this, the relation between user and system is complex. The level of autonomy given to the system directly influences its potential for creative behaviour and degree of contribution to the cooperation with the user. In this paper, we present our efforts to instil a more creative behaviour to an existing visual blending system – Emojinating. In order to do so, we integrate two functionalities: self-evaluation and context-adaptation.

Emojinating Co-Creativity: Integrating Self-Evaluation and Context-Adaptation

"In this paper we consider the notion of dialogic creative ar- tificial intelligence (DCAI) systems, where co-creativity be- tween a human user and a computational system is supported through dialogic interaction. By dialogue we mean both tra- ditional language-based communication for explicit critique and persuasion (dialogue about creative artefacts) as well as a broader potentially non-linguistic notion of dialogue that emerges through the exchange of suggestions and changes (dialogue through creative artefacts). To capture this, we de- fine DCAI as occurring when both system and user are able to influence each others’ creative objectives. The paper mo- tivates our pursuit of dialogic interaction and provides some explanation of why we have defined it through its impacts rather than its mechanism of action. We provide two anal- yses to support our argument: an exploration of a commer- cial creativity support tool that has an extensive vocabulary for describing artefacts abstractly but does not meet our def- inition of dialogic interaction, and a case study of a creative interaction between two human professionals that exhibits di- alogic interaction throughout. For the latter we consider how studies of human-human co-creation can offer non-obvious design concepts that might be applied to co-creative DCAI systems.
"

A Speculative Exploration of the Role of Dialogue in Human-Computer Co-creation

We aim to help bridge the research fields of generative deep learning and computational creativity by way of the creative AI community, and to advocate the common objective of more creatively autonomous generative learning systems. We argue here that generative deep learning models are inherently limited in their creative abilities because of a focus on learning for perfection. To highlight this, we present a series of techniques which actively diverge from standard usage of deep learning, with the specific intention of producing novel and interesting artefacts. We end by describing how a two-way bridge between the research fields could be built.

Score and Lyrics-Free Singing Voice Generation

Downloads

Next from ICCC'20

Shaping the Narrative Arc: Information-Theoretic Collaborative Dialogue

Similar lecture

Negative-Aware Training: Be Aware of Negative Samples

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Score and Lyrics-Free Singing Voice Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ICCC'20

Shaping the Narrative Arc: Information-Theoretic Collaborative Dialogue

Similar lecture

Negative-Aware Training: Be Aware of Negative Samples

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads