Abstract: Whisper is a specific mode of speech characterized by turbulent airflow at the glottis level. Despite an increased effort in speech perception, the intelligibility of whisper in human communication is very high. An enormous acoustic mismatch between normally phonated (neutral) and whispered speech is the main reason why modern Automatic Speech Recognition (ASR) systems have significant drop of performances when applied to whisper. In this paper, we present an analysis in recognition of whisper using 2 machine-learning techniques: Hidden Markov Models (HMM) and Support Vector Machines (SVM). The experiments are conducted in both Speaker Dependent (SD) and Speaker Independent (SI) fashion for Whi-Spe speech database. The best neutral-trained whisper recognition accuracy in SD fashion (83.36%) is obtained in SVM framework. At the same time, HMM-based recognition gave the highest recognition accuracy in SI fashion (87.42%). The results in recognition of neutral speech are given as well.
Keywords: Automatic Speech Recognition; Hidden Markov Models; Support Vector Machines; Whispered speech; Whi-Spe speech database
Abstract: This study focuses on children’s cognitive capability within the framework of cognitive infocommunication. Speech processing works in quasi-parallel in time between hearing and speech comprehension. Hierarchical operations are decisive for elaboration of the speech signal. To test children’s speech processing quickly and reliably is of great importance both for language acquisition and for learning to read and write. Specific speech synthesis using sufficient, but not redundant spectral cues highlight hearing and global speech perception processes. 644 monolingual Hungarian children aged between 4 and 8 years participated in the study. 20 monosyllables were specially synthesized based on a set of pre-determined spectral values. Children were asked to repeat what they heard. The combination of speech synthesis as information and communication technology with the study of cognitive capabilities is a new direction in research and practice. Our results show that the great majority of children were confirmed to have good hearing (about 95%), while some children had a previously unknown hearing impairment. More than 30% of all children encountered speech perception deficit, despite good hearing. Digital technology including speech synthesis has reshaped both speech science and its cognitive connections to get closer to a proper interpretation of the mechanisms analyzed.
Keywords: synthesized speech; frequency cues; cognitive processes; evaluation of speech processing
Abstract: This paper presents an experimental assessment of the children’s receptivity to the human-like conversational robot MARKO. It reports on a production of a corpus that is composed of recordings of interaction between children, with cerebral palsy and similar movement disorders, and MARKO, in realistic therapeutic settings. Twenty-nine children participated in this study: 17 of them were recruited from among patients with cerebral palsy and similar movement disorders, and 12 healthy. Approximately 222 minutes of session time was recorded. All dialogues were transcribed, and nonverbal acts were annotated. A control group of 15 children (14 with cerebral palsy, one with spina bifida) was also included. The evaluation of the corpus showed that the positive effects go beyond social triggering - the children not only positively responded to MARKO, but also experienced increased motivation and engagement in therapy.
Keywords: child-robot interaction; robot-assisted therapy; robot MARKO; cerebral palsy, cognitive infocommunications
Abstract: As Virtual Reality (VR) products are becoming more widely available in the consumer market, improving the usability of these devices and environments is crucial. In this paper, we are going to introduce a framework for the usability evaluation of collaborative 3D virtual environments based on a large-scale usability study of a mixed-modality collaborative VR system. We first review previous literature about important usability issues related to collaborative 3D virtual environments, supplemented with our research in which we conducted 122 interviews after participants solved a collaborative virtual reality task. Then, building on the literature review and our results, we extend previous usability frameworks. We identified twelve different usability problems, and based on the causes of the problems, we grouped them into three main categories: VR environment-, device interaction-, and task-specific problems. The framework can be used to guide the usability evaluation of collaborative VR environments.
Keywords: virtual reality; usability evaluation; content-analysis; CAVE
Abstract: The paper presents three Gain-Scheduling Control (GS-C) design procedures starting with classical Proportional-Integral (PI) controllers, resulting in PI-GS-C structures for positioning control of a Magnetic Levitation System (MLS) with two laboratory electromagnets. The nonlinear mathematical model of the MLS is first linearized at seven operating points and next stabilized by a state feedback control structure. Three PI-GS-C structures, namely as Lagrange, Cauchy and Switching GS versions, are next designed in order to ensure zero steady-state control error and the switching between PI controllers. All control solutions are validated by real-time experiments.
Keywords: Gain-Scheduling Control; magnetic levitation systems; Proportional-Integral control; real-time experiments
Abstract: The corrective focus is a particular kind of prosodic prominence where the speaker is intended to correct or to emphasize a concept. This work develops an Artificial Cognitive System (ACS) based on Recurrent Neural Networks that analyzes suitable features of the audio channel in order to automatically identify the Corrective Focus on speech signals. Two different approaches to build the ACS have been developed. The first one addresses the detection of focused syllables within a given Intonational Unit whereas the second one identifies a whole IU as focused or not. The experimental evaluation over an Italian Corpus has shown the ability of the Artificial Cognitive System to identify the focus in the speaker IUs. This ability can lead to further important improvements in human-machine communication. The addressed problem is a good example of synergies between Humans and Artificial Cognitive Systems.
