Kırbız, Serap

Profile URL
https://hdl.handle.net/20.500.11779/2707
Name Variants
Serap Kırbız & Kirbiz, Serap & Kırbız, S.
Job Title
Email Address
kirbizs@mef.edu.tr
Main Affiliation
02.05. Department of Electrical and Electronics Engineering
Status
Current Staff
Website
ORCID ID
0000-0001-7718-3683
Scopus Author ID
23008580500
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
LPP-8018-2024
Files
1728680416-academic-1400000114.avif (17.06 KB)

Research Topics

Domains
Physical Sciences
Fields
Computer Science
Subfields
Signal ProcessingComputer Vision and Pattern Recognition
Specific Research Areas
Speech and Audio Processing
Music and Audio Processing
Blind Source Separation Techniques
Digital Media Forensic Detection
Advanced Steganography and Watermarking Techniques

Sustainable Development Goals

SDG data is not available
Documents

30

Citations

132

h-index

6

Go to Scopus profile
Documents

29

Citations

86

Go to WoS profile

Publication Collaboration

Affiliation Name Count
Istanbul Technical University 21
MEF University 10
Boğaziçi University 9
Philips (Netherlands) 4
Adobe Systems (United States) 2
1 / 3
Data obtained from OpenAlex
Scholarly Output

14

Articles

7

Views / Downloads

1038/227

Supervised MSc Theses

0

Supervised PhD Theses

0

WoS Citation Count

44

Scopus Citation Count

29

Patents

0

Projects

1

WoS Citations per Publication

3.14

Scopus Citations per Publication

2.07

Open Access Source

5

Supervised Theses

0

JournalCount
IEEE Signal Processing Letters2
2019 27th Signal processing and communications applications conference (SIU)1
2019 27th Signal Processing and Communications Applications Conference (SIU)1
2020 28th Signal Processing and Communications Applications Conference (SIU)1
2023 Innovations in Intelligent Systems and Applications Conference (ASYU)1
Current Page: 1 / 3

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud

Filters

2014 - 201962020 - 20258

Settings

Author of Publication: search.filters.isAuthorOfPublication.552e4b0c-955f-4b93-925b-08cb2e6c5cc0

