Romanian Journal of
Human - Computer InteractionVol.8, No.1, 2015
ISSN 1843-4460
Contents
Prerequisites for an automatic speech recognition technology for the Romanian language used in the court of law.
Melania Duma, Corina Giurgea, Mihaela Ordean, Paula Zălhan
1 - 20 Facebook use by visually impaired students – an exploratory study.
Dragoş Daniel Iordache, Aurel Pătru
21 - 32 Music Composition through Chat Sonification According to the Polyphonic Model.
Ştefan Trăuşan-Matu, Alexandru Călinescu
33 - 44 A general description of automatic speech recognition systems architecture.
Valentina Sofroni, Alexandru Stan
45 - 64 Using visual interfaces in human-computer interaction.
Laurenţiu Tănase, Dorin-Mircea Popovici
65 - 80
Abstracts
Prerequisites for an automatic speech recognition technology for the Romanian language used in the court of law
Melania Duma1, Corina Giurgea2, Mihaela Ordean2, Paula Zălhan2
1Universitatea Babes-Bolyai din Cluj-Napoca – UBB
Str. M. Kogalnicaenu nr. 1, Cluj-Napoca, 060042
E-mail: duma_melania@yahoo.com
2iQuest Technologies Cluj-Napoca – iQuest
Str.Motilor nr.4-6, Cluj-Napoca, 40001
E-mail: duma_melania@yahoo.com; corina.giurgea@iquestgroup.com; mihaela.ordean@iquestgroup.com; paula.zalhan@iquestgroup.com;
Abstract. In response to an IT-based, strategic goal of the Romanian Ministry of Justice, the running JustASR project is responsible for developing the architecture and technical elements to be used in implementing a system which mediates the man-computer interaction via the automatic detection of the Romanian language. The project seeks to develop the core of a technology based on the automatic speech recognition of the discourse used in the Romanian court of law. The paper briefly presents the premises and some of the phonetic elements which are paramount to the project’s success. After introducing the Speech Recognition technology, the paper presents the advances of Romanian research in the field. The paper then focuses on the linguistic peculiarities of the Romanian language, the first and foremost element of the technology underlying the JustASR project. The most significant part of the paper deals with the applied aspect of the phonetic theory for the Romanian language. As far as the creation of the dictionary is concerned, the general criteria for constructing the dictionary are illustrated with a special focus on Phonetics and the word categories involved.
Keywords: speech recognition, corpus, dictionary, phonetic processes.
Cite this paper as:
Duma, M., Giurgea, C., Ordean, M., Zalhan, P. Prerequisites for an automatic speech recognition technology for the Romanian language used in the court of law. Revista Romana de Interactiune Om-Calculator 8(1), 1-20, 2015.
Facebook use by visually impaired students – an exploratory study
Dragoş Daniel Iordache1 , Aurel Pătru2
1Institutul Naţional de Cercetare-Dezvoltare în informatică – ICI Bucureşti
Bd. Mareşal Averescu, Nr. 8-10, 011455, Bucureşti
E-mail: iordache@ici.ro
2Liceul Special “Sfânta Maria” Arad
Str. Ghica Vodă, Nr. 4-10, Arad
E-mail: ap@baum.ro
Abstract. In recent years there is an unprecedented growth in popularity of Social Networking Sites (SNSs), Facebook being the best example. Blind people are distinct users of social networks. People with visual impairments are using Facebook with a set of accessibility tools. These tools differ depending on the severity of visual impairment and may take the form of screen readers, the magnifier etc. This paper aims to identify the main factors that motivate blind people to use Facebook, as well as the positive aspects and risks of using this social network. The results are based on a content analysis of the answers to a questionnaire applied to 24 students from the Special School "Sfânta Maria" in Arad. The main benefits identified by visually impaired students on the use of Facebook are: communication, socialization and keeping relationships with friends.
Keywords: Social networks, Facebook, visually impaired student.
Cite this paper as:
Iordache, D.D., Patru, A. Facebook use by visually impaired students – an exploratory study. Revista Romana de Interactiune Om-Calculator 8(1), 21-32, 2015.
