Publications

@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} }

@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{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} }

@inproceedings{khassanov-etal-2021-crowdsourced, title = "A Crowdsourced Open-Source {K}azakh Speech Corpus and Initial Speech Recognition Baseline", author = "Khassanov, Yerbolat and Mussakhojayeva, Saida and Mirzakhmetov, Almas and Adiyev, Alen and Nurpeiissov, Mukhamet and Varol, Huseyin Atakan", booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume", month = apr, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.eacl-main.58", pages = "697--706" }

@ARTICLE{9542855, author={Karabay, Aknur and Kuzdeuov, Askat and Ospanova, Shyryn and Lewis, Michael and Varol, Huseyin Atakan}, journal={IEEE Journal of Biomedical and Health Informatics}, title={A Vaccination Simulator for COVID-19: Effective and Sterilizing Immunization Cases}, year={2021}, volume={}, number={}, pages={1-1}, doi={10.1109/JBHI.2021.3114180}}

@InProceedings{10.1007/978-3-030-87802-3_40, author="Musaev, Muhammadjon and Mussakhojayeva, Saida and Khujayorov, Ilyos and Khassanov, Yerbolat and Ochilov, Mannon and Atakan Varol, Huseyin", editor="Karpov, Alexey and Potapova, Rodmonga", title="USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments", booktitle="Speech and Computer", year="2021", publisher="Springer International Publishing", address="Cham", pages="437--447", isbn="978-3-030-87802-3" } CLOSE

@inproceedings{mussakhojayeva21_interspeech, author={Saida Mussakhojayeva and Aigerim Janaliyeva and Almas Mirzakhmetov and Yerbolat Khassanov and Huseyin Atakan Varol}, title={{KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset}}, year=2021, booktitle={Proc. Interspeech 2021}, pages={2786--2790}, doi={10.21437/Interspeech.2021-2124} }

@InProceedings{10.1007/978-3-030-87802-3_41, author="Mussakhojayeva, Saida and Khassanov, Yerbolat and Atakan Varol, Huseyin", editor="Karpov, Alexey and Potapova, Rodmonga", title="A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English", booktitle="Speech and Computer", year="2021", publisher="Springer International Publishing", address="Cham", pages="448--459", isbn="978-3-030-87802-3" }

@ARTICLE{9497674, author={Baimukashev, Daulet and Rakhim, Bexultan and Rubagotti, Matteo and Varol, Huseyin Atakan}, journal={IEEE/ASME Transactions on Mechatronics}, title={End-to-End Deep Fault Tolerant Control}, year={2021}, volume={}, number={}, pages={1-1}, doi={10.1109/TMECH.2021.3100150}}

@INPROCEEDINGS{9630797, author={Karabay, Aknur and Kuzdeuov, Askat and Varol, Huseyin Atakan}, booktitle={2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)}, title={COVID-19 Vaccination Strategies Considering Hesitancy Using Particle-Based Epidemic Simulation}, year={2021}, volume={}, number={}, pages={1985-1988}, doi={10.1109/EMBC46164.2021.9630797}}