Scholarly Output Search Results

Now showing 1 - 10 of 14
  • Article
    A Bayesian Allocation Model Based Approach To Mixed Membership Stochastic Blockmodels
    (Taylor and Francis Ltd., 2022-01-31) Kırbız, Serap; Hızlı, Çağlar
    Although detecting communities in networks has attracted considerable recent attention, estimating the number of communities is still an open problem. In this paper, we propose a model, which replicates the generative process of the mixed-membership stochastic block model (MMSB) within the generic allocation framework of Bayesian allocation model (BAM) and BAM-MMSB. In contrast to traditional blockmodels, BAM-MMSB considers the observations as Poisson counts generated by a base Poisson process and marks according to the generative process of MMSB. Moreover, the optimal number of communities for BAM-MMSB is estimated by computing the variational approximations of the marginal likelihood for each model order. Experiments on synthetic and real data sets show that the proposed approach promises a generalized model selection solution that can choose not only the model size but also the most appropriate decomposition.
  • Conference Object
    Citation - WoS: 4
    Citation - Scopus: 4
    Perceptual Coding-Based Informed Source Separation
    (IEEE, 2014) Girin, Laurent; Kırbız, Serap; Ozerov, Alexey; Liutkus, Antoine
    Informed Source Separation (ISS) techniques enable manipulation of the source signals that compose an audio mixture, based on a coder-decoder configuration. Provided the source signals are known at the encoder, a low-bitrate side-information is sent to the decoder and permits to achieve efficient source separation. Recent research has focused on a Coding-based ISS framework, which has an advantage to encode the desired audio objects, while exploiting their mixture in an information-theoretic framework. Here, we show how the perceptual quality of the separated sources can be improved by inserting perceptual source coding techniques in this framework, achieving a continuum of optimal bitrate-perceptual distortion trade-offs.
  • Article
    Citation - WoS: 2
    Improving Facial Emotion Recognition Through Dataset Merging and Balanced Training Strategies
    (Pergamon-Elsevier Science Ltd, 2025-05-01) Kirbiz, Serap
    In this paper, a deep learning framework is proposed for automatic facial emotion based on deep convolutional networks. In order to increase the generalization ability and the robustness of the method, the dataset size is increased by merging three publicly available facial emotion datasets: CK+, FER+ and KDEF. Despite the increase in dataset size, the minority classes still suffer from insufficient number of training samples, leading to data imbalance. The data imbalance problem is minimized by online and offline augmentation techniques and random weighted sampling. Experimental results demonstrate that the proposed method can recognize the seven basic emotions with 82% accuracy. The results demonstrate the effectiveness of the proposed approach in tackling the challenges of data imbalance and improving classification performance in facial emotion recognition.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 1
    İlişkisel Veri Ayrıştırılmasında Model Seçimi
    (IEEE, 2019-04-01) Kırbız, Serap; Cemgil, Taylan; Hızlı, Çağlar
    Abstract—As a fundamental problem in relational data analysis, model selection for relational data factorization is still an open problem. In our work, we propose to estimate model order for mixed membership blockmodels (MMSB) within the generic allocation framework of Bayesian allocation model (BAM). We describe how relational data is represented as Poisson counts of the allocation model, and demonstrate our results both on synthetic and real-world data sets. We believe that the generic allocation perspective promises a generalized model selection solution where we do not only select the model order, but also choose the most appropriate factorization.
  • Master Term Project
    Market Basket Analysis on Retail Stores of Electronic Devices
    (MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Topçu, Feray Ece; Kırbız, Serap
    Market basket analysis is a technique that discovers the relationship between the pairs of products purchased together. It simply analyses the purchase coincidence with the products purchased among the sales transactions and explain what is purchased with what. This study presents a market basket analysis to discover the association rules between products within a dataset that is extracted from one of a leading retail company of electronic devices. The aim is to understand the purchasing behavior trends by examining which products are purchased together. The Apriori algorithm provides the opportunity to discover association rules. Market basket analysis is developed with R Language. R community has a library for association rules that’s called “arules”. Additionally, “arulesViz” and “plotly” libraries are used to visualize the output of analysis. Further steps to this study could be diversification of stores groups through machine learning algorithms and according to this classification, market basket analysis may apply on generated classes of the stores separately. In addition, the output of market basket analysis can be input for a recommendation engine.
  • Article
    Değişimli Oto-Kodlayıcılar kullanarak Diyalog Geliştirme
    (Dergi Park, 2025) Kırbız, Serap
    Bu makalede, kaynak ayrıştırma algoritmalarından faydalanarak birden fazla kaynaktan oluşan ses kayıtlarında konuşma işaretlerini güçlendirmek amacıyla bir yöntem sunulmaktadır. Konuşma sesleri ve diğer sesler arasındaki doğru dengeyi sağlamak, dinleyici şikayetleri arasında sıkça dile getirilen önemli bir sorun olarak öne çıkmaktadır. Bu çalışmada, diyalog içeren ses kayıtlarından diyalogların ayrıştırılmasında negatif olmayan gürültü giderici oto kodlayıcı modelleri kullanılmakta ve bu diyaloglar, diğer seslerle farklı oranlarda yeniden birleştirerek, kullanıcı tercihlerine uygun bir dinleme deneyimi sunulmaktadır. Önerilen yöntem, akan veri üzerinde çalışabilme özelliğine sahip olup, televizyon programları gibi gerçek zamanlı uygulamalara da uyarlanabilmektedir.
  • Conference Object
    Dialogue Enhancement Using Kernel Additive Modelling
    (Institute of Electrical and Electronics Engineers Inc., 2015-05-01) Liutkus, A.; Kırbız, Serap; Cemgil, A. Taylan
    It is a major problem for the sound engineers to find the right balance between the dialogue signals and the ambient sources. This problem also makes one of the main causes of the audience concerns. The audience wants to arrange the sound balance based on their personal preferences, listening environment and their hearing. In this work, a method is proposed for enhancing the dialogue signals in stereo recordings that consist of more than one source. The kernel additive modelling that has been used successfully in sound source separation is used to extract the dialogues and the ambient sources from the movie sounds. The separated dialogue and ambient sources can later be upmixed by the user to make a personal mix. The separation performance of the proposed method is evaluated on the sounds generated by mixing the sources which were taken from the only dialogue and only music parts of the movies. It has been shown that the Kernel Additive Modelling (KAM) based method can be successfully used for dialogue enhancement. © 2015 IEEE.
  • Article
    Citation - WoS: 22
    Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
    (Institute of Electrical and Electronics Engineers (IEEE), 2019-09-01) Kırbız, Serap; Karamatlı, Ertuğ; Cemgil, Ali Taylan; Karamatli, Ertug; Cemgil, Ali Taylan
    In this letter, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isolated sources. Since our method does not require source class labels for every time-frequency bin but only a single label for each source constituting the mixture signal, we call this scenario as weak class supervision. We associate a variational autoencoder (VAE) with each source class within a non negative (compositional) model. Each VAE provides a prior model to identify the signal from its associated class in a sound mixture. After training the model on mixtures, we obtain a generative model for each source class and demonstrate our method on one-second mixtures of utterances of digits from 0 to 9. We show that the separation performance obtained by source class supervision is as good as the performance obtained by source signal supervision.
  • Conference Object
    Joint Source Separation and Classification Using Variational Autoencoders
    (IEEE, 2020-10-05) Karamatlı, Ertuğ; Kırbız, Serap; Hızlı, Çağlar; Cemgil, Ali Taylan
    In this paper, we propose a novel multi-task variational auto encoder (VAE) based approach for joint source separation and classification. The network uses a probabilistic encoder for each sources to map the input data to latent space. The latent representation is then used by a probabilistic decoder for the two tasks: source separation and source classification. Throughout a variety of experiments performed on various image and audio datasets, source separation performance of our method is as good as the method that performs source separation under source class supervision. In addition, the proposed method does not require the class labels and can predict the labels.
  • Conference Object
    Citation - Scopus: 1
    Cnn-Based Emotion Recognition Using Data Augmentation and Preprocessing Methods
    (Institute of Electrical and Electronics Engineers Inc., 2023-10-11) Toktaş, Tolga; Kırbız, Serap; Kayaoğlu, Bora
    In this paper, a system that recognizes emotion from human faces is designed using Convolutional Neural Networks (CNN). CNN is known to perform well when trained with a large database. The lack of large and balanced publicly available databases that can be used by deep learning methods for emotion recognition is still a challenge. To overcome this problem, the number of data is increased by merging FER+, CK+ and KDEF databases; and preprocessing is applied to the face images in order to reduce the variations in the database. Data augmentation methods are used to reduce the imbalance in the data distribution that still remains despite the increasing number of data in the merged database. The CNN-based method developed using database merging, image preprocessing and data augmentation, achieved emotion recognition with 80% accuracy.