Anton Čižmár

Acoustic Events Detection Using MFCC and MPEG-7 Descriptors

This paper is focused on the acoustic events detection. Particularly two types of acoustic events (gun shot, breaking glass) were investigated. For any detection task the feature extraction methods play very important role. The feature extraction influences the recognition rate, therefore it is most important in any pattern recognition task. In this paper the impact of Mel-Frequency Cepstral Coefficients - MFCC and selected set of MPEG-7 low-level descriptors were examined. The best feature set contained MFCC and selected descriptors such as ASC, ASS, ASF. They were used to represent the sounds of acoustic events and background. We obtained the improvement of the detection rate using the mentioned set of features. In this task GMM classifiers are used to model the sound classes. This paper describes a basic aspect of our work.

Implementation of the New Integration Model of Security and QoS for MANET to the OPNET

The implementation of the new designed model used to integrating security and Quality of Service (QoS) as one parameter in mobile ad-hoc network (MANET) is introduced and studied in this paper. Security and QoS represent a highly important field of research in MANET and they are still being considered separately with no mechanisms used to establish cooperation between them. This new model provides alternative to cooperation between QoS and Security via Cross Layer Design (CLD) and modified Security Service Vector (SSV). Main motivation of this paper is indicating how could be security integrated as a QoS parameter to the MANET via this model. The performance analysis of the new designed model in the well-know simulator OPNET Modeler is also provides.

Evaluation of the Slovak Spoken Dialogue System Based on ITU-T

The development of the Slovak spoken dialogue system started in year 2006. The developed system is publicly available as a trial system and provides weather forecast and timetables information services. One of the very important questions is how to evaluate quality of such a system. A new method for quality assessment of the spoken dialogue system is proposed. The designed method is based on ITU-T P.851 recommendation. Three types of questionnaires were prepared --- A, B and C. The questionnaires serve for obtaining information about users background, completed interactions with the system and about overall impression of the system and its services. Scenarios, methodology of coding, classifying and rating of collected data were also developed. There are also six classes of quality for representation of systems features. Introduced method was used for evaluation of the dialogue system and timetables information service. This paper also summarizes the results of performed experiment.

Extracting sentence elements for the natural language understanding based on slovak national corpus

This paper introduces an approach for extracting sentence elements from Slovak sentences based on linguistic analysis. The key idea lies in the assumption that the sentence elements relates to the meaning and they can be helpful in the process of the semantic roles identification. The system for extracting sentence elements from Slovak sentences has been developed with a morphological analyzer, disambiguator and syntactic analyzer as fundamental components. The morphological analyzer uses data obtained from the Slovak National Corpus. The syntactic analyzer uses context-free grammars. Several evaluation experiments were done with limited range of sentences for obtaining information about success of the proposed approach.

EAR-TUKE: The Acoustic Event Detection System

This paper introduces acoustic events detection system capable of processing continuous input audio stream in order to detect potentially dangerous acoustic events. The system is representing a light, easy extendable, log-term running and complete solution to acoustic event detection. The system is based on its own approach to detection and classification of acoustic events using modified Viterbi decoding process using in combination with Weighted Finite-State Transducers (WFSTs) to support extensibility and acoustic modeling based on Hidden Markov Models (HMMs). Thesystem is completely programmed in C++ language and was designed to be self sufficient and to not require any additional dependencies. Additionally also a signal preprocessing part for feature extraction of Mel-Frequency Cepstral Coefficient(MFCC), Frequency Bank Coefficient (FBANK) and Mel-Spectral Coefficient (MELSPEC) is included. For robustness increase the system contains Cepstral Mean Normalization (CMN) and our proposed removal of basic coefficients from feature vector.

Comparison of Grapheme and Phoneme Based Acoustic Modeling in LVCSR Task in Slovak

Phonemes and allophones are the basic speech units for acoustic modeling in the majority of contemporary HMM based speech recognizers. Grapheme-based acoustic sub-word units were applied to multi-lingual and cross-lingual acoustic modeling in many tasks. Grapheme and phoneme based mono-, cross- and bilingual speech recognition of Czech and Slovak in the small and medium vocabulary task has been studied in our previous work. In this article we compare grapheme and phoneme based approach to acoustic modeling and model unit selection in large vocabulary continuous speech recognition (LVCSR) task in Slovak. The main goal of our experimental work is to investigate a possibility to select an optimal set of sub-word units for Slovak LVCSR system.

Towards Slovak Broadcast News Automatic Recording and Transcribing Service

An electric power steering system (100) for vehicles includes a driving control circuit (50) adapted to generate a torque magnitude signal (Sa) and a torque direction signal (Sdr, Sdl), based on an output signal (VR, VL) from a torque detection mechanism (4, 9) for detecting the magnitude and the direction of steering torque acting on an input shaft (101) connected to a steering wheel (8), and to feed, to an electric motor (5) for supplying auxiliary torque to an output shaft (3) operatively interconnected with a steered ground wheel, an armature current (Io) of such a magnitude and in such a direction of conduction as desirous in accordance with both the torque magnitude signal (Sa) and the torque direction signal (Sdr, Sdl). The steering shaft (101) comprises a first shaft (1) connected to the steering wheel (8), a second shaft (2) interconnected with the first shaft (1), and a third shaft (3) as the output shaft (3) interconnected with the second shaft (2), and a torque detecting means ( 4, 9) comprising a torque direction detecting mechanism (4) interposed between the first shaft (1) and the second shaft (2), and a torque magnitude detecting mechanism (9) interposed between the second shaft (2) and the third shaft (3).

Communication of Mobile Robots in Temporary Disconnected MANET

Mobile ad – hoc network (MANET) provides the new possibilities of multihop communication between mobile terminals without any fixed infrastructure. All mobile nodes are communicating with each other via wireless links and the topology of the network may change unpredictably. The MANET can be used not only for disaster events but can be used for robotic communication. The main problems of the all MANET routing protocols occur if the communication paths between mobile terminals are disconnected. In this paper we focused on the problem of temporary disconnections of the communication links. We propose the enhancement of the reactive routing protocol, also known as dynamic source routing protocol (DSR). Our enhancement provides possibilities to use opportunistic routing of the messages in the case that the routing protocol cannot find communication paths. In this case the routing protocols for MANET stop the routing process and wait for connection, and our modification provides the possibilities to send messages to mobile nodes if the routing protocols are stopped.

Towards to mobile multimodal telecommunications systems and services

The communication itself is considered as a multimodal interactive process binding speech with other modalities. In this contribution some results of the project MobilTel (Mobile Multimodal Telecommunications System) are presented. It has provided a research framework resulting in a development of mobile terminal (PDA) based multimodal interface, enabling user to obtain information from internet by multimodal way through wireless telecommunication network. The MobilTel communicator is a speech centric multimodal system with speech interaction capabilities in Slovak language supplemented with graphical modalities. The graphical modalities are pen - touch screen interaction, keyboard, and display on which the information is more user friendly presented, and provides hyperlink and scrolling menu availability. The architecture of the MobilTel communicator and methods of interaction between PDA and MobilTel communicator are described. The graphical examples of services that enable users to obtain information about weather or information about train connection are also presented.