he so-called “hubness” phenomenon is a general problem of machine learning in high dimensional data spaces. Hubs are data points which keep appearing unwontedly often in nearest neighbor lists of many other data points. This effect is particularly problematic in algorithms for similarity search, as the same “similar” objects are found over and over again. But it has also adverse effects for the many machine learning algorithms that make use of distance information. The effect has been shown to be a natural consequence of high dimensionality and as such is yet another aspect of the curse of dimensionality. The main goal of this project was to conduct an in-depth study of the hubness problem in the context of MIR.
CYBEREMOTIONS is a European IP (Large Scale Integrating Project) which focuses on the role of collective emotions in creating, forming and breaking-up e-communities. Understanding these phenomena is important in view of the growing role of ICT-mediated social interactions and some specific features of e-communities. The challenge of this interdisciplinary project is to combine psychological models of emotional interactions and algorithmic methods for detection and classification of human emotions in the Internet with probabilistic models of complex systems and data driven simulations based on heterogeneous emotionally-reacting agents.
MIReS was an EU FP7-funded 18-month project focusing on the future impact of music technology research on academia and industry. The project created a research roadmap of MIR field, by expanding its context and addressing challenges such as multimodal information, multiculturalism and multidisciplinarity.
Language varieties are a primary means of expressing a person's social affiliation and identity. Hence, computer systems that can adapt to the user by displaying a familiar socio-cultural identity are expected to raise the acceptance within certain contexts and target groups dramatically. However, current systems are far from achieving the fidelity required for realization of these benefits. For example, promising early results have been obtained in the context of speech synthesis through localized pronunciation, but it is clear that language variety is a multi-faceted concept that involves deviations from standard language on various linguistic levels. Our goal is to develop algorithmic methods that are capable of capturing and reproducing all major idiosyncrasies displayed by a language variety, be they syntactic, lexical or phonetic in nature. Conceptually, part of this task can be understood as a machine translation problem, which is, however, characterized by unique properties.
Quiew (quick review) ist ein Forschungsprojekt zur Entwicklung eines innovativen Online-Bewertungs- und Feedbacksystems für Produkte, Dienstleistungen und andere Objekte. Basierend auf der aus der Markt- und Konsumentenpsychologie stammenden Methode des Assoziationsgeflechts nach Kirchler und De Rosa (1996) wird ein computationelles System entwickelt zur automatischen Analyse und Gruppierung von sprachlichen Äußerungen (assoziativen Feedbacks), die zur Bewertung von Produkten, Diesntleistungen etc. abgegeben wurden.
In this project we develop core technology for a new kind of semantic search system that is able to automatically identify experts for clearly defined project tasks making use of textual similarities in expert and task profiles, and of models of explicit expert knowledge.
An important open research question in Music Information Retrieval (MIR) is the extraction of sound objects (e.g. a guitar chord, the beat of a bass drum, the bark of a dog) from polyphonic audio. Recent theoretical advances in mathematical signal processing indicate the possibility of a decisive improvement in identifying and extracting sound objects directly from the time-frequency plane. These mined sound objects can then automatically be organized into perceptually meaningful and easy to navigate sound libraries using the latest innovations in MIR based music similarity. Together this will form the core of a powerful new toolkit for audio manipulation with widespread applicability in fields like Sound Design, Computational Auditory Scene Analysis, Artefact Reduction or Audio Database Organisation.
IRIS (Integrating Research in Interactive Storytelling) is a European NoE (Network of Excellence) which aims at creating a virtual centre of excellence that will be able to achieve breakthroughs in the understanding of Interactive Storytelling and the development of corresponding technologies. Interactive Storytelling is a major endeavour to develop new media which could offer a radically new user experience, with a potential to revolutionise digital entertainment. The IRIS consortium involves ten partners in seven different countries in Europe.
In this project we aim at developing and implementing ontology-driven methods for domain-specific information extraction and retrieval.
In this project, we intend to go one step further and try to develop user-awareness and self-awareness through Theory of Mind (ToM) and Empathy in intelligent software agents or robots that have to take on complex interactive tasks. While context-awareness is based on "perception" of the environment, self-awareness is based in particular on registration of important "inner" states that can influence decisions. Time components, Theory of Mind and Empathy are aspects of self-awareness and user-awareness that have to be taken into account in this project.