Papers by Athanasios Manitsaris
IGI Global eBooks, Jan 18, 2011
HAL (Le Centre pour la Communication Scientifique Directe), 2012
Le présent article propose une méthodologie de vision par ordinateur pour la reconnaissance simul... more Le présent article propose une méthodologie de vision par ordinateur pour la reconnaissance simultanée des gestes musicaux et complexes des doigts qui sont effectués dans l'espace sans instrument de musique matériel. Les techniques d'analyse d'images sont appliquées pour segmenter la main ainsi que pour détecter et identifier les doigts dans une vidéo. La reconnaissance et la prédiction des gestes des doigts se basent sur la modélisation stochastique des caractéristiques de haut niveau à l'aide des Modèles de Markov Cachés (MMC) et des Modèles de Mélanges Gaussiens (MMG). Des techniques d'invariance d'échelle et de rotation ont été appliquées. Cet article propose également une méthodologie de mise en correspondance des gestes des doigts avec des paramètres sonores pour le contrôle gestuel du son. Les applications concernent directement la composition de la musique contemporaine et en général les arts du spectacle.
A Topic Map Editor and Navigation Tool
International Conference WWW/Internet, 2004
An Automatic Indicator of the Reusability of Learning Objects Based on Metadata That Satisfies Completeness Criteria
Communications in computer and information science, 2010
The search for learning objects in open repositories is currently a tedious task, owing to the va... more The search for learning objects in open repositories is currently a tedious task, owing to the vast amount of resources available and the fact that most of them do not have associated ratings to help users make a choice. In order to tackle this problem, we propose a reusability indicator, which can be calculated automatically using the metadata that describes the objects, allowing us to select those materials most likely to be reused. In order for this reusability indicator to be applied, metadata records must reach a certain amount of ...
Finding the optimum training solution for Byzantine music recognition — A Max/Msp approach
This paper presents a methodology implementation of a turn-key training system for music (singing... more This paper presents a methodology implementation of a turn-key training system for music (singing voice). The implementation took place with Max/Msp development software. Initially we create a small corpus of anthems for testing purposes by recording four(4) small hymns. Each hymn is been performed three(3) times from the same chanter. The reason of that repetition answers the purpose of finding the best performance(s) - therefore called optimum solution(s) - of the hymns. The process starts by extracting time series vectors from recorded wav files. After the extraction a statistical method for cross validation, called Jackknife, is applied in order to find the optimum solution(s) which will be used to train the system. Once the optimum solution(s) is(are) found, the system is ready to be trained. The training and recognition procedures takes place in real time via intelligent techniques which are a combination of Hidden Markov Models(HMM) and Dynamic Time Wrapping(DTW) algorithms. The evaluation of the system takes place simultaneously with Jackknife highlight and the optimum training solution is been highlighted at the same time. Precision and Recall metrics, are being estimated in order to validate the use of correct singing performance.
IGI Global eBooks, Jan 18, 2011
HAL (Le Centre pour la Communication Scientifique Directe), 2012
Le présent article propose une méthodologie de vision par ordinateur pour la reconnaissance simul... more Le présent article propose une méthodologie de vision par ordinateur pour la reconnaissance simultanée des gestes musicaux et complexes des doigts qui sont effectués dans l'espace sans instrument de musique matériel. Les techniques d'analyse d'images sont appliquées pour segmenter la main ainsi que pour détecter et identifier les doigts dans une vidéo. La reconnaissance et la prédiction des gestes des doigts se basent sur la modélisation stochastique des caractéristiques de haut niveau à l'aide des Modèles de Markov Cachés (MMC) et des Modèles de Mélanges Gaussiens (MMG). Des techniques d'invariance d'échelle et de rotation ont été appliquées. Cet article propose également une méthodologie de mise en correspondance des gestes des doigts avec des paramètres sonores pour le contrôle gestuel du son. Les applications concernent directement la composition de la musique contemporaine et en général les arts du spectacle.
A Topic Map Editor and Navigation Tool
International Conference WWW/Internet, 2004
An Automatic Indicator of the Reusability of Learning Objects Based on Metadata That Satisfies Completeness Criteria
Communications in computer and information science, 2010
The search for learning objects in open repositories is currently a tedious task, owing to the va... more The search for learning objects in open repositories is currently a tedious task, owing to the vast amount of resources available and the fact that most of them do not have associated ratings to help users make a choice. In order to tackle this problem, we propose a reusability indicator, which can be calculated automatically using the metadata that describes the objects, allowing us to select those materials most likely to be reused. In order for this reusability indicator to be applied, metadata records must reach a certain amount of ...