Keywords: Focus; Stress; Prosodic prominence; Neural networks
Abstract: This paper intends to introduce a novel model for query-topic relevance assessment from assessor and cognitive point of view in the sense that relevance is a multidimensional cognitive and dynamic conception. The focus of this presentation is concentrated on modeling the concept "Query Associative Vocabulary of Relevance" to emphasize the value of integrating intuitive, descriptive, multi-valued assessment, and agreement in the process of creating a query-topic relevance data. As this model differentiates between different types of query-topics and levels of relevance, it provides a facility to enhance the quality of relevance data by re-evaluating the resulted associative vocabulary at each cycle of refinement. This aspect is of importance, as it is directed toward extracting as much advantage from human assessment as possible. A prototype of this model has generated in an initial run a relevance dataset of 20.710 relevance assessor’s feedback and a co-occurrence matrix of 39607 terms distributed in intuitive, descriptive and document associative vocabularies. Most of the assessor feedback is descriptive produced by humans in context of establishing a relevance relationship between a query-topic and related documents. Furthermore, classifying query relevance datasets according to grades of agreements among judgments is useful as it gives a better overview of the performance of the considered system and the comparison of different datasets in context of consistency and performance becoming easier. Despite the importance of relevance in designing and evaluating Information Retrieval Systems as possible inter-cognitive systems, a consensus on definition is still debatable. However, considering relevance as a multidimensional cognitive and dynamic conception provides researcher with a research track to evaluate the performance of interactive and inter-cognitive processes in terms of the multidimensionality and cognitive aspects of relevance.
Keywords: Relevance Assessment; Query-Topic Modelling; Relevance Dataset; Assessor-Centric; Judgments Agreements; Cognitive Linguistics; Information Retrieval, Search Engine Performance; Word Associative Network, Cognitive InfoCommunication; Topic Model
Abstract: This manuscript focuses on cognitive aspects of spatial mental modeling. We examine possibilities for merging methods for sensing and modeling of cognitive capabilities and cognitive styles with the concept of cognitive infocommunications. Related aspects of cognitive psychology, the theory of senses, sensory substitution, and mental modeling are discussed. We illustrate practical impact of emerging CogInfoCom methods on people with special needs, in particular, those with vision impairment.
Keywords: cognition; senses; cognitive infocommunications; navigation; orientation
Abstract: If we have recently begun to understand how DNA gives life to embryos and then to individuals, only very little is understood of the intricate interactions between the biological bases of life, the environment and the human brain. The exponential acceleration of technological change could change many, perhaps all, the rules that have guided our civilization so far. It is very likely that these intelligent artificial entities will take much less time to understand the codes that constitute them, gaining forms of (self) awareness, decision-making skills, introspective capacities, mind reading and even free will. If all this is achieved, in the coming decades humanity will be destined to a profound cultural, epistemological and even physiological transformation. In this paper, we aim to show how the success or failure of a balanced man-machine co-evolution will also depend on some answers to fundamental scientific questions that have remained unexplored, such as consciousness and decision-making, creativity, but above all to the adaptive factor that more radically sustained and pushed the evolution beyond the constraints of our genetic code: improvisation. This entanglement of neuronal matrices could be at the origin of an intermodal communication - consists of a stream of semantic phenomena, mental images and more, tuned thanks to “pattern recognition” in centrencephalic space of functional integration - thus explaining “remote spectrum actions” at the base of primary adaptive unconscious and experiences life.
Keywords: consciousness; decision-making; creativity; improvisation; intelligent systems communication
Abstract: In the last decades, more and more virtual systems are used for various activities: training, explanation, simulation, or verifying different concepts. This paper presents a first attempt to create a CogInfoCom channel through which a Virtual Reality (VR) system communicates with a natural cognitive system (prototype and physical experimental system) in a way that improves human cognitive abilities to understand the way an ancient bow works and the sensations it exerts on the human body. This study proposes an immersive VR simulator for recreating the experience of shooting with 3 types of old bows, based on a customized haptic interface. The research focuses on optimizing the shooting experience by using the force characteristic measured from real replicas, as well as handling other important archery features such as the length of the draw or the weight of the bow. The results are mostly positive and the data collected demonstrates the adaptability and replicability of the developed solution, as the system is able to reproduce in VR any type of bow.
Keywords: Virtual Archery; Immersive VR; Haptic feedback; 3D interaction; CogInfoCom
Abstract: Augmented reality offers great solutions in learning because most of high school students are familiar with them. Augmented reality-based applications such as the Pokémon Go 3D, or Quiver and HP Reveal can be used effectively in education. Using AR technology, teachers or even students can create content. For example, triggers using the provided website. The triggers can be image or videos, so the AR experience can be customized. In this study, authors first introduce the augmented reality and a specific application, Pokémon Go, then demonstrate the use of AR in education and finally present a survey conducted among students of a higher education in Hungary.
Keywords: ICT; Augmented Reality; higher education; Pokémon GO; HP Reveal
Abstract: Mathability in its definition refers to cognitive infocommunication and combines machine and human cognitive capabilities essential for mathematics. In the paper educational aspects of the notion are considered. A new proposal of learning outcomes taxonomy is presented.
Keywords: Mathability; Education; Constructive Learning; Taxonomy of Learning Objectives
Abstract: Social sciences have an important challenge today to take advantage of new research opportunities provided by large amounts of data generated by online social networks. Because of its marketing value, sports clubs are also motivated in creating and maintaining a stable audience in social media. In this paper, we analyze followers of prominent footballs clubs on Twitter by obtaining their home locations. We then measure how city size is connected to the number of followers using the theory of urban scaling. The results show that the scaling exponents of club followers depend on the income of a country. These findings could be used to understand the structure and potential growth areas of global football audiences.
Keywords: urban scaling; Twitter; social media; football