Kosmas Kritsis

Kosmas Kritsis
Institute for Language and Speech Processing | ISLP · Voice and Sound Technology

M.Sc. Sound and Music Computing

About

13
Publications
2,924
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
94
Citations
Additional affiliations
September 2013 - November 2013
University of Strasbourg
Position
  • Research Assistant (Erasmus Internship)
Education
September 2015 - September 2016
University Pompeu Fabra
Field of study
  • Sound and Music Computing
September 2011 - June 2012
University Carlos III de Madrid
Field of study
  • Computer Science
September 2010 - July 2015

Publications

Publications (13)
Preprint
Full-text available
Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity. However, they suffer from training stability issues as well as incorrect alignment of the intermediate acoustic representation with the input text sequence. In this work, we introduce Regotron, a regularized version of...
Article
Full-text available
Tourism is a phenomenon that dates back to ancient times. Ancient Greek philosophers recognised, adopted, and promoted the concept of rest-based tourism. Ecotourism is a particular type of tourism that connects with activities that take place in nature, without harming it, along with the herbal and animal wealth. According to estimates, the global...
Article
Automatically synthesizing dance motion sequences is an increasingly popular research task in the broader field of human motion analysis. Recent approaches have mostly used recurrent neural networks (RNNs), which are known to suffer from prediction error accumulation, usually limiting models to synthesize short choreographies of less than 100 poses...
Article
Full-text available
Plant identification from images has become a rapidly developing research field in computer vision and is particularly challenging due to the morphological complexity of plants. The availability of large databases of plant images, and the research advancements in image processing, pattern recognition and machine learning, have resulted in a number...
Article
Full-text available
Jazz improvisation on a given lead sheet with chords is an interesting scenario for studying the behaviour of artificial agents when they collaborate with humans. Specifically in jazz improvisation, the role of the accompanist is crucial for reflecting the harmonic and metric characteristics of a jazz standard, while identifying in real-time the in...
Conference Paper
Full-text available
We present a web-based real-time application that enables gestural interaction with virtual instruments for musical expression. Skeletons of the users are tracked by a Kinect sensor, while the performance of the virtual instruments is accomplished using gestures inspired from their corresponding physical counterparts. The application supports the v...
Article
Full-text available
Envisioned communication densities in Internet of Things (IoT) applications are increasing continuously. Because these wireless devices are often battery powered, we need specific energy efficient (low-power) solutions. Moreover, these smart objects use low-cost hardware with possibly weak links, leading to a lossy network. Once deployed, these Low...
Article
Verification of theoretical analysis is a vital step to the development of an application or a protocol for wireless networks. Most of proposals are evaluated through mathematical analysis followed by either simulation or experimental validation campaigns. In this paper, we analyze a large set of statistics on articles published (i.e. 674 papers in...

Network

Cited By

Projects

Project (1)
Project
iMuSciCA will – through engagement in music activities – support mastery of core academic content on STEM subjects (Physics, Geometry, Mathematics, and Technology) for secondary school students (aged 12-16) alongside with the development of their creativity and deeper learning skills. To reach this goal, iMuSciCA introduces new methodologies and innovative technologies supporting active, discovery-based, collaborative, personalised, and more engaging learning. These technologies provide students and teachers with opportunities for collaboration, co-creation, and collective knowledge building. In particular, iMuSciCA will deliver a suite of software tools and services on top of market-ready new enabling technologies integrated on a web-based platform. These include: a 3D design environment for personalized virtual musical instruments; advanced music generation and processing technologies to apply and interpret related physics and mathematics principles; gesture and pen-enabled multimodal interaction functionality for music co-creation and performance; and 3D printing for realizing the actual/tangible physical instrument. The platform will be complemented with a suite of interdisciplinary project/problem based educational scenarios for STEAM integrating innovative and stimulating methods in teaching and learning. The iMuSciCA framework will be pilot-tested and evaluated in real learning contexts by a substantial number of students and teachers in three European countries (Belgium, Greece, and France). The project will be implemented in close collaboration of academic and industrial partners, bringing together existing technologies and promoting ground-breaking research in STEAM pedagogy and the involved core enabling technology. As such, iMuSciCA will be a pioneering approach using music for fostering creativity and deeper learning, thereby setting new grounds in the European curricula of STEAM.