Finding the optimum training solution for Byzantine music recognition — A Max/Msp approach
This paper presents a methodology implementation of a turn-key training system for music (singing... more This paper presents a methodology implementation of a turn-key training system for music (singing voice). The implementation took place with Max/Msp development software. Initially we create a small corpus of anthems for testing purposes by recording four(4) small hymns. Each hymn is been performed three(3) times from the same chanter. The reason of that repetition answers the purpose of finding the best performance(s) - therefore called optimum solution(s) - of the hymns. The process starts by extracting time series vectors from recorded wav files. After the extraction a statistical method for cross validation, called Jackknife, is applied in order to find the optimum solution(s) which will be used to train the system. Once the optimum solution(s) is(are) found, the system is ready to be trained. The training and recognition procedures takes place in real time via intelligent techniques which are a combination of Hidden Markov Models(HMM) and Dynamic Time Wrapping(DTW) algorithms. The evaluation of the system takes place simultaneously with Jackknife highlight and the optimum training solution is been highlighted at the same time. Precision and Recall metrics, are being estimated in order to validate the use of correct singing performance.
Real-time recognition and online characterization of singing voice in Byzantine Music
HAL (Le Centre pour la Communication Scientifique Directe), Oct 20, 2014
We present a system for recognition and comparison of acoustic signals of singing voices, aiming ... more We present a system for recognition and comparison of acoustic signals of singing voices, aiming at the sensorimotor learning of Byzantine music. Οur system is trained with chants performed by the expert and it recognizes any of the interpretations (expert/learner) from a small corpus. Τhe system can evaluate in real time the distance of the performances. The results are satisfying, regarding (a) the training of expert model with the fundamental frequency (pitch) F0 and the MFCC coefficients showing in parallel the optimum combination for training (b) regarding the recognition of the trainee’s singing voice, c) the real-time estimation of the distance between expert’s and learner’s performance.
Second Report on User Requirements Identification and Analysis - FP7 i-Treasures Deliverable 2.3
Second Report on User Requirements Identification and Analysis - FP7 i-Treasures Deliverable 2.3
Final Report on ICH Capture and Analysis - FP7 i-Treasures Deliverable 3.3
Final Version of ICH Capture and Analysis Modules - FP7 i-Treasures Deliverable 3.4
Evaluating an Early Motion Planning Feedforward Sensorimotor Mechanism for 2D Sketching
Proceedings of the 31st European Conference on Cognitive Ergonomics, 2019
Movement-based interactive systems, and gesture recognition in general, can contribute to the hum... more Movement-based interactive systems, and gesture recognition in general, can contribute to the human learning of motor skills. This paper presents the design and initial evaluation of a sensori-motor learning mechanism that provides on-line feedforward to the user when s/he repeats a gesture. This mechanism is based on real time statistical comparison between the input and reference gesture as well as on early motion planning principles that generate the feedforward. It has been implemented for improving the motor control in 2D sketching. 14 participants were appointed to evaluate whether this mechanism has the ability to impart motor skills.
IEEE Intelligent Systems, 2018
Intangible Cultural Heritage (ICH) creations include, amongst other, music, dance, singing, theat... more Intangible Cultural Heritage (ICH) creations include, amongst other, music, dance, singing, theatre, human skills and craftsmanship. These cultural expressions are usually transmitted orally and/or using gestures and are modified over a period of time, through a process of collective recreation. As the world becomes more interconnected and many different cultures come into contact, local communities run the risk of losing important elements of their ICH, while young people find it difficult to maintain the connection with the cultural heritage treasured by their elders. In this paper, we present a novel holistic approach for the safeguarding and transmission of ICH that goes beyond the mere digitization of ICH content. Based on multisensory technology for the capturing of ICH, the proposed approach enables the generation of completely novel cultural content. High-level semantics are extracted from the acquired data, enabling researchers to identify possible implicit or hidden correlations between different ICH expressions or interpretation styles and study the evolution of a specific ICH. This data, coupled with other cultural resources, is accessible through the i-Treasures Web-platform, which provides the means for supporting knowledge exchange between researchers as well as know-how transmission from ICH bearers to apprentices.
On mapping emotional states and implicit gestures to sonification output from the 'Intangible Musical Instrument
Proceedings of the 3rd International Symposium on Movement and Computing, 2016
Sonification is an interdisciplinary field of research, aiming at generating sound from data base... more Sonification is an interdisciplinary field of research, aiming at generating sound from data based on systematic, objective and reproducible transformations. Towards this direction, expressive gestures play an important role in music performances facilitating the artistic perception by the audience. Moreover, emotions are linked with music, as sound has the ability to evoke emotions. In this vein, a combinatory approach which aims at gesture and emotion sonification in the context of music composition and performance is presented here. The added value of the proposed system is that both gesture and emotion are able to continuously manipulate the reproduced sound in real-time.
Wind integration into an electricity network
Human resource management and productivity of the computer aided design systems in Northern Greece
Uploads
Papers by Athanasios Manitsaris