Agent-based Unsupervised Deep Interactive 0-shot-learning Networks Optimising Machines’ Ontological Understanding of Sound
DFG (German Research Foundation) Reinhart Koselleck-Projekt
Soundscapes are a component of our everyday acoustic environment; we are always surrounded by sounds, we react to them, as well as creating them. While computer audition, the understanding of audio by machines, has primarily been driven through the analysis of speech, the understanding of soundscapes has received comparatively little attention.
AUDI0NOMOUS, a long-term project based on artificial intelligent systems, aims to achieve a major breakthroughs in analysis, categorisation, and understanding of real-life soundscapes. A novel approach, based around the development of four highly cooperative and interactive intelligent agents, is proposed herein to achieve this highly ambitious goal. Each agent will autonomously infer a deep and holistic comprehension of sound. A Curious Agent will collect unique data from web sources and social media; an Audio Decomposition Agent will decompose overlapped sounds; a Learning Agent will recognise an unlimited number of unlabelled sound; and, an Ontology Agent will translate the soundscapes into verbal ontologies.
AUDI0NOMOUS will open up an entirely new dimension of comprehensive audio understanding; such knowledge will have a high and broad impact in disciplines of both the sciences and humanities, promoting advancements in health care, robotics, and smart devices and cities, amongst many others.
Start date: 01.01.2021
Duration: 4 years
Huawei & University of Augsburg Joint Lab
The Huawei-University of Augsburg Joint Lab aims to bring together Affective Computing & Human-Centered Intelligence for Human-centred empathic interaction.
The Lehrstuhl for Embedded Intelligence in Health Care and Wellbeing is one of two Lehrstuhls in the collaboration.
Start date: 01.01.2020
Duration: 3 years
Laufzeit: 14 Monaten
Drittmittelgeber: ZIM, Bundesministerium für Wirtschaft und Energie (BMWi)
Zielsetzung des Projektes „KIRun“ ist die Entwicklung intelligenter Algorithmen, die Messdaten aus Training (GPS), Biomechanik (Inertialsensorik), Physiologie (Atem-/Herzfrequenz), Umgebungsgeräuschen (Laufuntergrund), Tonalität und Qualität der Sprache und Atmung, und gezielter Spracherfassung während des Laufens aufnehmen, verarbeiten und auswerten.
Hierzu müssen grundlegend neuartige Funktionalitäten erarbeitet beziehungsweise aus anderen Anwendungsfeldern in den Laufsport transferiert werden. Im Rahmen des Projektes sollen bestehende Technologien aus dem IoT-, Sensorik- und dem Audio-Bereich in den sportwissenschaftlichen Bereich transferiert werden und das Know-how der beteiligten Partner durch eine integrierte KI-Plattform kombiniert werden.
Paralinguistische Stimmcharakteristika bei Depression
Start date: 01.01.2020
Duration: 36 Months
Funding body: Deutsche Forschungsgemeinschaft (DFG)
Die Erklärung, Diagnostik, Vorhersage und Behandlung der Major Depression stellen nach wie vor zentrale Herausforderungen der Psychotherapieforschung dar.
Als neuer und innovativer Ansatz in der Diagnostik und Therapie der Depression erforscht die Paralinguistik Intonationsmerkmale wie Sprechpausen, Sprachrhythmus, Intonation, Tonhöhe und Lautstärke. In diesem interdisziplinären Projekt arbeiten die klinische Psychologie und Informatik zusammen, um über optimierte Algorithmen Depressionen anhand paralinguistischer Stimmcharakteristika (PSCs) möglichst gut zu erkennen, vorherzusagen und zu klären, inwieweit ein bestimmter Intonationsstil dazu beiträgt, die Depression aufrecht zu erhalten.
Darüber hinaus wollen wir die PSCs perspektivisch auch als Therapie einsetzen. Das bedeutet, dass Therapeuten nicht nur, wie gewohnt in der Depressionsbewältigung, mit ihren Patienten erarbeiten, was sie sich sagen, sondern auch wie. Ein Du schaffst das schon! mit leiser, monotoner und kraftloser Stimme wird nichts bewirken, da es nicht emotional überzeugend klingt. Wenn der Satz dagegen mit kraftvoller, deutlicher und dynamischer Stimme ausgesprochen wird, sind die Chance deutlich größer, dass sich damit auch ein Gefühl von Hoffnung und Optimismus auslösen lässt.
