Publications

Bissarinova U, Rakhimzhanova T, Kenzhebalin D, Varol HA. Faces in Event Streams (FES): An Annotated Face Dataset for Event Cameras. Sensors. 2024; 24(5):1409. https://doi.org/10.3390/s24051409

@INPROCEEDINGS{10463419, author={Mussakhojayeva, Saida and Gilmullin, Rinat and Khakimov, Bulat and Galimov, Mansur and Orel, Daniil and Adilbekov, Adal and Varol, Huseyin Atakan}, booktitle={2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)}, title={Noise-Robust Multilingual Speech Recognition and the Tatar Speech Corpus}, year={2024}, volume={}, number={}, pages={732-737}, keywords={Codes;Buildings;Focusing;Speech recognition;Noise robustness;Artificial intelligence;Automatic speech recognition}, doi={10.1109/ICAIIC60209.2024.10463419}}

@INPROCEEDINGS{10463261, author={Orel, Daniil and Kuzdeuov, Askat and Gilmullin, Rinat and Khakimov, Bulat and Varol, Huseyin Atakan}, booktitle={2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)}, title={TatarTTS: An Open-Source Text-to-Speech Synthesis Dataset for the Tatar Language}, year={2024}, volume={}, number={}, pages={717-721}, keywords={Training;Globalization;Training data;Coherence;Speech enhancement;Linguistics;Audio recording;Text- to-speech;speech synthesis;low-resource languages;Turkic languages}, doi={10.1109/ICAIIC60209.2024.10463261}}

@INPROCEEDINGS{10463430, author={Kuzdeuov, Askat and Mukayev, Olzhas and Nurgaliyev, Shakhizat and Kunbolsyn, Alisher and Varol, Huseyin Atakan}, booktitle={2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)}, title={ChatGPT for Visually Impaired and Blind}, year={2024}, volume={}, number={}, pages={722-727}, keywords={Voice activity detection;Visualization;Source coding;Oral communication;Blindness;User interfaces;Chatbots}, doi={10.1109/ICAIIC60209.2024.10463430}}

@EMBC 2023, author={Batyr Arystanbekov, Askat Kuzdeuov, Shakhizat Nurgaliyev, and Huseyin Atakan Varol}, booktitle={2023 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)}, title={Image Captioning for Visually Impaired and Blind: A Recipe for Lower-Resourced Languages}, year={2023}, volume={}, number={}, pages={}, doi={10.36227/techrxiv.22133894.v2}

@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" }

@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} }

@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} }

@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}}

@INPROCEEDINGS{10066768, author={Orel, Daniil and Yeshpanov, Rustem and Varol, Huseyin Atakan}, booktitle={2023 IEEE International Conference on Big Data and Smart Computing (BigComp)}, title={Speech Recognition for Turkic Languages Using Cross-Lingual Transfer Learning from Kazakh}, year={2023}, volume={}, number={}, pages={174-182}, doi={10.1109/BigComp57234.2023.00037}}

@inproceedings {yeshpanov23_interspeech, author={Rustem Yeshpanov and Saida Mussakhojayeva and Yerbolat Khassanov}, title={{Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration}}, year=2023, booktitle={Proc. INTERSPEECH 2023}, pages={5521--5525}, doi={10.21437/Interspeech.2023-249} }