Publications

@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}}

@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{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}}

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{yeshpanov-varol-2024-kazsandra-kazakh, title = "{K}az{SA}n{DRA}: {K}azakh Sentiment Analysis Dataset of Reviews and Attitudes", author = "Yeshpanov, Rustem and Varol, Huseyin Atakan", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.844", pages = "9657--9667", abstract = "This paper presents KazSAnDRA, a dataset developed for Kazakh sentiment analysis that is the first and largest publicly available dataset of its kind. KazSAnDRA comprises an extensive collection of 180,064 reviews obtained from various sources and includes numerical ratings ranging from 1 to 5, providing a quantitative representation of customer attitudes. The study also pursued the automation of Kazakh sentiment classification through the development and evaluation of four machine learning models trained for both polarity classification and score classification. Experimental analysis included evaluation of the results considering both balanced and imbalanced scenarios. The most successful model attained an F1-score of 0.81 for polarity classification and 0.39 for score classification on the test sets. The dataset and fine-tuned models are open access and available for download under the Creative Commons Attribution 4.0 International License (CC BY 4.0) through our GitHub repository.", }

@inproceedings{abilbekov-etal-2024-kazemotts-dataset, title = "{K}az{E}mo{TTS}: A Dataset for {K}azakh Emotional Text-to-Speech Synthesis", author = "Abilbekov, Adal and Mussakhojayeva, Saida and Yeshpanov, Rustem and Varol, Huseyin Atakan", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.841", pages = "9626--9632", abstract = "This study focuses on the creation of the KazEmoTTS dataset, designed for emotional Kazakh text-to-speech (TTS) applications. KazEmoTTS is a collection of 54,760 audio-text pairs, with a total duration of 74.85 hours, featuring 34.23 hours delivered by a female narrator and 40.62 hours by two male narrators. The list of the emotions considered include {`}neutral{''}, {}angry{''}, {}happy{''}, {}sad{''}, {}scared{''}, and {`}surprised{''}. We also developed a TTS model trained on the KazEmoTTS dataset. Objective and subjective evaluations were employed to assess the quality of synthesized speech, yielding an MCD score within the range of 6.02 to 7.67, alongside a MOS that spanned from 3.51 to 3.57. To facilitate reproducibility and inspire further research, we have made our code, pre-trained model, and dataset accessible in our GitHub repository.", }

@inproceedings{yeshpanov-etal-2024-kazparc-kazakh, title = "{K}az{P}ar{C}: {K}azakh Parallel Corpus for Machine Translation", author = "Yeshpanov, Rustem and Polonskaya, Alina and Varol, Huseyin Atakan", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.842", pages = "9633--9644", abstract = "We introduce KazParC, a parallel corpus designed for machine translation across Kazakh, English, Russian, and Turkish. The first and largest publicly available corpus of its kind, KazParC contains a collection of 371,902 parallel sentences covering different domains and developed with the assistance of human translators. Our research efforts also extend to the development of a neural machine translation model nicknamed Tilmash. Remarkably, the performance of Tilmash is on par with, and in certain instances, surpasses that of industry giants, such as Google Translate and Yandex Translate, as measured by standard evaluation metrics such as BLEU and chrF. Both KazParC and Tilmash are openly available for download under the Creative Commons Attribution 4.0 International License (CC BY 4.0) through our GitHub repository.", }

@inproceedings{yeshpanov-etal-2024-kazqad-kazakh, title = "{K}az{QAD}: {K}azakh Open-Domain Question Answering Dataset", author = "Yeshpanov, Rustem and Efimov, Pavel and Boytsov, Leonid and Shalkarbayuli, Ardak and Braslavski, Pavel", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.843", pages = "9645--9656", abstract = "We introduce KazQAD{---}a Kazakh open-domain question answering (ODQA) dataset{---}that can be used in both reading comprehension and full ODQA settings, as well as for information retrieval experiments. KazQAD contains just under 6,000 unique questions with extracted short answers and nearly 12,000 passage-level relevance judgements. We use a combination of machine translation, Wikipedia search, and in-house manual annotation to ensure annotation efficiency and data quality. The questions come from two sources: translated items from the Natural Questions (NQ) dataset (only for training) and the original Kazakh Unified National Testing (UNT) exam (for development and testing). The accompanying text corpus contains more than 800,000 passages from the Kazakh Wikipedia. As a supplementary dataset, we release around 61,000 question-passage-answer triples from the NQ dataset that have been machine-translated into Kazakh. We develop baseline retrievers and readers that achieve reasonable scores in retrieval (NDCG10 = 0.389 MRR = 0.382), reading comprehension (EM = 38.5 F1 = 54.2), and full ODQA (EM = 17.8 F1 = 28.7) settings. Nevertheless, these results are substantially lower than state-of-the-art results for English QA collections, and we think that there should still be ample room for improvement. We also show that the current OpenAI{'}s ChatGPTv3.5 is not able to answer KazQAD test questions in the closed-book setting with acceptable quality. The dataset is freely available under the Creative Commons licence (CC BY-SA) at url https://github.com/IS2AI/KazQAD", }

@INPROCEEDINGS{10581992, author={Kuzdeuov, Askat and Taratynova, Darya and Tleuliyev, Alim and Varol, Huseyin Atakan}, booktitle={2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)}, title={OpenThermalPose: An Open-Source Annotated Thermal Human Pose Dataset and Initial YOLOv8-Pose Baselines}, year={2024}, volume={}, number={}, pages={1-8}, keywords={Privacy;Annotations;Source coding;Pose estimation;Lighting;Medical services;Motion capture}, doi={10.1109/FG59268.2024.10581992}}

@ARTICLE{10595079, author={Abdrakhmanova, Madina and Yermekova, Assel and Barko, Yuliya and Ryspayev, Vladislav and Jumadildayev, Medet and Varol, Huseyin Atakan}, journal={IEEE Access}, title={One Model to Rule Them all: A Universal Transformer for Biometric Matching}, year={2024}, volume={12}, number={}, pages={96729-96739}, keywords={Transformers;Vectors;Feature extraction;Visualization;Speech recognition;Biological system modeling;Task analysis;Biometrics (access control);Biometric matching;cross-modal matching;face verification;face-audio association;metric learning;multimodal verification;speaker verification;transformer}, doi={10.1109/ACCESS.2024.3426602}}