Das von der DFG geförderte Forschungsprojekt will die wissenschaftliche Grundlage hierfür schaffen. Dazu sollen Sprachproben mit Hilfe von maschinellem Lernen untersucht werden, um Intonationsunterschiede zwischen klinisch-depressiven und nicht-depressiven Personen zu erkennen. Wir werden Algorithmen entwickeln, mit deren Hilfe depressionsrelevante Intonations-Muster identifiziert werden können. Die gewonnenen Erkenntnisse sollen dann wiederum helfen, ein Intonations-fokussiertes Feedback-Training zu entwickeln, das Menschen mit Depressionen helfen soll, depressive Phasen zu bewältigen.
Affective loop in Socially Assistive Robotics as an Intervention Tool for Children with Autism
Start date: 01.09.2019
Duration: 36 Months
Funding body: EU, Erasmus Plus Strategic Partnership
Partners: Politechnika Gdanska, University of Hertfordshire, Istanbul Teknik Universitesi, Yeditepe University Vakif, Macedonian association for applied psychology & University of Augsburg
Description: The EMBOA project aims are the development of guidelines and practical evaluation of applying emotion recognition technologies in robot-supported intervention in children with autism.
Children with autism spectrum disorder (ASD) suffer from multiple deficits and limited social and emotional skills are among those that influence their ability to involve in interaction and communication. Limited communication occurs in human-human interactions and affects relations with family members, peers and therapists.
There are promising results in the use of robots in supporting the social and emotional development of children with autism. We do not know why children with autism are eager to interact with human-like looking robots and not with humans. Regardless of the reason, social robots proved to be a way to get through the social obstacles of a child and make him/her involved in the interaction. Once the interaction happens, we have a unique opportunity to engage a child in gradually building and practicing social and emotional skills.
In the project, we combine social robots that are already used in therapy for children with autism with algorithms for automatic emotion recognition. The EMBOA project goal is to confirm the possibility of the application (feasibility study), and, in particular, we aim to identify the best practices and obstacles in using the combination of the technologies. What we hope to obtain is a novel approach for creating an affective loop in child-robot interaction that would enhance interventions regarding emotional intelligence building in children with autism.
The lessons learned, summarized in the form of guidelines, might be used in higher education in all involved countries in robotics, computer science, and special pedagogy fields of study. The results will be disseminated in the form of training, multiple events, and to the general public by scientific papers and published reports. The project consortium is multidisciplinary and combines partners with competence in interventions in autism, robotics, and automatic emotion recognition from Poland, UK, Germany, North Macedonia, and Turkey.
The methodological approach includes systematic literature reviews and meta-analysis, data analysis based on statistical and machine learning approaches, as well as observational studies. We have planned a double-loop of observational studies. The first round is to analyse the application of emotion recognition methods in robot-based interaction in autism, and to compare diverse channels for observation of emotion symptoms in particular.
The lessons learned will be formulated in the form of guidelines. The guidelines will be evaluated with the AGREE (Appraisal of Guidelines, Research, and Evaluation) instrument and confirmed with the second round of observational studies. The objectives of our project match the Social Inclusion horizontal priority with regards to supporting the actions for improvement of learning performance of disadvantaged learners (testing of a novel approach for improvement of learning performances of children with autism).
Smart Environments for Person-centered Sustainable Work and Well-being
Start date: 01.01.2019
Duration: 36 Months
Funding body: EU Horizon 2020 Research & Innovation Action (RIA)
sustAGE will provide a paradigm shift in human machine interaction, building upon seven strategic technology trends, IoT, Machine learning, micro-moments, temporal reasoning, recommender systems, data analytics and gamification to deliver a composite system integrated with the daily activities at work and outside, to support employers and ageing employees to jointly increase well-being, wellness at work and productivity. The manifold contribution focuses on the support of the employment and later retirement of older adults from work and the optimization of the workforce management.
The sustAGE platform guides workers on work-related tasks, recommends personalized cognitive and physical training activities with emphasis on game and social aspects, delivers warnings regarding occupational risks and cares for their proper positioning in work tasks that will maximize team performance.
By combining a broad range of the innovation chain activities namely, technology R&D, demonstration, prototyping, pilots, and extensive validation, the project aims to explore how health and safety at work, continuous training and proper workforce management can prolongue older workers’ competitiveness at work. The deployment of the proposed technologies in two critical industrial sectors and their extensive evaluation will lead to a ground-breaking contribution that will improve the performance and quality of life at work and beyond for many ageing adult workers.
Holistic Deep Modelling for User Recognition and Affective Social Behaviour Sensing
Start date: 01.10.2018
Duration: 30 Months
Project paused: 01.05.2020 to 30.04.2021
Funding body: EU Horizon 2020 Marie Skłodowska-Curie action Individual Fellowship
The “Holistic Deep Modelling for User Recognition and Affective Social Behaviour Sensing” (HOL-DEEP-SENSE) project aims at augmenting affective machines such as virtual assistants and social robots with human-like acumen based on holistic perception and understanding abilities.
