Publications

@INPROCEEDINGS{10066796, author={Kuzdeuov, Askat and Koishigarina, Darina and Varol, Huseyin Atakan}, booktitle={2023 IEEE International Conference on Big Data and Smart Computing (BigComp)}, title={AnyFace: A Data-Centric Approach For Input-Agnostic Face Detection}, year={2023}, volume={}, number={}, pages={211-218}, doi={10.1109/BigComp57234.2023.00042}}

@Article{nu15071728, AUTHOR = {Karabay, Aknur and Bolatov, Arman and Varol, Huseyin Atakan and Chan, Mei-Yen}, TITLE = {A Central Asian Food Dataset for Personalized Dietary Interventions}, JOURNAL = {Nutrients}, VOLUME = {15}, YEAR = {2023}, NUMBER = {7}, ARTICLE-NUMBER = {1728}, URL = {https://www.mdpi.com/2072-6643/15/7/1728}, ISSN = {2072-6643}, ABSTRACT = {Nowadays, it is common for people to take photographs of every beverage, snack, or meal they eat and then post these photographs on social media platforms. Leveraging these social trends, real-time food recognition and reliable classification of these captured food images can potentially help replace some of the tedious recording and coding of food diaries to enable personalized dietary interventions. Although Central Asian cuisine is culturally and historically distinct, there has been little published data on the food and dietary habits of people in this region. To fill this gap, we aim to create a reliable dataset of regional foods that is easily accessible to both public consumers and researchers. To the best of our knowledge, this is the first work on the creation of a Central Asian Food Dataset (CAFD). The final dataset contains 42 food categories and over 16,000 images of national dishes unique to this region. We achieved a classification accuracy of 88.70% (42 classes) on the CAFD using the ResNet152 neural network model. The food recognition models trained on the CAFD demonstrate the effectiveness and high accuracy of computer vision for dietary assessment.}, DOI = {10.3390/nu15071728} }

@Article{info14020074, AUTHOR = {Mussakhojayeva, Saida and Dauletbek, Kaisar and Yeshpanov, Rustem and Varol, Huseyin Atakan}, TITLE = {Multilingual Speech Recognition for Turkic Languages}, JOURNAL = {Information}, VOLUME = {14}, YEAR = {2023}, NUMBER = {2}, ARTICLE-NUMBER = {74}, URL = {https://www.mdpi.com/2078-2489/14/2/74}, ISSN = {2078-2489}, ABSTRACT = {The primary aim of this study was to contribute to the development of multilingual automatic speech recognition for lower-resourced Turkic languages. Ten languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek—were considered. A total of 22 models were developed (13 monolingual and 9 multilingual). The multilingual models that were trained using joint speech data performed more robustly than the baseline monolingual models, with the best model achieving an average character and word error rate reduction of 56.7%/54.3%, respectively. The results of the experiment showed that character and word error rate reduction was more likely when multilingual models were trained with data from related Turkic languages than when they were developed using data from unrelated, non-Turkic languages, such as English and Russian. The study also presented an open-source Turkish speech corpus. The corpus contains 218.2 h of transcribed speech with 186,171 utterances and is the largest publicly available Turkish dataset of its kind. The datasets and codes used to train the models are available for download from our GitHub page.}, DOI = {10.3390/info14020074} }

@Inbook{Makhataeva2023, author="Makhataeva, Zhanat and Akhmetov, Tolegen and Varol, Huseyin Atakan", editor="Nee, Andrew Yeh Ching and Ong, Soh Khim", title="Augmented Reality for Cognitive Impairments", bookTitle="Springer Handbook of Augmented Reality", year="2023", publisher="Springer International Publishing", address="Cham", pages="765--793", abstract="Augmented reality (AR) is a rapidly developing technology that has introduced new approaches for the design of human technology interaction in various fields. However, application of AR in the area of assistive systems for cognitively impaired people is not deeply studied yet. In this chapter, we investigate the state of the art of AR in assistive systems for the cognitively impaired. Specifically, we will investigate the role of AR during the design, implementation, and performance assessment of perception and memory augmentation assistive systems. We start with a summary of various technologies utilized for the development of AR systems, including sensor and camera technology, data visualization methods, computing paradigms, and intelligent data processing algorithms. Then, we discuss the fundamental mechanisms behind human memory system and look at the examples of the first technology-based human memory and intelligence augmentation systems. We overview various methods for estimation of the human cognitive state and mental workload utilized during the evaluations of such assistive systems in human involved experimental studies. Our main objective in this work is to find out the current status, challenges, and future perspectives of AR in the research of human memory and perception augmentation systems for the people with cognitive impairments.", isbn="978-3-030-67822-7", doi="10.1007/978-3-030-67822-7_31", url="https://doi.org/10.1007/978-3-030-67822-7_31" }

