Yazar "Cevik, Ulus" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • [ X ]
    Öğe
    A Review on Feature Extraction for Speaker Recognition under Degraded Conditions
    (Taylor & Francis Ltd, 2017) Disken, Gokay; Tufekci, Zekeriya; Saribulut, Lutfu; Cevik, Ulus
    Speech is a signal that includes speaker's emotion, characteristic specification, phoneme-information etc. Various methods have been proposed for speaker recognition by extracting specifications of a given utterance. Among them, short-term cepstral features are used excessively in speech, and speaker recognition areas because of their low complexity, and high performance in controlled environments. On the other hand, their performances decrease dramatically under degraded conditions such as channel mismatch, additive noise, emotional variability, etc. In this paper, a literature review on speaker-specific information extraction from speech is presented by considering the latest studies offering solutions to the aforementioned problem. The studies are categorized in three groups considering their robustness against channel mismatch, additive noise, and other degradations such as vocal effort, emotion mismatch, etc. For a more understandable representation, they are also classified into two tables by utilizing their classification methods, and used data-sets.
  • [ X ]
    Öğe
    A robust polynomial regression-based voice activity detector for speaker verification
    (Springer International Publishing Ag, 2017) Disken, Gokay; Tufekci, Zekeriya; Cevik, Ulus
    Robustness against background noise is a major research area for speech-related applications such as speech recognition and speaker recognition. One of the many solutions for this problem is to detect speech-dominant regions by using a voice activity detector (VAD). In this paper, a second-order polynomial regression-based algorithm is proposed with a similar function as a VAD for text-independent speaker verification systems. The proposed method aims to separate steady noise/silence regions, steady speech regions, and speech onset/offset regions. The regression is applied independently to each filter band of a mel spectrum, which makes the algorithm fit seamlessly to the conventional extraction process of the mel-frequency cepstral coefficients (MFCCs). The kmeans algorithm is also applied to estimate average noise energy in each band for spectral subtraction. A pseudo SNR-dependent linear thresholding for the final VAD output decision is introduced based on the k-means energy centers. This thresholding considers the speech presence in each band. Conventional VADs usually neglect the deteriorative effects of the additive noise in the speech regions. Contrary to this, the proposed method decides not only for the speech presence, but also if the frame is dominated by the speech, or the noise. Performance of the proposed algorithm is compared with a continuous noise tracking method, and another VAD method in speaker verification experiments, where five different noise types at five different SNR levels were considered. The proposed algorithm showed superior verification performance both with the conventional GMM-UBM method, and the stateof- the-art i-vector method.
  • [ X ]
    Öğe
    Analysis of breast cancer classification robustness with radiomics feature extraction and deep learning techniques
    (Wiley, 2022) Rashid, Harun Ur; Ibrikci, Turgay; Paydas, Semra; Binokay, Figen; Cevik, Ulus
    Breast cancer and breast imaging diagnostic procedures are typically carried out using a variety of imaging modalities, including mammography, MRI, and ultrasound. However, ultrasound and mammography have limitations and MRI is recognized as better than other procedures. Recent computational approaches, such as radiomics, applied to image analysis have shown remarkable progress in lowering diagnostic difficulties. This research analysed the robustness of breast tumour classification with feature extraction (radiomics) and a featureless method (deep learning). The proposal consists of two stages: the first stage introduced and explored radiomics-based steps. A total of 111 tumour lesions were used to derive 74 radiomic features consisting of shape, and three separate second-order metrics. Associations of these features were used to classify tumour lesions with four different kernels from support vector machine algorithm. In the confusion matrix analysis, the SVM-RBF kernel developed optimal diagnostic efficiency with a maximum test accuracy of 97.06% on the combination of feature analysis. The second stage developed with deep learning techniques (InceptionV3 and CNN-SVM). A total of 2998 images were used to create the models. In this portion, the CNN-SVM model achieved the highest accuracy, 95.28%, with an AUC of 0.974, where the pre-trained InceptionV3 achieved an AUC of only 0.932. Finally, the obtained result in both stages was discussed together and other related studies.
  • [ X ]
    Öğe
    Real-Time Speaker Independent Isolated Word Recognition on Banana Pi
    (IEEE, 2018) Disken, Gokay; Saribulut, Lutfu; Tufekci, Zekeriya; Cevik, Ulus
    Devices controlled with voice commands have gained popularity over the last decade. To recognize an utterance, they usually require an internet connection, or use commercial programming libraries. Therefore, their flexibility is low, and algorithm update opportunities are limited. In this study, a speaker independent isolated word recognition algorithm, embedded in a single board computer, is proposed to recognize utterances in real-time. The proposed system neither requires an internet connection, nor uses external libraries. Mel Frequency Cepstral Coefficients and their deltas are used as feature vectors. Gaussian mixture models are utilized to define word models. Digits and some confirmation words of Turkish language are recorded ten times in one session from twenty-four individuals. Seven of these records are used for training, and the others for testing the system. The off-line experimental results showed that the system is working with 99.98%. In real-time experiments, the system's recognition accuracy was proficient for controlled environments.
  • [ X ]
    Öğe
    Real-Time Speaker Independent Isolated Word Recognition on Banana Pi
    (Institute of Electrical and Electronics Engineers Inc., 2018) Disken, Gokay; Saribulut, Lutfu; Tufekci, Zekeriya; Cevik, Ulus
    Devices controlled with voice commands have gained popularity over the last decade. To recognize an utterance, they usually require an internet connection, or use commercial programming libraries. Therefore, their flexibility is low, and algorithm update opportunities are limited. In this study, a speaker independent isolated word recognition algorithm, embedded in a single board computer, is proposed to recognize utterances in realtime. The proposed system neither requires an internet connection, nor uses external libraries. Mel Frequency Cepstral Coefficients and their deltas are used as feature vectors. Gaussian mixture models are utilized to define word models. Digits and some confirmation words of Turkish language are recorded ten times in one session from twenty-four individuals. Seven of these records are used for training, and the others for testing the system. The off-line experimental results showed that the system is working with 99.98%. In real-time experiments, the system's recognition accuracy was proficient for controlled environments. © 2018 IEEE.
  • [ X ]
    Öğe
    Speaker Model Clustering to Construct Background Models for Speaker Verification
    (Polska Akad Nauk, Polish Acad Sciences, Inst Fundamental Tech Res Pas, 2017) Disken, Gokay; Tufekci, Zekeriya; Cevik, Ulus
    Conventional speaker recognition systems use the Universal Background Model (UBM) as an imposter for all speakers. In this paper, speaker models are clustered to obtain better imposter model representations for speaker verification purpose. First, a UBM is trained, and speaker models are adapted from the UBM. Then, the k-means algorithm with the Euclidean distance measure is applied to the speaker models. The speakers are divided into two, three, four, and five clusters. The resulting cluster centers are used as background models of their respective speakers. Experiments showed that the proposed method consistently produced lower Equal Error Rates (EER) than the conventional UBM approach for 3, 10, and 30 seconds long test utterances, and also for channel mismatch conditions. The proposed method is also compared with the i-vector approach. The three-cluster model achieved the best performance with a 12.4% relative EER reduction in average, compared to the i-vector method. Statistical significance of the results are also given.