9 results
Search Results
Now showing 1 - 9 of 9
Conference Object Higher Order Statistical Analysis of Turkish Phones(Ieee, 2014) Tora, Hakan; Uslu, BaranIn this study, histograms of Turkish phones were examined using higher order cumulants. As is known, phones constituting a language, are composed of letters as vowels and consonants. These letters can also be grouped as voiced and unvoiced phones. It is observed that unvoiced letters show a Gaussian-like distribution and result in small values of skewness and kurtosis. On the other hand, vowels and voiced consonants lead to a non-Gaussian distribution. Voiced and unvoiced phones are related with their skewness and kurtosis values. It is empirically shown that higher order cumulants are likely to be a feature in describing Turkish phones.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.Article Yalıtık Sözcüklü Bir Türkçe Konuşma Tanıma Sisteminin Yapay Veri Artırımı ile Tasarımı ve Gerçekleştirimi(2020) Uslu, İbrahim Baran; Tora, Hakan; Sümer, Emre; Türker, Mustafa; Uslu, BaranBu çalışmada toplamda doksan iki adet sesli komuttan oluşan bir yalıtık sözcüklü Türkçe konuşmatanıma sistemi tasarlanmış ve gerçekleştirilmiştir. Sistem, destek vektör makinesi (SVM) tabanlı olup,eğitimde kullanılan veri kümesi kaydedilen konuşmaların yapay olarak çeşitlendirilip artırılmasıyla eldeedilmiştir. Farklı yapay veri oranlarının tanıma başarımı üzerindeki etkisi incelenmiştir. Akustik öznitelikolarak, mel frekansı kepstral katsayıları (MFCC) kullanılmıştır. Ayrıca, ses aktivitesi tespitinin ve MFCCkatsayılarının tanıma başarımına etkileri de irdelenmiştir. Sonuçta doksan iki yalıtık komut için ortalama%92.6’lık doğrulukla çalışan bir konuşma tanıma sistemi geliştirilmiştirConference Object Design and Implementation of an Expressive Talking Mobile Robot: Toztorus(Ieee, 2018) Tozan, Ozalp; Tora, Hakan; Uslu, Baran; Unal, Bulcnt; Ceylan, EceThis paper is about a brand new robot and all its development stages from the design to the show time. As an undergraduate research project (the LAP program at Atilim University), the robot TozTorUs is the outcome of the dense efforts of a team. With the sensors equipped, it navigates autonomously in the environment in which it is located by avoiding the obstacles. It can understand your questions and answer them using Google's speech technologies. Although it is not a humanoid robot, with eyes and mouth simulator LED displays, it is as friendly as a human. We can also control TozTorUs using a mobile phone. Apart from these, it is able to adjust its height with respect to the visitor's, thus allowing it to make an eye contact with the person. Although TozTorUs is designed for welcoming, it may also be employed for consulting, security and elderly assistance.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.Article Eye Movement Controlled Peripherals for the Handicapped-Paralyzed People and Als Patients(2017) Uslu, İbrahim Baran; Arı, Fikret; Sümer, Emre; Türker, Mustafa; Uslu, BaranControlling some devices in their daily life for the handicapped-paralyzed people and ALS (Amyotrophic Lateral Sclerosis) patients is an important challenge. In this study, a wearable system, called SmartEyes, is developed. The system is controlled by the eye movements of the user. With the help of this system, two groups of facilities are provided. The first is: communicating with predefined voiced messages, valuable especially for people who are unable to talk, and the second is: controlling some peripherals which are in the range around the user. The novelty of the developed system is that it navigates among the menus by means of the eye movements with the help of synthesized voice messages and without a need to sit across a monitor. In the control part, both the infrared (IR) and radio frequency (RF) wireless technologies were employed. The details of the peripheral control operations, namely: controlling the desk light, rolling curtain, TV, air conditioner and the sickbed, are explained in detail. The test results show that the system works quite satisfactorily in tracing and implementing the commands given by the user’s pupil gaze directions. We found that the overall satisfaction is quite high by yielding a total average survey score of 4.7 out of 5. We believe that the developed system offers a practical and efficient solution for making the lives of handicapped-paralyzed people and ALS patients easier. We carry on improving the skills of our SmartEyes systemConference 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.Article Implementation of Turkish Text-To Synthesis on a Voice Synthesizer Card With Prosodic Features(2017) Tora, Hakan; Uslu, İbrahim Baran; Karamehmet, Timur; Uslu, BaranThis study is on hardware implementation of the Turkish text-to-speech (TTS) synthesis with a voice synthesizer card. Here, a fully functional TTS system, capable of synthesizing every Turkish text, including abbreviations, numbers, etc. is designed and implemented. The system is additionally enriched by applying some prosodic attributes for more intelligible and natural speech production. A set of rules required for proper pronunciation and stress patterns are precisely defined in a lexicon utilized for synthesizing Turkish speech. Performance of the developed system is assessed by the Mean Opinion Score (MOS) test. An average score of 3.29 out of 5 is achieved.It indicates that the proposed synthesizer can be successfully integrated to many practical Turkish TTS applications.Conference Object Citation - WoS: 8Hand Gesture Classification Using Inertial Based Sensors Via a Neural Network(Ieee, 2017) Akan, Erhan; Tora, Hakan; Uslu, BaranIn this study, a mobile phone equipped with four types of sensors namely, accelerometer, gyroscope, magnetometer and orientation, is used for gesture classification. Without feature selection, the raw data from the sensor outputs are processed and fed into a Multi-Layer Perceptron classifier for recognition. The user independent, single user dependent and multiple user dependent cases are all examined. Accuracy values of 91.66% for single user dependent case, 87.48% for multiple user dependent case and 60% for the user independent case are obtained. In addition, performance of each sensor is assessed separately and the highest performance is achieved with the orientation sensor.