Social competencies comprising context awareress, salience detection and affective sensitivity present a central aspect of human communication, and thus are indispensable for enabling natural and spontaneous human-machine interaction. Therefore, with the aim to advance affective computing and social signal processing, we envision a “Social Intelligent Multi-modal Ontological Net” (SIMON) that builds on technologies at the leading edge of deep learning for pattern recognition. In particular, our approach is driven by multi-modal information fusion using end-to-end deep neural networks trained on large datasets, allowing SIMON to exploit combined auditory, visual and physiological analysis.
In contrast to standard machine learning systems, SIMON makes use of task relatedness to adapt its topology within a novel construct of subdivided neural networks. Through deep affective feature transformation, SIMON is able to perform associative domain adaptation via transfer and multi-task learning, and thus can infer user characteristics and social cues in a holistic context.
This new unified sensing architecture will enable affective computers to assimilate ontological human phenomena, leading to a step change in machine perception. This will offer a wide range of applications for health and wellbeing in future IoT-inspired environments, connected to dedicated sensors and consumer electronics.
By verifying the gains through holistic sensing, the project will show the true potential of the much sought-after emotionally and socially intelligent AI, and herald a new generation of machines with hitherto unseen skills to interact with humans via universal communication channels.
Start date: 01.05.2018
End date: 31.05.2021
Funding body: BMW AG
The project aims at real-time internet-scale sentiment analysis in unstructured multimodal data in the wild.
Training network on Automatic Processing of PAthological Speech
Start date: 01.11.2017
End date: 31.10.2021
Funding body: EU (Europäische Union)
There are an increasing number of people across Europe with debilitating speech pathologies (e.g., due to stroke, Parkinson’s, etc). These groups face communication problems that can lead to social exclusion. They are now being further marginalised by a new wave of speech technology that is increasingly woven into everyday life but which is not robust to atypical speech. TAPAS is proposing a programme of pathological speech research, that aims to transform the well-being of these people.
The TAPAS work programme targets three key research problems:
(a) Detection: We will develop speech processing techniques for early detection of conditions that impact on speech production. The outcomes will be cheap and non-invasive diagnostic tools that provide early warning of the onset of progressive conditions such as Alzheimer’s and Parkinson’s.
(b) Therapy: We will use newly-emerging speech processing techniques to produce automated speech therapy tools. These tools will make therapy more accessible and more individually targeted. Better therapy can increase the chances of recovering intelligible speech after traumatic events such a stroke or oral surgery.
(c) Assisted Living: We will re-design current speech technology so that it works well for people with speech impairments and also helps in making informed clinical choices. People with speech impairments often have other co-occurring conditions making them reliant on carers. Speech-driven tools for assisted-living are a way to allow such people to live more independently.
TAPAS adopts an inter-disciplinary and multi-sectorial approach. The consortium includes clinical practitioners, academic researchers and industrial partners, with expertise spanning speech engineering, linguistics and clinical science. All members have expertise in some element of pathological speech. This rich network will train a new generation of 15 researchers, equipping them with the skills and resources necessary for lasting success.
Remote Assessment of Disease and Relapse – Central Nervous System
Start date: 01.04.2016
End date: 31.03.2021
Funding body: EU (Europäische Union)
RADAR-CNS is a major research programme that is developing new ways of monitoring major depressive disorder, epilepsy, and multiple sclerosis using wearable devices and smartphone technology. RADAR-CNS aims to improve patients’ quality of life, and potentially to change how these and other chronic disorders are treated.
An Embedded Soundscape System for Personalised Wellness via Multimodal Bio-Signal and Speech Monitoring
Start date: 01.01.2018
End date: 31.12.2020
Funding body: The Bavarian State Ministry of Education, Science and the Arts in the framework of the Centre Digitisation.Bavaria (ZD.B)
The soundscape (the audible components of a given environment), is an omnipresence in daily-life. Yet research has shown, that elements of our acoustic soundscapes can negatively affect mental wellbeing.
Taking a dual analysis-synthesis approach this project, through multimodal feedback analysis, will explore the benefits of synthesised soundscape design and develop a ‘deep-listening’ personalised embedded system to improve human wellness. The project will explore questions pertaining to audible perception and develop novel methods for soundscape generation, informed by intelligent signal state monitoring.
Hier finden Sie eine Übersicht über vergangene Projekte.