WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8653
Browse
2 results
Search Results
Article Investigation of Factors Affecting Noise Robustness in Voice Activity Detectors(Gazi Univ, Fac Engineering Architecture, 2023) Ozaydin, SelmaIn this manuscript, some voice activity detectors (VADs) in the literature were examined in terms of factors affecting their robustness under different acoustic noise conditions and in this context, the changes in detection accuracy rates according to changing noise conditions were tested. In this scope, the effect of situations such as whether the threshold value used in the decision phase in VAD methods is fixed or adaptive, the analysis window is short or long, the use of more than one feature vector together has been evaluated and analyzed comparatively. While three of the four different VAD detectors examined in this manuscript use feature vectors within the short-term analysis window while generating the decision result, one decides according to the measurement result of long-term spectral vectors. The VAD detectors in the article have been tested using the NOIZEUS noisy speech database. Thus, the performance of the analyzed VADs has been evaluated under different acoustic conditions using an extensive database that has already taken place in the literature. During the testing of the analyzed VADs, different input noise speech signals with environmental background noises between [15-0dB] such as restaurant, car, street, or station were tested. Tests were carried out using objective test measurement methods and the detection accuracy rate of each VAD method was measured. The results showed that each method gave different endurance performance in adverse environmental conditions.Article Citation - WoS: 7Citation - Scopus: 10Extending a Sentiment Lexicon With Synonym-Antonym Datasets: Swnettr Plus(Tubitak Scientific & Technological Research Council Turkey, 2019) Genc, Burkay; Sever, Hayri; Saglam, FatihIn our previous studies on developing a general-purpose Turkish sentiment lexicon, we constructed SWNetTR-PLUS, a sentiment lexicon of 37K words. In this paper, we show how to use Turkish synonym and antonym word pairs to extend SWNetTR-PLUS by almost 33% to obtain SWNetTR++, a Turkish sentiment lexicon of 49K words. The extension was done by transferring the problem into the graph domain, where nodes are words, and edges are synonym- antonym relations between words, and propagating the existing tone and polarity scores to the newly added words using an algorithm we have developed. We tested the existing and new lexicons using a manually labeled Turkish news media corpus of 500 news texts. The results show that our method yielded a significantly more accurate lexicon than SWNetTR-PLUS, resulting in an accuracy increase from 72.2% to 80.4%. At this level, we have now maximized the accuracy rates of translation-based sentiment analysis approaches, which first translate a Turkish text to English and then do the analysis using English sentiment lexicons.