| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Search the digital library catalog Help

Query: search in
search in
search in
search in
* old and bologna study programme


721 - 730 / 745
First pagePrevious page66676869707172737475Next pageLast page
Annotating discourse markers in spontaneous speech corpora on an example for the Slovenian
Darinka Verdonik, Matej Rojc, Marko Stabej, 2007, original scientific article

Abstract: Speech-to-speech translation technology has difficulties processing elements of spontaneity in conversation. We propose a discourse marker attribute in speech corpora to help overcome some of these problems. There have already been some attempts to annotate discourse markers in speech corpora. However, as there is no consistency on what expressions count as discourse markers, we have to reconsider how to set a framework for annotating, and, in order to better understand what we gain by introducing a discourse marker category, we have to analyse their characteristics and functions in discourse. This is especially important for languages such as Slovenian where no or little research on the topic of discourse markers has been carried out. The aims of this paper are to present a scheme for annotating discourse markers based on the analysis of a corpus of telephone conversations in the tourism domain in the Slovenian language, and to give some additional arguments based on the characteristics and functions of discourse markers that confirm their special status in conversation.
Keywords: discourse markers, speech corpora, annotating, conversation, discourse analysis, speech-to-speech translation, spontaneous speech, Slovenian language
Published: 31.05.2012; Views: 1122; Downloads: 24
URL Link to full text

Progressive method for color selective edge detection
Peter Rulić, Iztok Kramberger, Zdravko Kačič, 2007, original scientific article

Abstract: Edge detection plays an important role in image analysis systems. We present acolor selective edge detection technique, which consists of two image processing steps. The first step represents pixel-based color detection and the second progressive block-oriented edge detection. The combination of these two steps defines a selective edge detection technique, which enables fast and simple processing of those images captured using arbitrary cameras incomplex scenes with nonstandard illumination. The proposed method was implemented for the detecting of skin color objects and tested on real scene images.
Keywords: image analysis system, image processing, color detection, skin color
Published: 31.05.2012; Views: 1026; Downloads: 59
URL Link to full text

Software and equipment for remote testing of sensors
Barbara Brezovec, Vojko Matko, 2007, original scientific article

Abstract: An improved approach for remote testing of elements and systems is presented in this article. To ensure high reliability of products, tests must be done in the production phase to detect possible errors in working mode. Because environmental testing involves long-term processes the possibility of remote observation and remote controlling of tests is very useful solution. The concept is to connect the testing chamber with a personal computer, create a reliable driver and control it remotely over the local network or Internet from other client. It is designed for performing tests on wide area of sensors and sensor based systems.
Keywords: sensors reliability, testing methods, remote control, virtual instruments
Published: 31.05.2012; Views: 1082; Downloads: 145
.pdf Full text (243,72 KB)
This document has many files! More...

A unified approach to grapheme-to-phoneme conversion for the plattos slovenian text-to-speech system
Matej Rojc, Zdravko Kačič, 2007, original scientific article

Abstract: This article presents a new unified approach to modeling grapheme-to-phoneme conversion for the PLATTOS Slovenian text-to-speech system. A cascaded structure consisting of several successive processing steps is proposed for the aim of grapheme-to-phoneme conversion. Processing foreign words and rules for the post-processing of phonetic transcriptions are also incorporated in the engine. The grapheme-to-phoneme conversion engine is flexible, efficient, and appropriate for multilingual text-to-speech systems. The grapheme-to-phoneme conversion process is described via finite-state machine formalism. The engine developed for Slovenian language can be integrated into various applications but can be even more efficiently integrated into architectures based on finite-state machine formalisms. Provided the necessary language resources are available, the presented approach can also be used for other languages.
Keywords: spech system, grapheme-to-phoneme
Published: 31.05.2012; Views: 1181; Downloads: 40
URL Link to full text

Fuzzy logic based quality monitoring in short-circuit gas metal arc welding
Marjan Golob, Arpad Köveš, 2007, original scientific article

Abstract: Conventional methods, e.g. destructive and non-destructive testing methods, are expensive and time-consuming; therefore, possibilities of online and automated quality control of a welding process during welding as such are investigated. The paper deals with the possibilities of application of fuzzy logic to the analysis of weld quality, particularly assessment of the weld surface condition by means of measurable electric signals emitted during welding. A simple fuzzy inference system was realised which could relatively efficiently assess the weld quality on the basis of time variations of the welding voltage and short-circuit time in a certain time window.
Keywords: fuzzy systems, fuzzy logic, gas metal arc welding, GMAW, quality monitoring, statistical analysis, quality control, weld quality
Published: 31.05.2012; Views: 984; Downloads: 61
URL Link to full text

Adaptive learning by using SCOs metadata
Danijela Milošević, Mirjana Brković, Matjaž Debevc, Radojka Krneta, 2007, original scientific article

Published: 31.05.2012; Views: 523; Downloads: 70
URL Link to full text

A noise robust feature extraction algorithm using joint wavelet packet subband decomposition and AR modeling of speech signals
Bojan Kotnik, Zdravko Kačič, 2007, original scientific article

Abstract: This paper presents a noise robust feature extraction algorithm NRFE using joint wavelet packet decomposition (WPD) and autoregressive (AR) modeling of a speech signal. In opposition to the short time Fourier transform (STFT)-based time-frequency signal representation, wavelet packet decomposition can lead to better representation of non-stationary parts of the speech signal (e.g. consonants). The vowels are well described with an AR model as in LPC analysis. The proposed Root-Log compression scheme is used to perform the computation of the wavelet packet parameters. The separately extracted WPD and AR-based parameters are combined together and then transformed with the usage of linear discriminant analysis (LDA) to finally produce a lower dimensional output feature vector. The noise robustness is improved with the application of proposed wavelet-based denoising algorithm with a modified soft thresholding procedure and time-frequency adaptive threshold. The proposed voice activity detector based on a skewness-to-kurtosis ratio of the LPC residual signal is used to effectively perform a frame-dropping principle. The speech recognition results achieved on Aurora 2 and Aurora 3 databases show overall performance improvement of 44.7% and 48.2% relative to the baseline MFCC front-end, respectively.
Keywords: automatic speech recognition, autoregressive modeling, modified soft thresholding, noise robust speech parameterization, wavelet packet decomposition
Published: 31.05.2012; Views: 1146; Downloads: 46
URL Link to full text

Search done in 0.44 sec.
Back to top
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica