Cemil Demir

Learn More
In this study, we describe a mixture model based single-channel speech-music separation method. Given a catalog of background music material, we propose a generative model for the superposed speech and music spectrograms. The background music signal is assumed to be generated by a jingle in the catalog. The background music component is modeled by a scaled(More)
BACKGROUND & OBJECTIVES This study was carried out to evaluate the association between the antibiotic susceptibility patterns and the antibiotic resistance genes in staphylococcal isolates obtained from various clinical samples of patients attending a teaching hospital in Hatay, Turkey. METHODS A total of 298 staphylococci clinical isolates were subjected(More)
In this study, single-channel speech source separation is carried out to separate the speech from the background music, which degrades the speech recognition performance especially in broadcast news transcription systems. Since the separation is done using single observation of the source signals, the sources have to be previously modeled using training(More)
In this study, we propose a semi-supervised speech-music separation method which uses the speech, music and speech-music segments in a given segmented audio signal to separate speech and music signals from each other in the mixed speech-music segments. In this strategy, we assume, the background music of the mixed signal is partially composed of the(More)
In this study, single-channel speech source separation is carried out to separate the speech from the background music, which degrades the speech recognition performance especially in broadcast news transcription systems. In the proposed method, assuming that we know a catalog of the background music, we developed a generative model for the superposed(More)
—In this study, we analyze the gain estimation problem of the catalog-based single-channel speech-music separation method, which we proposed previously. In the proposed method, assuming that we know a catalog of the background music, we developed a generative model for the superposed speech and music spectrograms. We represent the speech spectrogram by a(More)
Leptin is a protein hormone which plays a critical role in the regulation of both body-weight through reducing food intake and stimulating energy expenditure. Several polymorphisms in leptin gene (LEP), which encodes for leptin, have been described. However, its association with obesity is still controversial. Therefore, in the present study, we aimed to(More)
Using posterior probability based features to segment an audio signal as speech and music has been commonly used method In this study Hidden-Markov-Model (HMM) based acoustic models are used to calculate posterior probabilities. Acoustic Models includes states of context-independent phones as modeling unit. Entropy and Dynamism are found using via the(More)
In this study a system that segments an audio signal as speech and music by using posterior probability based features is proposed and implemented in Sphinx. Unlike the earlier efforts that uses Multi-Layer Perceptrons (MLP), this system uses Hidden-Markov-Model based acoustic models that are trained in Sphinx for posterior probability calculations.(More)