Researcher:
Türker, Bekir Berker

Profile Picture
ORCID

Job Title

PhD Student

First Name

Bekir Berker

Last Name

Türker

Name

Name Variants

Türker, Bekir Berker

Email Address

Birth Date

Filters

2014 - 2019132020 - 20235

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.ccff344c-30fc-45ee-a879-47e545e423a3

Search Results

Now showing 1 - 10 of 18
  • Placeholder
    PublicationMetadata only
    Audio-facial laughter detection in naturalistic dyadic conversations
    (Ieee-Inst Electrical Electronics Engineers Inc, 2017) N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Yemez, Yücel; Sezgin, Tevfik Metin; Erzin, Engin; PhD Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 107907; 18632; 34503
    We address the problem of continuous laughter detection over audio-facial input streams obtained from naturalistic dyadic conversations. We first present meticulous annotation of laughters, cross-talks and environmental noise in an audio-facial database with explicit 3D facial mocap data. Using this annotated database, we rigorously investigate the utility of facial information, head movement and audio features for laughter detection. We identify a set of discriminative features using mutual information-based criteria, and show how they can be used with classifiers based on support vector machines (SVMs) and time delay neural networks (TDNNs). Informed by the analysis of the individual modalities, we propose a multimodal fusion setup for laughter detection using different classifier-feature combinations. We also effectively incorporate bagging into our classification pipeline to address the class imbalance problem caused by the scarcity of positive laughter instances. Our results indicate that a combination of TDNNs and SVMs lead to superior detection performance, and bagging effectively addresses data imbalance. Our experiments show that our multimodal approach supported by bagging compares favorably to the state of the art in presence of detrimental factors such as cross-talk, environmental noise, and data imbalance.
  • Placeholder
    PublicationMetadata only
    Affect burst detection using multi-modal cues
    (IEEE, 2015) Department of Computer Engineering; Department of Computer Engineering; N/A; Department of Computer Engineering; N/A; Sezgin, Tevfik Metin; Yemez, Yücel; Türker, Bekir Berker; Erzin, Engin; Marzban, Shabbir; Faculty Member; Faculty Member; PhD Student; Faculty Member; Master Student; Department of Computer Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; College of Engineering; Graduate School of Sciences and Engineering; 18632; 107907; N/A; 34503; N/A
    Recently, affect bursts have gained significant importance in the field of emotion recognition since they can serve as prior in recognising underlying affect bursts. In this paper we propose a data driven approach for detecting affect bursts using multimodal streams of input such as audio and facial landmark points. The proposed Gaussian Mixture Model based method learns each modality independently followed by combining the probabilistic outputs to form a decision. This gives us an edge over feature fusion based methods as it allows us to handle events when one of the modalities is too noisy or not available. We demonstrate robustness of the proposed approach on 'Interactive emotional dyadic motion capture database' (IEMOCAP) which contains realistic and natural dyadic conversations. This database is annotated by three annotators to segment and label affect bursts to be used for training and testing purposes. We also present performance comparison between SVM based methods and GMM based methods for the same configuration of experiments.
  • Placeholder
    PublicationMetadata only
    The JESTKOD database: an affective multimodal database of dyadic interactions
    (Springer, 2017) N/A; N/A; N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Bozkurt, Elif; Khaki, Hossein; Keçeci, Sinan; Türker, Bekir Berker; Yemez, Yücel; Erzin, Engin; PhD Student; PhD Student; Master Student; PhD Student; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; N/A; N/A; N/A; 107907; 34503
    in human-to-human communication, gesture and speech co-exist in time with a tight synchrony, and gestures are often utilized to complement or to emphasize speech. in human-computer interaction systems, natural, Affective and believable use of gestures would be a valuable key component in adopting and emphasizing human-centered aspects. However, natural and affective multimodal data, for studying computational models of gesture and speech, is limited. in this study, we introduce the JESTKOD database, which consists of speech and full-body motion capture data recordings in dyadic interaction setting under agreement and disagreement scenarios. Participants of the dyadic interactions are native Turkish speakers and recordings of each participant are rated in dimensional affect space. We present our multimodal data collection and annotation process, As well as our preliminary experimental studies on agreement/disagreement classification of dyadic interactions using body gesture and speech data. the JESTKOD database provides a valuable asset to investigate gesture and speech towards designing more natural and affective human-computer interaction systems.
  • Placeholder
    PublicationMetadata only
    Audio-visual prediction of head-nod and turn-taking events in dyadic interactions
    (Isca-int Speech Communication assoc, 2018) N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Erzin, Engin; Yemez, Yücel; Sezgin, Tevfik Metin; PhD Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; 34503; 107907; 18632
    Head-nods and turn-taking both significantly contribute conversational dynamics in dyadic interactions. Timely prediction and use of these events is quite valuable for dialog management systems in human-robot interaction. in this study, we present an audio-visual prediction framework for the head-nod and turn taking events that can also be utilized in real-time systems. Prediction systems based on Support vector Machines (SVM) and Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) are trained on human-human conversational data. Unimodal and multi-modal classification performances of head-nod and turn-taking events are reported over the IEMOCaP dataset.
  • Placeholder
    PublicationMetadata only
    Realtime engagement measurement in human-computer interaction