@INPROCEEDINGS{10601292, author={Kuzdeuov, Askat and Nurgaliyev, Shakhizat and Turmakhan, Diana and Laiyk, Nurkhan and Varol, Huseyin Atakan}, booktitle={2023 3rd International Conference on Robotics, Automation and Artificial Intelligence (RAAI)}, title={Speech Command Recognition: Text-to-Speech and Speech Corpus Scraping Are All You Need}, year={2023}, volume={}, number={}, pages={286-291}, keywords={Accuracy;Speech coding;Virtual assistants;Speech recognition;Data collection;Benchmark testing;Data models;Speech commands recognition;text-to-speech;Kazakh Speech Corpus;voice commands;data-centric AI}, doi={10.1109/RAAI59955.2023.10601292}}

@INPROCEEDINGS{10601208, author={Akhmetov, Tolegen and Moger, Gourav and Tursynbek, Iliyas and Atakan Varol, Huseyin}, booktitle={2023 3rd International Conference on Robotics, Automation and Artificial Intelligence (RAAI)}, title={Thermal Perception Using Augmented Reality for Industrial Safety}, year={2023}, volume={}, number={}, pages={91-96}, keywords={Wireless communication;Industries;Visualization;Three-dimensional displays;Thermal factors;Service robots;Cameras;augmented reality;thermal camera;industrial safety;computer vision}, doi={10.1109/RAAI59955.2023.10601208}}

@inproceedings{abdrakhmanova22_odyssey, author={Madina Abdrakhmanova and Saniya Abushakimova and Yerbolat Khassanov and Huseyin Atakan Varol}, title={{A Study of Multimodal Person Verification Using Audio-Visual-Thermal Data}}, year=2022, booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2022)}, pages={233--239}, doi={10.21437/Odyssey.2022-33} }

@ARTICLE{9781417, author={Kuzdeuov, Askat and Aubakirova, Dana and Koishigarina, Darina and Varol, Huseyin Atakan}, journal={IEEE Transactions on Information Forensics and Security}, title={TFW: Annotated Thermal Faces in the Wild Dataset}, year={2022}, volume={17}, number={}, pages={2084-2094}, doi={10.1109/TIFS.2022.3177949}}

@InProceedings{yeshpanov-khassanov-varol:2022:LREC, author = {Yeshpanov, Rustem and Khassanov, Yerbolat and Varol, Huseyin Atakan}, title = {KazNERD: Kazakh Named Entity Recognition Dataset}, booktitle = {Proceedings of the Language Resources and Evaluation Conference}, month = {June}, year = {2022}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {417--426}, abstract = {We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward—but rigorous—rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named entity recognition were also built, with the best-performing model achieving an exact match F1-score of 97.22\% on the test set. The annotated dataset, guidelines, and codes used to train the models are freely available for download under the CC BY 4.0 licence from https://github.com/IS2AI/KazNERD.}, url = {https://aclanthology.org/2022.lrec-1.44} }

@InProceedings{mussakhojayeva-khassanov-varol:2022:LREC, author = {Mussakhojayeva, Saida and Khassanov, Yerbolat and Varol, Huseyin Atakan}, title = {KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics}, booktitle = {Proceedings of the Language Resources and Evaluation Conference}, month = {June}, year = {2022}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {5404--5411}, abstract = {We present an expanded version of our previously released Kazakh text-to-speech (KazakhTTS) synthesis corpus. In the new KazakhTTS2 corpus, the overall size has increased from 93 hours to 271 hours, the number of speakers has risen from two to five (three females and two males), and the topic coverage has been diversified with the help of new sources, including a book and Wikipedia articles. This corpus is necessary for building high-quality TTS systems for Kazakh, a Central Asian agglutinative language from the Turkic family, which presents several linguistic challenges. We describe the corpus construction process and provide the details of the training and evaluation procedures for the TTS system. Our experimental results indicate that the constructed corpus is sufficient to build robust TTS models for real-world applications, with a subjective mean opinion score ranging from 3.6 to 4.2 for all the five speakers. We believe that our corpus will facilitate speech and language research for Kazakh and other Turkic languages, which are widely considered to be low-resource due to the limited availability of free linguistic data. The constructed corpus, code, and pretrained models are publicly available in our GitHub repository.}, url = {https://aclanthology.org/2022.lrec-1.578} }

@INPROCEEDINGS{9863362, author={Baimukashev, Daulet and Rzagaliyev, Yerzhan and Rubagotti, Matteo and Varol, Huseyin Atakan}, booktitle={2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)}, title={Deep Robust Control of a Mechatronic System With Parametric Uncertainties}, year={2022}, volume={}, number={}, pages={1031-1038}, doi={10.1109/AIM52237.2022.9863362}}