M. Demirekler

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by M. Demirekler

Duration Modeling For Turkish Text-to-Speech Synthesis System

by Tolga Çiloglu and M. Demirekler

Naturalness of synthetic speech depends on appropriate modeling of prosodic aspects. Mostly, thre... more Naturalness of synthetic speech depends on appropriate modeling of prosodic aspects. Mostly, three prosody components are modeled: segmental duration, pitch contour and intensity. In this study, we present our work on modeling segmental duration in Turkish by using machine-learning algorithms. The models predict phone durations based on attributes such as phone identity, neighboring phone identities, lexical stress, position of syllable in word, part-of-speech information, word length in number of syllables and position of word in utterance. Obtained models predict segment durations better than mean duration approximations.

Download

A unified view of rank-based decision combination

by M. Demirekler and Afsar Saranli

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2000

ABSTRACT This study presents a theoretical investigation of the rank-based multiple classifier de... more ABSTRACT This study presents a theoretical investigation of the rank-based multiple classifier decision problem for closed-set pattern classification. The case with classifier raw outputs in the form of candidate class rankings is considered and formulated as a discrete optimization problem with the objective function being the total probability of correct decision. The problem has a global optimum solution but is of prohibitive dimensionality. We present a partitioning formalism under which this dimensionality can be reduced by incorporating our prior knowledge about the problem domain and the structure of the training data. The formalism can effectively explain a number of rank-based combination approaches successfully used in the literature, one of which is discussed

Visual Tracking With Group Motion Approach

2004 Conference on Computer Vision and Pattern Recognition Workshop, 2004

An algorithm for tracking single visual targets is developed in this study.

Download

Representation of covariance matrices in track fusion problems

2008 IEEE 16th Signal Processing, Communication and Applications Conference, 2008

... Kullback-Leibler uzaklıgından faydanılmıstır. Bunların yanında bu gösterimlerin karsılastırıl... more

An Efficient Algorithm for Pitch Determination of Speech Signals - Kalman Filter Approach

2006 IEEE 14th Signal Processing and Communications Applications, 2006

... Algoritma - Kalman Filtre Yaklalimi An Efficient Algorithm for Pitch Determination of Speech ... more

Implementation of an enhanced fixed point variable bit-rate MELP vocoder on TMS320C549

by M. Demirekler and O. Karpat

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258), 1999

In this paper, a fixed point Variable Bit-Rate (VBR) Mixed Excitation Linear Predictive Coding (M... more

Download

On a property of pencils of matrices

by M. Demirekler and Erol KocaoĞlan

International Journal of Control, 1984

ABSTRACT Let A and B be n×n symmetric matrices. Then the adjoint of the expression (A—λB) can be ... more ABSTRACT Let A and B be n×n symmetric matrices. Then the adjoint of the expression (A—λB) can be written as the summation of the terms λ for Ak = 0, 1,..., n −1. It is shown that if both A and B are positive definite then the matrices A k are positive definite for k even and negative definite for k odd.

Estimation of Articulatory Trajectories Based on Gaussian Mixture Model (GMM) With Audio-Visual Information Fusion and Dynamic Kalman Smoothing

IEEE Transactions on Audio, Speech, and Language Processing, 2000

This paper presents a detailed framework for Gaussian mixture model (GMM) based articulatory inve... more This paper presents a detailed framework for Gaussian mixture model (GMM) based articulatory inversion equipped with special post-processing smoothers, and with the capability to perform audio-visual information fusion. The effects of different acoustic features on the GMM inversion performance are investigated and it is shown that the integration of various types of acoustic (and visual) features improves the performance of the articulatory inversion process. Dynamic Kalman smoothers are proposed to adapt the cutoff frequency of the smoother to data and noise characteristics; Kalman smoothers also enable the incorporation of auxiliary information such as phonetic transcriptions to improve articulatory estimation. Two types of dynamic Kalman smoothers are introduced: global Kalman (GK) and phoneme-based Kalman (PBK). The same dynamic model is used for all phonemes in the GK smoother; it is shown that GK improves the performance of articulatory inversion better than the conventional low-pass (LP) smoother. However, the PBK smoother, which uses one dynamic model for each phoneme, gives significantly better results than the GK smoother. Different methodologies to fuse the audio and visual information are examined. A novel modified late fusion algorithm, designed to consider the observability degree of the articulators, is shown to give better results than either the early or the late fusion methods. Extensive experimental studies are conducted with the MOCHA database to illustrate the performance gains obtained by the proposed algorithms. The average RMS error and correlation coefficient between the true (measured) and the estimated articulatory trajectories are 1.227 mm and 0.868 using audiovisual information fusion and GK smoothing, and 1.199 mm and 0.876 using audiovisual information fusion together with PBK smoothing based on a phonetic transcription of the utterance.

Download

On Improving Dynamic State Space Approaches to Articulatory Inversion With MAP-Based Parameter Estimation

IEEE Transactions on Audio, Speech, and Language Processing, 2000

This paper presents a complete framework for articulatory inversion based on jump Markov linear s... more This paper presents a complete framework for articulatory inversion based on jump Markov linear systems (JMLS). In the model, the acoustic measurements and the position of each articulator are considered as observable measurement and continuous-valued hidden state of the system, respectively, and discrete regimes of the system are represented by the use of a discrete-valued hidden modal state. Articulatory inversion based on JMLS involves learning the model parameter set of the system and making inference about the state (position of each articulator) of the system using acoustic measurements. Iterative learning algorithms based on maximum likelihood (ML) and maximum a posteriori (MAP) criteria are proposed to learn the model parameter set of the JMLS. It is shown that the learning procedure of JMLSs is a generalized version of hidden Markov model (HMM) training when both acoustic and articulatory data are given. In this study it is shown that the MAP based learning algorithm improves modeling performance of the system and gives significantly better results compared to ML. The inference stage of the proposed algorithm is based on an interacting multiple models (IMM) approach, and done online (filtering), and/or off-line (smoothing). Formulas are provided for IMMbased JMLS smoothing. It is shown that smoothing significantly improves the performance of articulatory inversion compared to filtering. Several experiments are conducted with the MOCHA database to show the performance of the proposed method. Comparison of the performance of the proposed method with the ones given in the literature shows that the proposed method improves the performance of state space approaches, making state space approaches comparable to the best published results.

Download

Various induction generator schemes for wind-electricity generation

by M. Ermiş, Yildirim Uctug, M. Demirekler, and B. Saribatir

Electric Power Systems Research, 1992

In this paper, various generator types and control systems employed in wind energy conversion sys... more In this paper, various generator types and control systems employed in wind energy conversion systems have been reviewed with particular emphasis on systems including induction generators. Advantages and disadvantages of these systems and relative generator sizes are also discussed. Variable shaft speed schemes employing induction generators have been studied more closely and the important aspects of the findings are emphasized. Throughout the paper, the importance of maximizing the conversion efficiency is stressed. The parameters controlling the energy conversion are identified. Simple methods have been developed to determine the optimum parameters for a constant speed synchronous generator wind energy conversion system and a variable speed squirrel-cage induction generator wind energy conversion system. This last configuration is shown to have advantages from the viewpoint of energy production as well as some other aspects including simplicity and robustness.

Download

M. Demirekler

Uploads

Papers by M. Demirekler

Log In