45 results
Search Results
Now showing 1 - 10 of 45
Conference Object Naturalness Analysis of the Speech Synthesized by a Tts Card(Ieee, 2016) Tora, Hakan; Uslu, BaranIt is known that the performance of a developed text-to-speech (TTS) synthesis system is assessed by subjective tests. These assessments are usually based on the intelligibility and naturalness of the synthesized speech. In this study, an investigation on relating these subjective test results, thus the naturalness of the synthesized speech, to which acoustic features is accomplished. Consequently the features which will increase the performance while synthesizing the speech are determined. Our work is focused especially on the pitch frequency and energy parameters.Conference Object Citation - WoS: 2New Wavelet-Based Features for the Recognition of Jittered and Stagger Pri Modulation Types(Ieee, 2015) Gencol, Kenan; Kara, Ali; At, NurayIn dense electronic warfare environments, numerous emitters can be active simultaneously and an interleaved stream of pulses in natural time of arrival order is received by the Electronic Support Measures (ESM) receiver. It is the task of the ESM system to de-interleave this mixed pulse sequence and thus to identify the surrounding threatening emitters. In this processing, pulse repetition interval (PRI) modulation recognition has a significant role due to the fact that it can reveal the hidden patterns inside pulse repetition intervals and thus help identify the emission source and its functional purpose. In this paper, we propose new wavelet-based features for the recognition of jittered and stagger PRI modulation types. The recognition of these types are heavily based on histogram features. Experimental results show that the proposed feature set have very high recognition rates and outperform histogram based methods.Conference Object Citation - WoS: 1THE USE OF CUMULANTS FOR VOICED-UNVOICED SEGMENTS IDENTIFICATION IN SPEECH SIGNALS(Ieee, 2014) Uslu, Baran; Tora, HakanIn this study, voiced-unvoiced classification performance of Turkish sounds using skewness and kurtosis is examined. The analyses show that higher order cumulants can be employed as a feature in voiced-unvoiced classification that is vital in speech processing applications. Furthermore, it has been shown that cumulants are also useful for identifying voiced and unvoiced segments in noisy speech signals.Conference Object Citation - WoS: 6Bar Code Localization in Wavelet Domain by Using Binary Morphology(Ieee, 2004) Öktem, REIn this paper, a wavelet transform based bar code localization algorithm is proposed. The algorithm is designed to enable fast and memory efficient application for automatic bar code recognition systems that are used in big manufacturing and distribution units. The region of interest areas are kept and other regions are discarded by applying binary morphology on wavelet transform coefficients.Conference Object A Fast Hough Transform Approximation and Its Application for Barcode Localization(Ieee, 2007) Safran, Mehmet Ilhami; Oektem, RusenThis paper addresses barcode localization in images acquired by wireles cameras. For this purpose, a fast Hough transform approximation by use of a sliding mask is developed. The approximation decomposes the lines at different orientations into distinct bitplanes. Barcode localization is achieved by considering the high density locations in the bitplanes via morphology and profiling. The time complexity of the proposed approximation is lower than the previously proposed fast Hough transform, though it achieves the equal performance in localization of barcodes.Conference Object The Usability Study for the Personal Health Record Systems(Ieee, 2015) Gokay, Gonca; Ercil, Yavuz; Tokdemir, Gul; Cagiltay, Nergiz; Aykac, Y. EvrenWith the emergence of new technologies, there is an increasing number of studies to improve healthcare delivery quality and health services. The studies have shown that the focus should be on integrated, sharable and personalized healthcare solutions which requires usage of patient data as much as possible for fast and correct diagnosis and care. Hence, data related to people when they are healthy and when they are sick become very critical for which many projects have been initiated to increase awareness of people about the importance of data collection all over the world and in our country as well. This requires more active role of the citizens in tracking their healthcare data. In this study, Microsoft Health Vault system that is used for storage of personal health records, has been analyzed in terms of its usability characteristics and the results have been discussed.Conference Object Design, Analysis and Manufacturing of Dielectric Rod Added Conical Rom Antennas(Ieee, 2016) Avcioglu, Esra; Özaslan, Alper; Caliskan, FatmaIn this study, ANSYS HFSS (High Frequency Structural Simulator) software had been used. By using this software, dielectric rod added conical horn antennas with various shapes and dimensions had been designed and analyzed. 5 (five) distinct antennas designed and their gains and return losses had been observed to evaluate the effects of the changes. From the results of these comparisons, the proper antenna type was selected and it was manufactured.Conference Object Segmentation of Isolated Words Into Voiced-Unvoiced Sound Components by Kurtosis(Ieee, 2015) Uslu, Baran; Tora, HakanThis study presents a new approach to the segmentation of isolated words into their voiced/unvoiced parts. It is well known that voiced/unvoiced discrimination has an important role in speech synthesis and coding applications. The offered method makes this discrimination using the kurtosis values of the words. The performance of the proposed approach was tested on Turkish digit recordings from zero to nine. It has been observed that this approach segments the parts successfully in not only clean speech but also in noisy speech.Conference Object Shape Recognition With Low Cost Sensors(Ieee, 2018) Saloglu, Keziban; Hosafci, Arda; Birbilen, Merve; Bulut, Yigit A.; Gunes, AhmetThis paper proposes a method to recognize the shape of some objects that have different geometrical properties using an infra-red sensor.To that end, a mechanism that has two degrees of freedom is designed. Scanning of the different objects are obtained. Noise on scanning output is removed. Finally, all the outputs for different objects are discussed to obtain the specifications to do shape recognition.Conference Object Citation - WoS: 1Recognition of Hand-Sketched Digital Logic Gates(Ieee, 2015) Gul, Nuray; Tora, HakanHand-Sketched circuit recognition is a very useful tool in engineering area. Because most of the engineers prefer to design their circuits on the paper firstly. So, this can cause time wasting and some mistakes. In this study, which is based on the solving these kinds of problems, classification and recognition of the handwritten digital logic gates according to their complex and scalar FDs (Fourier Descriptors) is presented. Test results are obtained as 84.3 % accuracy rate for complex FDs, 98.6 % for scalar FDs. Then these results are compared and decided the optimum FDs type for this study.
