1,721,117 research outputs found
Introduction: Gaetano Salvemini: profile of a transnational intellectual
No full textIntroduction to the special issue dedicated to Salvemini's intellectual and political biograph
Computational Model of Entrainment within Small Groups of People: Toward Novel Approaches to KANSEI information Processing
No full textEthnic music audio documents: From preservation to fruition
No full textDespite the youthfulness of the musical recording technologies and the content, their preservation is already becoming an important issue to avoid the loss of precious ethno-musical cultural heritage recordings. These documents have a shorter life span compared to other cultural heritage materials and their maintenance and restoration introduce novel problems requiring different and original approaches. Ethnic music, in particular, is not based on score notation, thus the traditional music conservatories are unable to ‘‘preserve’’ the performance praxis. Therefore, in order to assure the long-term conservation of this musical culture, immediate interventions are necessary, conducted by recognized institutions and experts in the fields of musicology, cultural heritage, computer engi- neering, information and communication technology (ICT), and signal processing. The short life of the carriers, of the playing systems of the data, and the musical instruments, impose that these interventions are crucial, in order to avoid the permanent loss of the musical heritage which is already being heavily corrupted. In particular, for the audio restoration of musical instru- ments, the construction and the luthier’s know-how should be carefully considered as fundamental interdisciplinary information to help with signal processing and computational models; unfortunately, several musical instruments are no longer on the market. This is particularly true in the fields of ethnic and electro-acoustic music. The preservation presupposes the presence of several highly skilled experts, since the damages of a bad conservation or an inadequate restoration are usually irreversible. Conservation and restoration activities should be therefore planned and performed within agreed international standards and procedures and carried out within institutional environments. This is a challenge, which signal processing, sound and music computing, and ICT research can contribute significantly
Analysis of Dominance in Small Music Ensemble
No full textThis study addresses the application of the Multi-Scale Fuzzy Entropy Analysis to investigate dominance in small music ensemble. Taking a string quartet as the case for study, it confirms and extends previous results found in revealing that dominance over others may be achieved through the regulation of individual and group’s behavior complexit
Audio processing in a multimodal framework
No full textThe EyesWeb system (www.eyesweb.org) is an open platform for real-time multimodal processing. It has now reached a mature stage, and is being used both for research in multimodal interfaces and for applications such as naturally interacting systems for museum exhibits, performing arts, therapy and rehabilitation. This paper presents the latest development concerning audio processing in EyesWeb with a special focus on multimodal processing. The integrated audio processing support includes modules for the analysis and synthesis of audio streams, for musical processing through the MIDI protocol, and for interoperability with other audio processing platforms, technologies and standards. Advanced real-time audio support for the mapping of multimodal input into multimedia output is described in the paper
Keep it Simple: Handcrafting Feature and Tuning Random Forests and XGBoost to face the Affective Movement Recognition Challenge 2021
No full textIn this paper, we face the Affective Movement Recognition Challenge 2021 which is based on 3 naturalistic datasets on body movement, which is a fundamental component of everyday living both in the execution of the actions that make up physical functioning as well as in rich expression of affect, cognition, and intent. The datasets were built on deep understanding of the requirements of automatic detection technology for chronic pain physical rehabilitation, maths problem solving, and interactive dance contexts respectively. In particular, we will rely on a single, simple yet effective, approach able to be competitive with state-of-the-art results in the literature on all of the 3 datasets. Our approach is based on a two step procedure: first we will carefully handcraft features able to fully and synthetically represent the raw data and then we will apply Random Forest and XGBoost, carefully tuned with rigorous statistical procedures, on top of it to deliver the predictions. As requested by the challenge, we will report results in terms of three different metrics: accuracy, F1-score, and Matthew Correlation Coefficient
Evaluating Movement Quality Through Intrapersonal Synchronization
No full textWe present a method to measure intrapersonal synchronization of movement from motion capture data, and we show that our method is effective in classifying the level of skills of athletes performing karate kata. Our method is based on detecting relevant peaks of acceleration of limbs (arms and legs) and measuring their synchronization. We run a multiscale analysis, based on topological persistence, to rank the importance of peaks of acceleration. The resulting impulse signals are processed next with a multievent class synchronization algorithm, in order to define an overall synchronization index that scores the level of intrapersonal synchronization with a single scalar value. We build a basic multiclass classifier, which uses just the means of indexes computed on the different classes in the training set. We make a statistical analysis and a cross validation of the classifier on real data. Performances by athletes from three levels of skill have been recorded, classified by experts, and used to test our method. Cross validation of the classifier is performed by leave-one-out and bootstrap resampling. Results show that our method can classify correctly with very high probability (beyond ), while it succeeds on of the data used in cross validation
Modeling Multiple Temporal Scales of Full-body Movements for Emotion Classification
No full textThis work investigates classification of emotions from full-body movements by using a novel Convolutional Neural Network-based architecture. The model is composed of two shallow networks processing in parallel where the 8-bit RGB images obtained from time intervals of 3D-positional data are the inputs. One network performs a coarse-grained modelling in the time domain while the other one applies a fine-grained modelling. We show that combining different temporal scales into one architecture improves the classification results of a dataset composed of short excerpts of the performances of professional dancers who interpreted four affective states: anger, happiness, sadness, and insecurity. Additionally, we investigate the effect of data chunk duration, overlapping, the size of the input images and the contribution of several data augmentation strategies for our proposed method. Better recognition results were obtained when the duration of a data chunk was longer, and this was further improved by applying balanced data augmentation. Moreover, we test our method on other existing motion capture datasets and compare the results with prior art. In all of the experiments, our results surpassed the state-of-the-art approaches, showing that this method generalizes across diverse settings and contexts
- …