    (Ieee, 2020) N/A; N/A; N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Kesim, Ege; Numanoğlu, Tuğçe; Türker, Bekir Berker; Erzin, Engin; Yemez, Yücel; Sezgin, Tevfik Metin; Master Student; Master Student; PhD Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; N/A; N/A; 34503; 107907; 18632
    Social robots are expected to understand their interlocutors and behave accordingly like humans do. Endowing robots with the capability of monitoring user engagement during their interactions with humans is one of the crucial steps towards achieving this goal. In this work, an interactive game is designed and implemented, which is played with a robot. During the interaction, the user engagement is monitored in realtime via detection of user gaze, turn-taking, laughters/smiles and head nods from audio-visual data. In the experiments conducted, the real-time monitored engagement is found to be consistent with the human-annotated engagement levels.
  • Placeholder
    PublicationMetadata only
    Complaint detection and classification of customer reviews
    (IEEE, 2021) Bayrak, Ahmet Tuğrul; Yıldız, Eray; Özbek, Eyüp Erkan; Türker, Bekir Berker; PhD Student; Graduate School of Sciences and Engineering; N/A
    In a world where competition and technology usage increase consistently, customer satisfaction has become important for companies. In this study, the customer reviews, obtained from the results of the surveys that are made via different channels, are analyzed and when a problem is detected, a quick solution is aimed. For the complaint detection and classification on the customer reviews process, long short-term memory, which is a recurrent neural network, is applied. A data set from the tourism industry is labelled to carry out the proposed method. The results retrieved on performing the method on the data, which is relatively larger than the similar works in literature, are acceptable and the proposed model works in real-time.
  • Placeholder
    PublicationMetadata only
    Analysis of engagement and user experience with a laughter responsive social robot
    (Isca-int Speech Communication assoc, 2017) N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Buçinca, Zana; Erzin, Engin; Yemez, Yücel; Sezgin, Tevfik Metin; PhD Student; Master Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; N/A; 34503; 107907; 18632
    We explore the effect of laughter perception and response in terms of engagement in human-robot interaction. We designed two distinct experiments in which the robot has two modes: laughter responsive and laughter non-responsive. in responsive mode, the robot detects laughter using a multimodal real-time laughter detection module and invokes laughter as a backchannel to users accordingly. in non-responsive mode, robot has no utilization of detection, thus provides no feedback. in the experimental design, we use a straightforward question-answer based interaction scenario using a back-projected robot head. We evaluate the interactions with objective and subjective measurements of engagement and user experience.
  • Placeholder
    PublicationMetadata only
    Affect burst recognition using multi-modal cues
    (IEEE Computer Society, 2014) N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Marzban, Shabbir; Erzin, Engin; Yemez, Yücel; Sezgin, Tevfik Metin; PhD Student; Master Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; N/A; 34503; 107907; 18632
    Affect bursts, which are nonverbal expressions of emotions in conversations, play a critical role in analyzing affective states. Although there exist a number of methods on affect burst detection and recognition using only audio information, little effort has been spent for combining cues in a multi-modal setup. We suggest that facial gestures constitute a key component to characterize affect bursts, and hence have potential for more robust affect burst detection and recognition. We take a data-driven approach to characterize affect bursts using Hidden Markov Models (HMM), and employ a multimodal decision fusion scheme that combines cues from audio and facial gestures for classification of affect bursts. We demonstrate the contribution of facial gestures to affect burst recognition by conducting experiments on an audiovisual database which comprise speech and facial motion data belonging to various dyadic conversations.
  • Placeholder
    PublicationMetadata only
    Real-time audiovisual laughter detection
    (Ieee, 2017) N/A; N/A; N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Türker, Bekir Berker; Buçinca, Zana; Sezgin, Tevfik Metin; Yemez, Yücel; Erzin, Engin; PhD Student; Master Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; N/A; 18632; 107907; 34503
    Laughter detection is an essential aspect towards effective human-computer interaction. This work primarily addresses the problem of laughter detection in a real-time environment. We utilize annotated audio and visual data collected from a Kinect sensor to identify discriminative features for audio and video, separately. We show how the features can be used with classifiers such as support vector machines (SVM). The two modalities are then fused into a single output to form a decision. We test our setup by emulating real-time data with Kinect sensor, and compare the results with the offline version of the setup. Our results indicate that our laughter detection system gives a promising performance for a real-time human-computer interactions.
  • Placeholder
    PublicationMetadata only
    Typo correction in domain-specific texts using FastText
    (Institute of Electrical and Electronics Engineers Inc., 2020) Bayrak, Ahmet Tuğrul; N/A; Türker, Bekir Berker; PhD Student; Graduate School of Sciences and Engineering; N/A
    Analyzing customer reviews are quite important for customer satisfaction. Customer reviews might contain spelling mistakes, which causes data pollution and decreases the efficiency of the analyzes. In this study, a domain-specific solution is proposed by using the data related to tourism. Even if there are several applications to correct typos in Turkish, domain-specific solutions are limited. Since a correction should be specific for the meaning of a typo, this study is required. For the study, a FastText model-oriented typo correction algorithm has been developed by using customer reviews in the tourism industry. The results are compared with a commonly used correction application and it is observed that the algorithm developed is more successful for correcting typos in tourism specific phrases.