Music Composition through Chat Sonification According to the Polyphonic Model
Ştefan Trăuşan-Matu1,2,3, Alexandru Călinescu1
1Universitatea Politehnica din Bucureşti
Splaiul Independenţei nr. 313, Bucureşti,
E-mail: stefan.trausan@cs.pub.ro, alex.calinescu10@gmail.com
2Institutul de Cercetări în Inteligenţa Artificială
Calea 13 Septembrie nr. 13, Bucureşti
3Academia Oamenilor de Ştiinţă din România
Splaiul Independentei nr. 54, Bucureşti
Abstract. The paper presents the theoretical details and the description of the implementation of a system of sonication of chat conversations, starting from the textual logs and generating MusicXML format files containing a music representation containing several voices. The system is a manifestation of two ideas, the first being that the speech in conversations, in general, and in particular in the instant messaging chats, have a structure similar to the polyphonic music. The second idea is that sonication, that means an audible representation of a given processes, is a very useful way of investigation. The approach was validated by the fact that the results were particularly appreciated by a composer and also a professor at the Academy of Music in Bucharest and, moreover, have been adapted and presented in a concert at the Romanian Athenaeum.
Keywords: sonification, polyphony, dialogism, computer music, natural language processing.
Cite this paper as:
Trausan-Matu, S., Calinescu, A. Music Composition through Chat Sonification According to the Polyphonic Model. Revista Romana de Interactiune Om-Calculator 8(1), 33-44, 2015.
A general description of automatic speech recognition systems architecture
Valentina Sofroni, Alexandru Stan
Babes-Bolyai University
Str. Teodor Mihali nr. 58-60, Cluj-Napoca 400591 Romania
E-mail: valentinasofroni@gmail.com, alexandru.stan@econ.ubbcluj.ro
Abstract. Over the last decades, the progress in the ASR domain has been amplified by a significant amount of technical and scientific advancements, amongst which the continuous expansion in the power of computing systems. From a technological point of view, speech recognition has been undergoing tides of major innovations in methodology, algorithms, learning concepts or practical system implementations. This paper provides an up-to-date perspective on the architecture of automatic speech recognition systems and their constituent components. It presents modeling paradigms currently dominant in this type of systems (Hidden Markov Models, Gaussian mixture models, Bayes classifiers, N-gram language model, etc.) together with the architectural constraints they impose upon the design of the system. This study stands for an intermediate step in a larger process which aims to conceive and implement a highly accurate speaker independent ASR system for the recognition of the Romanian language in a limited field of application, such as justice.
Keywords: human-computer interaction, automatic recognition of speech, system architecture.
Cite this paper as:
Sofroni, V., Stan, A. A general description of automatic speech recognition systems architecture. Revista Romana de Interactiune Om-Calculator 8(1), 45-64, 2015.
Using visual interfaces in human-computer interaction
Laurenţiu Tănase, Dorin-Mircea Popovici
Ovidius University of Constanţa
124 Mamaia Bd., 900527, Constanţa
E-mail: tanaselc@gmail.com , dmpopovici@univ-ovidius.ro
Abstract. In response to the decreasing interest in the environment discovery of and direct users interpersonal communication, primary school children, MyDearDaisy application aims to raise awareness and encourage them to study the evolution of the environment, materialized in the form of flowers gardens, as motivational opportunity for personal interaction. Experimentation of the environmental conditions effects on vegetation occurs through natural gestures of young users, detected through Xbox Kinect technology. Virtual environment modeling, rendering and simulation were performed using Unity platform while MS Visual Studio was used to interpret user gestures and translate these gestures in the virtual environment. Usability study prooved the positive appreciation of the educational and motivational side of the system, complete with intuitive, simple and easy to use interface.
Keywords: visual interfaces, gesture-based interaction, virtual reality, education.
Cite this paper as:
Tanase, L., Popovici, D.M. Using visual interfaces in human-computer interaction. Revista Romana de Interactiune Om-Calculator 8(1), 65-80, 2015.